system

Abstract

We provide the system. [Solution] Means for acquiring video data and desired conditions, A means of recommending appropriate facilities according to the desired conditions, A means for generating an image based on the video data, A means for processing reservations for the facility, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When choosing a wedding venue, it is difficult to efficiently find an optimal venue that meets the conditions desired by the user. Furthermore, there is a problem that it is difficult for the user to specifically imagine the atmosphere of the venue in advance. Along with this, it is required to consistently manage the selection and reservation procedures of the venue to reduce the burden on the user.

Means for Solving the Problems

[0005] This invention includes means for acquiring video data and conditions related to the desired wedding from the user. Furthermore, it includes means for recommending a suitable wedding venue based on the acquired conditions. In addition, it provides means for generating an image of the wedding ceremony at the selected venue based on the user's video data and presenting it to the user. It also includes means for processing a reservation for the recommended venue. Through this series of means, the user can efficiently select a wedding venue that suits their wishes and have a clear image of it in advance.

[0006] "Video data" refers to image and video information obtained from users, and is used to generate wedding imagery.

[0007] "Desired conditions" refer to information that indicates the user's specific requests regarding the style of wedding, location, budget, and other details.

[0008] A "facility" refers to a place or venue where weddings and related events can be held.

[0009] "Recommendation" is the process of presenting appropriate options based on the user's preferences.

[0010] An "image rendering" is a visual representation generated based on acquired video data, allowing users to virtually experience a wedding ceremony.

[0011] "Reservation processing" refers to a series of procedures for securing and coordinating a facility selected by the user.

[0012] "System" refers to information processing equipment and software that include the means described above and are used to smoothly carry out a series of processes. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the processor with a reference numeral (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0017] In the following embodiments, the RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the communication I / F (Interface) with a reference numeral is an interface including a communication processor and 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), or Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] As one embodiment of the present invention, an AI agent-based system for supporting the selection of wedding venues is provided. This system includes a process of selecting the most suitable venue for the user's needs using the user's desired wedding conditions and video data, and then making a reservation.

[0035] First, users input information such as location, style, and budget as their desired wedding conditions via a terminal. In addition, users upload photos and related video data to the system. This allows the system to identify the user's individual needs and gather the necessary materials to generate a concrete image.

[0036] Next, the server receives these input conditions and video data and matches them against wedding venue data in the database. In this step, a recommendation engine is used to suggest several optimal venues based on past data and the preferences of similar users.

[0037] Subsequently, the server uses image generation AI to create wedding ceremony images for each proposed venue based on the video data provided by the user. This allows the user to visually confirm a concrete image of the wedding ceremony.

[0038] The suggested information is provided to the user through the terminal's user interface. Based on the displayed information, the user can determine which venue best matches their ideal and view detailed information. If the user wishes to make a reservation for their chosen venue, the server will automatically proceed with the reservation process based on instructions from the terminal. Once the reservation is complete, the server will notify the user of the details and update the reservation information.

[0039] Finally, after using the service, users can submit feedback via their device. This feedback is analyzed on the server and used to improve the accuracy of the recommendation engine and enhance the service.

[0040] This system allows users to efficiently discover, visualize, and book wedding venues that meet their preferences. This integrated service process significantly simplifies the traditional, time-consuming process of choosing a venue, improving user convenience.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Users enter their desired wedding conditions (location, style, budget) via their device and upload photos and related video data. The entered information is then sent to the server.

[0044] Step 2:

[0045] The server receives data from the user and stores it in the database. It validates the entered conditions and returns error messages to the terminal as needed.

[0046] Step 3:

[0047] The server's recommendation engine searches the database for wedding venue information based on the user's preferences, selects several suitable venues, and lists them.

[0048] Step 4:

[0049] The server uses image generation AI to create wedding images for each proposed venue based on the user's facial photograph. These generated images are temporarily stored.

[0050] Step 5:

[0051] The terminal displays a list of wedding venues received from the server, along with generated image files, to the user. It provides an interface for the user to select a venue of interest and view details.

[0052] Step 6:

[0053] If a user wishes to make a reservation for a wedding venue they have selected, they submit a reservation request from their device. The server receives this request and begins the reservation process with the venue.

[0054] Step 7:

[0055] If a reservation is secured, the server notifies the user of its details. At the same time, it records the user's reservation information in the database.

[0056] Step 8:

[0057] After using the service, users submit feedback from their devices. The server collects this feedback and uses it to improve the recommendation engine and the overall system.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In recent years, there has been a growing demand for facility selection based on individualized criteria, and recommending facilities that accurately meet the needs of users is particularly difficult for important events such as weddings. Furthermore, there is a lack of systems that enable users to form a concrete image of what they want based on the information provided and make selections accordingly. In addition, there is a need to provide a smooth way to make reservations at selected facilities.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for acquiring information data and desired conditions, means equipped with a computing device for recommending appropriate facilities, means including a learning algorithm, means for utilizing a generative model, and means for automatically performing processing on facilities. This enables the recommendation of optimal facilities based on the user's desired conditions and the formation of concrete images utilizing the generated visual images, and then enables rapid reservation processing for the selected facilities.

[0063] "Information data" refers to all data, including user-provided preferences and video materials.

[0064] "Desired conditions" refer to information that represents the specific requirements and attributes of the facilities and services that the user is looking for.

[0065] "Computing equipment" refers to devices including computers and their peripherals used for data processing and analysis.

[0066] A "learning algorithm" is a mathematical method or model used to find patterns in data and predict the optimal outcome.

[0067] A "generative model" refers to a technology that includes algorithms for generating new data or images based on input data.

[0068] "Processing a facility" refers to a series of operations, including making reservations and arrangements for the facility selected by the user.

[0069] This invention is implemented as a system for users to efficiently select and reserve facilities that meet their specific requirements. Users first input their desired conditions and video data via a terminal. This information is then transmitted to a server.

[0070] The server first receives this information data and then uses computing devices to analyze it. Specifically, it processes the input data using learning algorithms and compares it with past user data in the database to identify the appropriate facility. This calculation uses machine learning libraries and database management systems, and is often implemented using software such as Python or SQL.

[0071] Next, the server uses a generative model to generate visual images from the video data. This generation process utilizes a generative AI model to concretize the visual representation of events at the target facility. The generative AI models used include image generation tools and APIs provided as open-source libraries.

[0072] As a concrete example, suppose a couple inputs conditions such as "a garden-style wedding in Tokyo, with a budget of under 3 million yen." The server receives these conditions as a prompt and presents them to the generative model in the form of "generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo."

[0073] The visual images generated in this way are presented to the user via the device and serve as information to support the optimal selection. If the user selects a facility they like, the server automatically initiates the reservation process for that facility, providing a smooth user experience.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user uses a terminal to input wedding details (e.g., region, style, budget) and video data (e.g., portraits). This data is sent from the terminal to the server. The input data arrives on the server as text and image data and is then sent directly to the next processing step.

[0077] Step 2:

[0078] The server analyzes the received information data. Using a computing device, it matches the desired conditions with past user data in the database and generates a list of optimal facilities based on this. This process utilizes machine learning algorithms to score facilities that meet the conditions and outputs the results.

[0079] Step 3:

[0080] The server uses a generative AI model to generate visual images based on video data provided by the user. A prompt (e.g., "Generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo") is input to the generative AI model, and the model outputs an image that combines the video data with the given conditions.

[0081] Step 4:

[0082] The server sends the generated visual image and a list of facilities to the terminal. The terminal then presents this information to the user, who selects facilities while viewing the visual image. The selection results are sent back to the server via the terminal.

[0083] Step 5:

[0084] When a user wishes to make a reservation for a selected facility, they send that information to the server via their device. The server receives the reservation information and automatically proceeds with the reservation process for the selected facility. This process includes confirming and registering the date, time, and user information, and outputs the results as a notification.

[0085] Step 6:

[0086] Once the reservation is complete, the server will notify the user of the details (e.g., reservation number, date and time). This information will be sent via the terminal, allowing the user to confirm the reservation details.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] In e-commerce and service selection, users typically spend considerable time and effort choosing the right option from a multitude of choices. Furthermore, a lack of consistent and efficient payment processing methods for selected services and products can detract from the user experience. There is a need to address these challenges and provide a system that enables quick and efficient service selection and payment processes.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for acquiring video information and desired requirements, means for recommending appropriate facilities according to the desired requirements, means for generating an image based on the video information, and means for performing an automatic payment procedure according to the user's selection. This enables the user to efficiently and easily select the desired service and perform a seamless payment procedure.

[0092] "Visual information" refers to visual data such as facial photos and videos provided by users, and is used to clarify individual needs and images when selecting services or products.

[0093] "Desired requirements" refer to specific conditions such as the user's preferred region, style, and budget, and are used as criteria when selecting recommended services and products.

[0094] "Means of recommending appropriate facilities" refers to an internal system function that identifies and suggests the most suitable facility or service from a number of options based on the user's desired requirements.

[0095] "Means of generating images" refers to image generation technologies and processes used to visualize specific usage scenarios in proposed facilities and services based on video information provided by the user.

[0096] "Means of processing reservations" refers to the procedures that the system automatically performs to confirm and secure the date, time, and conditions for the facility or service selected by the user.

[0097] "Means of performing automatic payment procedures" refers to a processing function that automatically completes payment for the service selected by the user using pre-registered payment information.

[0098] This invention is a system for efficiently enabling users to select desired services or products and complete payment procedures. The server first receives video information and desired requirements from the user's terminal. The video information consists of visual data such as facial photos and videos provided by the user, while the desired requirements include specific conditions such as region, style, and budget.

[0099] Next, the server recommends suitable facilities based on the acquired preferences. This involves a process that uses a recommendation engine to refer to past data and the preferences of similar users to identify the best options. Furthermore, a generative AI model is used to generate images that visualize specific usage scenarios for the suggested facilities and services based on the video information.

[0100] The user then reviews and selects the options presented through the terminal. The server processes the reservation and automatic payment for the facility or service based on the user's selection. At this stage, an appropriate payment gateway is used to securely process the registered payment information.

[0101] As a concrete example, consider a scenario where a user uses a travel booking app to plan their honeymoon. The user inputs their destination, budget, and preferred style of stay, and the app uses AI to suggest options for sightseeing, accommodation, and activities. The user then reviews a visualized image of their chosen honeymoon, and the booking and payment are completed instantly.

[0102] Examples of prompts for a generative AI model:

[0103] "Please choose from the following honeymoon packages: Island Resort Package, City Sightseeing Package, or Mountain Retreat Package. We will then process your payment quickly."

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] Users input video information and desired requirements into the system using a terminal. The input includes the user's facial photograph and video data (video information), as well as desired conditions such as region, style, and budget. This data is sent from the terminal to the server, where its integrity is first verified. This information is then used as the basic data for system operation.

[0107] Step 2:

[0108] The server recommends appropriate facilities and services based on the received preferences. At this stage, a recommendation engine is used, matching the entered preferences with past data and similar cases in the database. This extracts the best service options and generates a list of recommendations to present to the user.

[0109] Step 3:

[0110] The server uses a generative AI model to generate images based on video information provided by the user. In this process, the received video information is used as material to generate images of specific usage scenarios at recommended facilities and services. This step utilizes image generation algorithms to create visually impressive content.

[0111] Step 4:

[0112] The user reviews the server-generated image and recommended options through their terminal. This is where the user interface comes into play, enabling the user to make choices easily and intuitively. The interface displays images, clarifies the user's options, and guides them to the next step.

[0113] Step 5:

[0114] Once the user makes a selection, the server automatically initiates the booking process for the selected facility or service. Simultaneously, an automated payment process is initiated using the registered payment information. The server uses a secure payment gateway to ensure reliable settlement. This confirms the booking, and the user is notified of its details.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] As an embodiment of the present invention, a system is provided that combines an AI agent-based support system for selecting a wedding venue with an emotion engine that recognizes the user's emotions. This system can propose facilities that meet the user's preferences and carry out the entire process, from selection to booking, while taking emotional information into consideration.

[0117] First, the user enters their desired wedding conditions through their device and uploads photos and video data. Additionally, the device's built-in camera and microphone are used by an emotion engine to analyze the user's facial expressions and voice in real time, recognizing their current emotional state. This data, along with the user's desired conditions, is then sent to the server.

[0118] The server matches the received conditions and emotion data with wedding venue information in the database. The recommendation engine generates a list of suitable venues based on the user's preferences and emotions. Emotional information is also used to adjust the recommendations; for example, if the user feels joy, the system suggests elements that further emphasize that emotion.

[0119] The server uses image generation AI to create wedding images for suggested venues based on the user's facial photo and emotions. These images reflect emotional information; for example, if the user is judged to be satisfied, a brighter tone and more emotionally charged presentation can be set.

[0120] The generated list of wedding venues and their images are displayed to the user via their device. The user can visually confirm concrete images and, based on the presented information, select a venue, allowing for a more satisfying decision. Furthermore, if the user's emotions change during the selection process, the server can detect this and immediately adjust the suggestions.

[0121] The user requests a reservation from their terminal for the wedding venue they have selected. The server processes the reservation accordingly and notifies the user upon completion. Furthermore, the feedback received can be used to improve the overall system and enhance the accuracy of the emotion engine.

[0122] Through this format, a personalized venue selection experience that takes user emotions into account is provided, enabling users to make more satisfying choices.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] Users input their wedding preferences (location, style, budget) through their device and upload photos and related video data. The input from the device is transmitted to the server, and at the same time, the device uses its camera and microphone to collect the user's facial expressions and voice, generating emotion data in real time.

[0126] Step 2:

[0127] The server collects user preferences, video data, and emotional data received from the user and stores them in a database. This allows for data integration and lays the foundation for further processing.

[0128] Step 3:

[0129] The recommendation engine on the server searches the database, taking into account the user's preferences and emotional state. Emotional data is used for scoring to determine which venue best matches the user's current emotional state, and a list of recommended venues is generated.

[0130] Step 4:

[0131] The server's image generation AI creates wedding images for each proposed venue based on the user's facial photo and emotional data. Based on the emotional information, the image is adjusted; for example, if the user is nervous, a relaxed atmosphere is emphasized.

[0132] Step 5:

[0133] The terminal displays a list of suggested venues received from the server, along with generated image files, to the user. The user receives visual feedback, selects the venue they are most interested in, and is provided with an interactive interface to view detailed information and suggestions.

[0134] Step 6:

[0135] If a user wishes to make a reservation for a selected venue, they submit a reservation request from their device. The server accepts this request and proceeds with the reservation process with the relevant venue. Once the reservation is complete, the server notifies the user of the details.

[0136] Step 7:

[0137] After using the system, users provide feedback on the service through their device. This feedback is sent to the server and used to improve the accuracy of the sentiment engine and recommendation engine.

[0138] (Example 2)

[0139] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0140] Traditional venue selection and booking systems simply offered suggestions based on conditions, without considering the user's emotional state. As a result, they failed to make choices that suited the user's feelings and desires, leading to decreased satisfaction. Furthermore, the lack of visual representation made it difficult for users to form concrete images of their choices.

[0141] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0142] In this invention, the server includes means for acquiring video information and specification conditions, means for analyzing emotional states using a terminal, and means for recommending appropriate locations based on the user's specification conditions and emotional state. This enables personalized facility selection that takes into account the user's emotions and allows for highly satisfying choices.

[0143] "Video information" refers to facial images and video data acquired by the device, and is used to analyze the user's emotional state.

[0144] "Specification conditions" refer to information about desired facilities and conditions entered by the user, and are factors that influence the recommendation results.

[0145] "Device" refers to a device used by a user to input information or analyze emotional data, and includes smartphones and tablets.

[0146] "Emotional state" refers to the user's facial expressions and voice, which are analyzed in real time by the emotion engine, and is a useful element for customizing recommendation results.

[0147] A "suitable location" refers to a facility recommended by the server based on the user's specifications and emotional state, with the aim of increasing user satisfaction.

[0148] "Visual information" refers to images created by a generative AI model based on video information and emotional states, enabling users to form a concrete image of the facility.

[0149] "Reservation processing" refers to the procedure in which the server confirms a reservation for a specified location based on the user's selection, and has the function of notifying the user of the result.

[0150] "Opinions" refers to feedback from users, including evaluations and suggestions for improvement regarding recommendations and visual information.

[0151] This invention is a system to support personalized wedding venue selection that takes into account the user's emotions. Based on the user's desired conditions and emotional state, this system suggests suitable wedding venues and supports the booking process.

[0152] First, the user uses the device to input their specific wedding preferences. These preferences include specifications such as "a venue by the sea" and "accommodates up to 100 people." The device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine to determine their current emotional state. If the user is smiling, the system recognizes this as "enjoying themselves."

[0153] This information is sent directly to the server. The server then compares the received specifications and emotional state with a database in the cloud. A recommendation engine then operates to suggest appropriate facilities, generating a list of facilities tailored to the user's conditions and emotions. Specifically, if the user desires a calm atmosphere, it will recommend places where they can relax.

[0154] Next, the server utilizes a generative AI model to create a wedding image at the suggested wedding venue, based on the user's facial photo and emotional information. This image reflects the user's emotional state, such as enjoyment, and for example, a visual with bright colors is generated.

[0155] The generated list of venues and visual information are presented to the user via the terminal. The user can select a venue based on this visual information. An example of a prompt message that can be input to the generating AI model is, "I'm looking for a wedding venue with a natural and homey atmosphere. I'm very happy right now. Please generate images of a wedding that meets these criteria."

[0156] Once a facility is selected, the user submits a reservation request from their terminal, and the server processes the reservation. The system also collects user feedback to improve the overall system and enhance the accuracy of the sentiment engine. This allows users to make more satisfying choices.

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The user enters their desired wedding conditions through a terminal. This input includes specific specifications such as "a venue by the sea" or "a casual atmosphere." The input data is retrieved through the terminal's interface and converted into a format that can be processed.

[0160] Step 2:

[0161] The device uses its built-in camera and microphone to record the user's facial expressions and voice in real time. Based on this, an emotion engine analyzes the data and recognizes the user's emotional state. For example, if the user is smiling, it generates emotion data indicating "enjoying themselves." This analysis result is then prepared to be sent to the server as output.

[0162] Step 3:

[0163] The server receives specification conditions and emotional data sent from the terminal. This input data is used to compare it with wedding venue information in the database. The recommendation engine analyzes this and selects venues that are suitable for the specification conditions and emotional state. For example, if the user is looking for a relaxed atmosphere, the server will generate a list of such venues.

[0164] Step 4:

[0165] The server utilizes a generative AI model to generate specific wedding images based on the user's facial photograph and emotional data. This calculation is based on the facial photograph; for example, if the user has positive emotions, the generated image will also have bright colors. The result is output as an image file and sent to the terminal.

[0166] Step 5:

[0167] The terminal displays a list of facilities and wedding ceremony images sent from the server to the user. The user makes a decision based on this information and notifies the system of their selected facility. For example, if a bright wedding ceremony image with the sea as a background is presented, the user will proceed with their selection accordingly.

[0168] Step 6:

[0169] The user sends a reservation request from their device to the facility they selected. The server receives this request and processes the reservation with the facility. Once the process is complete, the user is notified of the result via a confirmation message.

[0170] Step 7:

[0171] After a reservation is confirmed, the server collects feedback from the user. This feedback is used to improve user satisfaction and the accuracy of suggestions, and helps to improve the sentiment engine and recommendation engine.

[0172] (Application Example 2)

[0173] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0174] In the modern shopping experience, providing personalized recommendations that reflect users' emotions and preferences is challenging. Current technologies have limitations in accurately assessing a user's emotional state and incorporating that feedback in real time. This results in users having very limited information to make the best choices, leading to a lower quality of the experience.

[0175] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0176] In this invention, the server includes means for acquiring video data and desired conditions, means for recommending an appropriate installation location according to the desired conditions, means for generating an image based on the video data, means for analyzing the user's emotional state, means for adjusting the recommendation content based on the analysis results, and means for processing a reservation for the installation location. This enables dynamic recommendations that respond to the user's emotional state, providing a more personalized purchasing experience.

[0177] "Video data" refers to visual information acquired to analyze the user's emotional state.

[0178] "Desired conditions" refer to the requirements and preferences specified by the user when using the system, and are used in selecting recommended installation locations.

[0179] "Installation location" refers to facilities or stores recommended based on the user's preferences and emotional state.

[0180] An "image rendering" is generated based on acquired video data and provides a visual representation of the experience and product at the installation location.

[0181] "Emotional state" refers to the user's psychological state, identified by analyzing their facial expressions and tone of voice.

[0182] "Recommendations" refer to appropriate installation locations and product information presented based on the user's desired conditions and analyzed emotional state.

[0183] "Reservation processing" refers to the process of handling procedures and confirmations related to the installation location selected by the user.

[0184] In this configuration, when a user accesses the service via a smart device, video and audio data are first acquired using the device's built-in camera and microphone. This data is sent to an emotion recognition engine, which analyzes the user's emotional state based on their facial expressions and voice pitch. Software such as Affectiva and Microsoft® Azure® Cognitive Services are used for emotion recognition.

[0185] Next, the server receives this data in real time, along with the user's input preferences, and performs analysis to recommend the optimal installation location. During this process, a Recommendation Engine (e.g., Apache® Mahout) is used to provide dynamic recommendations tailored to the user's preferences and emotions.

[0186] The server uses a generative AI model based on the acquired video data to synthesize imagery that realistically recreates the experience at the installation site. This allows users to have a more concrete and visual experience. For example, Python could be used with TENSORFLOW® or PyTorch.

[0187] This image is displayed on a smart device's screen, and the user selects an installation location based on the presented content through emotion recognition. Once the selection is made, the server executes a reservation procedure for the selected installation location. This process is hosted on a cloud system.

[0188] For example, in a virtual bookstore, the system could capture the emotions of users who show interest in the cover of a book they are browsing and display recommended books from related genres and publishers. This also allows for personalized promotions based on those emotions.

[0189] An example of a prompt for a generative AI model might be: "Create a script that suggests related products for items in which the user has shown a joyful expression, and provide the most appealing product information in real time based on the user's emotional data."

[0190] This invention makes it possible to provide users with personalized experiences and achieve higher satisfaction levels.

[0191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0192] Step 1:

[0193] The device uses its camera and microphone to acquire video and audio data of the user in real time. This data is prepared as input for the emotion recognition engine. Specifically, it captures the user's facial expressions and voice pitch, and uses this data during the session without saving it to a database.

[0194] Step 2:

[0195] The device sends the acquired video and audio data to an emotion recognition engine. This engine analyzes the acquired data and identifies the user's emotional state. Using software such as Microsoft Azure Cognitive Services, it performs the analysis and outputs the results as an emotional state such as "joy," "interest," or "surprise."

[0196] Step 3:

[0197] The server matches the user's desired conditions with the emotional state obtained in step 2 against the database and generates a list of installation locations using the Recommendation Engine. Using desired conditions and emotional state as input, it lists appropriate installation locations based on the analysis results.

[0198] Step 4:

[0199] The server creates image data using a generative AI model. It takes user preferences, emotional states, and installation location data as input to output an image that simulates the experience at the installation location. Image generation is performed using TensorFlow or PyTorch.

[0200] Step 5:

[0201] The terminal displays a list of installation locations and image files received from the server to the user. This display is done via a user interface, allowing the user to visually review the images and select a more appropriate installation location based on emotional information.

[0202] Step 6:

[0203] The terminal proceeds with the reservation process for the installation location selected by the user. At this stage, the server confirms the reservation on the cloud system in response to the user's request and outputs a completion message to the terminal.

[0204] Step 7:

[0205] The server collects user feedback and stores it in a database. This helps improve the accuracy of the Recommendation Engine and emotion recognition engine, contributing to overall system improvement. This process will lead to improved user experience in the future.

[0206] The processing steps described above enable a personalized experience based on the user's emotions and preferences.

[0207] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0208] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0209] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0213] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0214] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0215] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0216] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0217] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0218] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0219] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0220] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0221] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0222] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0223] As one embodiment of the present invention, an AI agent-based system for supporting the selection of wedding venues is provided. This system includes a process of selecting the most suitable venue for the user's needs using the user's desired wedding conditions and video data, and then making a reservation.

[0224] First, users input information such as location, style, and budget as their desired wedding conditions via a terminal. In addition, users upload photos and related video data to the system. This allows the system to identify the user's individual needs and gather the necessary materials to generate a concrete image.

[0225] Next, the server receives these input conditions and video data and matches them against wedding venue data in the database. In this step, a recommendation engine is used to suggest several optimal venues based on past data and the preferences of similar users.

[0226] Subsequently, the server uses image generation AI to create wedding ceremony images for each proposed venue based on the video data provided by the user. This allows the user to visually confirm a concrete image of the wedding ceremony.

[0227] The suggested information is provided to the user through the terminal's user interface. Based on the displayed information, the user can determine which venue best matches their ideal and view detailed information. If the user wishes to make a reservation for their chosen venue, the server will automatically proceed with the reservation process based on instructions from the terminal. Once the reservation is complete, the server will notify the user of the details and update the reservation information.

[0228] Finally, after using the service, users can submit feedback via their device. This feedback is analyzed on the server and used to improve the accuracy of the recommendation engine and enhance the service.

[0229] This system allows users to efficiently discover, visualize, and book wedding venues that meet their preferences. This integrated service process significantly simplifies the traditional, time-consuming process of choosing a venue, improving user convenience.

[0230] The following describes the processing flow.

[0231] Step 1:

[0232] Users enter their desired wedding conditions (location, style, budget) via their device and upload photos and related video data. The entered information is then sent to the server.

[0233] Step 2:

[0234] The server receives data from the user and stores it in the database. It validates the entered conditions and returns error messages to the terminal as needed.

[0235] Step 3:

[0236] The server's recommendation engine searches the database for wedding venue information based on the user's preferences, selects several suitable venues, and lists them.

[0237] Step 4:

[0238] The server uses image generation AI to create wedding images for each proposed venue based on the user's facial photograph. These generated images are temporarily stored.

[0239] Step 5:

[0240] The terminal displays a list of wedding venues received from the server, along with generated image files, to the user. It provides an interface for the user to select a venue of interest and view details.

[0241] Step 6:

[0242] If a user wishes to make a reservation for a wedding venue they have selected, they submit a reservation request from their device. The server receives this request and begins the reservation process with the venue.

[0243] Step 7:

[0244] If a reservation is secured, the server notifies the user of its details. At the same time, it records the user's reservation information in the database.

[0245] Step 8:

[0246] After using the service, users submit feedback from their devices. The server collects this feedback and uses it to improve the recommendation engine and the overall system.

[0247] (Example 1)

[0248] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0249] In recent years, there has been a growing demand for facility selection based on individualized criteria, and recommending facilities that accurately meet the needs of users is particularly difficult for important events such as weddings. Furthermore, there is a lack of systems that enable users to form a concrete image of what they want based on the information provided and make selections accordingly. In addition, there is a need to provide a smooth way to make reservations at selected facilities.

[0250] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0251] In this invention, the server includes means for acquiring information data and desired conditions, means equipped with a computing device for recommending appropriate facilities, means including a learning algorithm, means for utilizing a generative model, and means for automatically performing processing on facilities. This enables the recommendation of optimal facilities based on the user's desired conditions and the formation of concrete images utilizing the generated visual images, and then enables rapid reservation processing for the selected facilities.

[0252] "Information data" refers to all data, including user-provided preferences and video materials.

[0253] "Desired conditions" refer to information that represents the specific requirements and attributes of the facilities and services that the user is looking for.

[0254] "Computing equipment" refers to devices including computers and their peripherals used for data processing and analysis.

[0255] A "learning algorithm" is a mathematical method or model used to find patterns in data and predict the optimal outcome.

[0256] A "generative model" refers to a technology that includes algorithms for generating new data or images based on input data.

[0257] "Processing a facility" refers to a series of operations, including making reservations and arrangements for the facility selected by the user.

[0258] This invention is implemented as a system for users to efficiently select and reserve facilities that meet their specific requirements. Users first input their desired conditions and video data via a terminal. This information is then transmitted to a server.

[0259] The server first receives this information data and then uses computing devices to analyze it. Specifically, it processes the input data using learning algorithms and compares it with past user data in the database to identify the appropriate facility. This calculation uses machine learning libraries and database management systems, and is often implemented using software such as Python or SQL.

[0260] Next, the server uses a generative model to generate visual images from the video data. This generation process utilizes a generative AI model to concretize the visual representation of events at the target facility. The generative AI models used include image generation tools and APIs provided as open-source libraries.

[0261] As a concrete example, suppose a couple inputs conditions such as "a garden-style wedding in Tokyo, with a budget of under 3 million yen." The server receives these conditions as a prompt and presents them to the generative model in the form of "generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo."

[0262] The visual images generated in this way are presented to the user via the device and serve as information to support the optimal selection. If the user selects a facility they like, the server automatically initiates the reservation process for that facility, providing a smooth user experience.

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The user uses a terminal to input wedding details (e.g., region, style, budget) and video data (e.g., portraits). This data is sent from the terminal to the server. The input data arrives on the server as text and image data and is then sent directly to the next processing step.

[0266] Step 2:

[0267] The server analyzes the received information data. Using a computing device, it matches the desired conditions with past user data in the database and generates a list of optimal facilities based on this. This process utilizes machine learning algorithms to score facilities that meet the conditions and outputs the results.

[0268] Step 3:

[0269] The server uses a generative AI model to generate visual images based on video data provided by the user. A prompt (e.g., "Generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo") is input to the generative AI model, and the model outputs an image that combines the video data with the given conditions.

[0270] Step 4:

[0271] The server sends the generated visual image and a list of facilities to the terminal. The terminal then presents this information to the user, who selects facilities while viewing the visual image. The selection results are sent back to the server via the terminal.

[0272] Step 5:

[0273] When a user wishes to make a reservation for a selected facility, they send that information to the server via their device. The server receives the reservation information and automatically proceeds with the reservation process for the selected facility. This process includes confirming and registering the date, time, and user information, and outputs the results as a notification.

[0274] Step 6:

[0275] Once the reservation is complete, the server will notify the user of the details (e.g., reservation number, date and time). This information will be sent via the terminal, allowing the user to confirm the reservation details.

[0276] (Application Example 1)

[0277] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0278] In e-commerce and service selection, users typically spend considerable time and effort choosing the right option from a multitude of choices. Furthermore, a lack of consistent and efficient payment processing methods for selected services and products can detract from the user experience. There is a need to address these challenges and provide a system that enables quick and efficient service selection and payment processes.

[0279] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0280] In this invention, the server includes means for acquiring video information and desired requirements, means for recommending appropriate facilities according to the desired requirements, means for generating an image based on the video information, and means for performing an automatic payment procedure according to the selection by the user. Thereby, it becomes possible for the user to efficiently and conveniently select the desired service and perform a seamless payment procedure.

[0281] "Video information" refers to visual data such as face photos and videos provided by the user, and is used to clarify individual needs and images when selecting services and products.

[0282] "Desired requirements" refer to specific conditions such as the area, style, and budget desired by the user, and are information used as a criterion when selecting recommended services and products.

[0283] "Means for recommending appropriate facilities" refers to an internal function of the system for identifying and proposing the most suitable facilities or services from a number of options based on the user's desired requirements.

[0284] "Means for generating an image" refers to an image generation technology and process used to visualize a specific usage scene in the proposed facilities and services based on the video information provided by the user.

[0285] "Means for performing a reservation process" refers to a procedure automatically implemented by the system to confirm and secure the date and conditions for the facilities or services selected by the user.

[0286] "Means for performing an automatic payment procedure" refers to a processing function for automatically completing the settlement for the service selected by the user using the pre-registered payment information.

[0287] This invention is a system for efficiently enabling users to select desired services or products and complete payment procedures. The server first receives video information and desired requirements from the user's terminal. The video information consists of visual data such as facial photos and videos provided by the user, while the desired requirements include specific conditions such as region, style, and budget.

[0288] Next, the server recommends suitable facilities based on the acquired preferences. This involves a process that uses a recommendation engine to refer to past data and the preferences of similar users to identify the best options. Furthermore, a generative AI model is used to generate images that visualize specific usage scenarios for the suggested facilities and services based on the video information.

[0289] The user then reviews and selects the options presented through the terminal. The server processes the reservation and automatic payment for the facility or service based on the user's selection. At this stage, an appropriate payment gateway is used to securely process the registered payment information.

[0290] As a concrete example, consider a scenario where a user uses a travel booking app to plan their honeymoon. The user inputs their destination, budget, and preferred style of stay, and the app uses AI to suggest options for sightseeing, accommodation, and activities. The user then reviews a visualized image of their chosen honeymoon, and the booking and payment are completed instantly.

[0291] Examples of prompts for a generative AI model:

[0292] "Please choose from the following honeymoon packages: Island Resort Package, City Sightseeing Package, or Mountain Retreat Package. We will then process your payment quickly."

[0293] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0294] Step 1:

[0295] Users input video information and desired requirements into the system using a terminal. The input includes the user's facial photograph and video data (video information), as well as desired conditions such as region, style, and budget. This data is sent from the terminal to the server, where its integrity is first verified. This information is then used as the basic data for system operation.

[0296] Step 2:

[0297] The server recommends appropriate facilities and services based on the received preferences. At this stage, a recommendation engine is used, matching the entered preferences with past data and similar cases in the database. This extracts the best service options and generates a list of recommendations to present to the user.

[0298] Step 3:

[0299] The server uses a generative AI model to generate images based on video information provided by the user. In this process, the received video information is used as material to generate images of specific usage scenarios at recommended facilities and services. This step utilizes image generation algorithms to create visually impressive content.

[0300] Step 4:

[0301] The user reviews the server-generated image and recommended options through their terminal. This is where the user interface comes into play, enabling the user to make choices easily and intuitively. The interface displays images, clarifies the user's options, and guides them to the next step.

[0302] Step 5:

[0303] When the user makes a selection, the server automatically proceeds with the reservation process for the selected facility or service. At the same time, the automatic payment process is initiated using the registered payment information. The server uses a secure payment gateway to perform reliable settlement processing. As a result, the reservation is confirmed and the user is notified of the details.

[0304] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0305] As a form for implementing the present invention, a form in which an emotion engine for recognizing the user's emotions is combined with the wedding venue selection support system by the AI agent is provided. This system can propose a facility that meets the user's wishes and perform a series of processes up to the reservation in a form that takes into account the emotion information.

[0306] First, the user inputs the desired conditions regarding their wedding through the terminal and uploads a face photo and video data. Also, using the camera and microphone installed in the terminal, the emotion engine analyzes the user's expression and voice in real time and recognizes the current emotional state. As a result, the user's desired conditions and emotion data are transmitted to the server.

[0307] Based on the received conditions and emotion data, the server matches them with the wedding venue information in the database. The recommendation engine generates a list of appropriate venues based on the user's desired conditions and emotions. The emotion information can also be used to adjust the recommendation, for example, by proposing an effect that emphasizes the emotion when the user feels happy.

[0308] The server uses image generation AI to generate an image of the ceremony at the proposed venue based on the user's face photo and emotions. This image reflects the emotion information, and for example, when the user is judged to be satisfied, a brighter tone or a moving effect can be set.

[0309] The generated list of wedding venues and their images are displayed to the user via their device. The user can visually confirm concrete images and, based on the presented information, select a venue, allowing for a more satisfying decision. Furthermore, if the user's emotions change during the selection process, the server can detect this and immediately adjust the suggestions.

[0310] The user requests a reservation from their terminal for the wedding venue they have selected. The server processes the reservation accordingly and notifies the user upon completion. Furthermore, the feedback received can be used to improve the overall system and enhance the accuracy of the emotion engine.

[0311] Through this format, a personalized venue selection experience that takes user emotions into account is provided, enabling users to make more satisfying choices.

[0312] The following describes the processing flow.

[0313] Step 1:

[0314] Users input their wedding preferences (location, style, budget) through their device and upload photos and related video data. The input from the device is transmitted to the server, and at the same time, the device uses its camera and microphone to collect the user's facial expressions and voice, generating emotion data in real time.

[0315] Step 2:

[0316] The server collects user preferences, video data, and emotional data received from the user and stores them in a database. This allows for data integration and lays the foundation for further processing.

[0317] Step 3:

[0318] The recommendation engine on the server searches the database, taking into account the user's preferences and emotional state. Emotional data is used for scoring to determine which venue best matches the user's current emotional state, and a list of recommended venues is generated.

[0319] Step 4:

[0320] The server's image generation AI creates wedding images for each proposed venue based on the user's facial photo and emotional data. Based on the emotional information, the image is adjusted; for example, if the user is nervous, a relaxed atmosphere is emphasized.

[0321] Step 5:

[0322] The terminal displays a list of suggested venues received from the server, along with generated image files, to the user. The user receives visual feedback, selects the venue they are most interested in, and is provided with an interactive interface to view detailed information and suggestions.

[0323] Step 6:

[0324] If a user wishes to make a reservation for a selected venue, they submit a reservation request from their device. The server accepts this request and proceeds with the reservation process with the relevant venue. Once the reservation is complete, the server notifies the user of the details.

[0325] Step 7:

[0326] After using the system, users provide feedback on the service through their device. This feedback is sent to the server and used to improve the accuracy of the sentiment engine and recommendation engine.

[0327] (Example 2)

[0328] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0329] Traditional venue selection and booking systems simply offered suggestions based on conditions, without considering the user's emotional state. As a result, they failed to make choices that suited the user's feelings and desires, leading to decreased satisfaction. Furthermore, the lack of visual representation made it difficult for users to form concrete images of their choices.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes means for acquiring video information and specification conditions, means for analyzing emotional states using a terminal, and means for recommending appropriate locations based on the user's specification conditions and emotional state. This enables personalized facility selection that takes into account the user's emotions and allows for highly satisfying choices.

[0332] "Video information" refers to facial images and video data acquired by the device, and is used to analyze the user's emotional state.

[0333] "Specification conditions" refer to information about desired facilities and conditions entered by the user, and are factors that influence the recommendation results.

[0334] "Device" refers to a device used by a user to input information or analyze emotional data, and includes smartphones and tablets.

[0335] "Emotional state" refers to the user's facial expressions and voice, which are analyzed in real time by the emotion engine, and is a useful element for customizing recommendation results.

[0336] A "suitable location" refers to a facility recommended by the server based on the user's specifications and emotional state, with the aim of increasing user satisfaction.

[0337] "Visual information" refers to images created by a generative AI model based on video information and emotional states, enabling users to form a concrete image of the facility.

[0338] "Reservation processing" refers to the procedure in which the server confirms a reservation for a specified location based on the user's selection, and has the function of notifying the user of the result.

[0339] "Opinions" refers to feedback from users, including evaluations and suggestions for improvement regarding recommendations and visual information.

[0340] This invention is a system to support personalized wedding venue selection that takes into account the user's emotions. Based on the user's desired conditions and emotional state, this system suggests suitable wedding venues and supports the booking process.

[0341] First, the user uses the device to input their specific wedding preferences. These preferences include specifications such as "a venue by the sea" and "accommodates up to 100 people." The device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine to determine their current emotional state. If the user is smiling, the system recognizes this as "enjoying themselves."

[0342] This information is sent directly to the server. The server then compares the received specifications and emotional state with a database in the cloud. A recommendation engine then operates to suggest appropriate facilities, generating a list of facilities tailored to the user's conditions and emotions. Specifically, if the user desires a calm atmosphere, it will recommend places where they can relax.

[0343] Next, the server utilizes a generative AI model to create a wedding image at the suggested wedding venue, based on the user's facial photo and emotional information. This image reflects the user's emotional state, such as enjoyment, and for example, a visual with bright colors is generated.

[0344] The generated list of venues and visual information are presented to the user via the terminal. The user can select a venue based on this visual information. An example of a prompt message that can be input to the generating AI model is, "I'm looking for a wedding venue with a natural and homey atmosphere. I'm very happy right now. Please generate images of a wedding that meets these criteria."

[0345] Once a facility is selected, the user submits a reservation request from their terminal, and the server processes the reservation. The system also collects user feedback to improve the overall system and enhance the accuracy of the sentiment engine. This allows users to make more satisfying choices.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The user enters their desired wedding conditions through a terminal. This input includes specific specifications such as "a venue by the sea" or "a casual atmosphere." The input data is retrieved through the terminal's interface and converted into a format that can be processed.

[0349] Step 2:

[0350] The device uses its built-in camera and microphone to record the user's facial expressions and voice in real time. Based on this, an emotion engine analyzes the data and recognizes the user's emotional state. For example, if the user is smiling, it generates emotion data indicating "enjoying themselves." This analysis result is then prepared to be sent to the server as output.

[0351] Step 3:

[0352] The server receives specification conditions and emotional data sent from the terminal. This input data is used to compare it with wedding venue information in the database. The recommendation engine analyzes this and selects venues that are suitable for the specification conditions and emotional state. For example, if the user is looking for a relaxed atmosphere, the server will generate a list of such venues.

[0353] Step 4:

[0354] The server utilizes a generative AI model to generate specific wedding images based on the user's facial photograph and emotional data. This calculation is based on the facial photograph; for example, if the user has positive emotions, the generated image will also have bright colors. The result is output as an image file and sent to the terminal.

[0355] Step 5:

[0356] The terminal displays a list of facilities and wedding ceremony images sent from the server to the user. The user makes a decision based on this information and notifies the system of their selected facility. For example, if a bright wedding ceremony image with the sea as a background is presented, the user will proceed with their selection accordingly.

[0357] Step 6:

[0358] The user sends a reservation request from their device to the facility they selected. The server receives this request and processes the reservation with the facility. Once the process is complete, the user is notified of the result via a confirmation message.

[0359] Step 7:

[0360] After a reservation is confirmed, the server collects feedback from the user. This feedback is used to improve user satisfaction and the accuracy of suggestions, and helps to improve the sentiment engine and recommendation engine.

[0361] (Application Example 2)

[0362] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0363] In the modern shopping experience, providing personalized recommendations that reflect users' emotions and preferences is challenging. Current technologies have limitations in accurately assessing a user's emotional state and incorporating that feedback in real time. This results in users having very limited information to make the best choices, leading to a lower quality of the experience.

[0364] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0365] In this invention, the server includes means for acquiring video data and desired conditions, means for recommending an appropriate installation location according to the desired conditions, means for generating an image based on the video data, means for analyzing the user's emotional state, means for adjusting the recommendation content based on the analysis results, and means for processing a reservation for the installation location. This enables dynamic recommendations that respond to the user's emotional state, providing a more personalized purchasing experience.

[0366] "Video data" refers to visual information acquired to analyze the user's emotional state.

[0367] "Desired conditions" refer to the requirements and preferences specified by the user when using the system, and are used in selecting recommended installation locations.

[0368] "Installation location" refers to facilities or stores recommended based on the user's preferences and emotional state.

[0369] An "image rendering" is generated based on acquired video data and provides a visual representation of the experience and product at the installation location.

[0370] "Emotional state" refers to the user's psychological state, identified by analyzing their facial expressions and tone of voice.

[0371] "Recommendations" refer to appropriate installation locations and product information presented based on the user's desired conditions and analyzed emotional state.

[0372] "Reservation processing" refers to the process of handling procedures and confirmations related to the installation location selected by the user.

[0373] In this configuration, when a user accesses the service via a smart device, the device first uses its built-in camera and microphone to acquire video and audio data. This data is then sent to an emotion recognition engine, which analyzes the user's emotional state based on their facial expressions and voice pitch. Software such as Affectiva or Microsoft Azure Cognitive Services is used for emotion recognition.

[0374] Next, the server receives this data in real time, along with the user's input preferences, and performs analysis to recommend the optimal installation location. During this process, a Recommendation Engine (e.g., Apache Mahout) is used to provide dynamic recommendations tailored to the user's preferences and emotions.

[0375] The server uses a generative AI model based on the acquired video data to synthesize imagery that realistically recreates the experience at the installation site. This allows users to have a more concrete and visual experience. For example, this could be done using Python with TensorFlow or PyTorch.

[0376] This image is displayed on a smart device's screen, and the user selects an installation location based on the presented content through emotion recognition. Once the selection is made, the server executes a reservation procedure for the selected installation location. This process is hosted on a cloud system.

[0377] For example, in a virtual bookstore, the system could capture the emotions of users who show interest in the cover of a book they are browsing and display recommended books from related genres and publishers. This also allows for personalized promotions based on those emotions.

[0378] An example of a prompt for a generative AI model might be: "Create a script that suggests related products for items in which the user has shown a joyful expression, and provide the most appealing product information in real time based on the user's emotional data."

[0379] This invention makes it possible to provide users with personalized experiences and achieve higher satisfaction levels.

[0380] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0381] Step 1:

[0382] The device uses its camera and microphone to acquire video and audio data of the user in real time. This data is prepared as input for the emotion recognition engine. Specifically, it captures the user's facial expressions and voice pitch, and uses this data during the session without saving it to a database.

[0383] Step 2:

[0384] The device sends the acquired video and audio data to an emotion recognition engine. This engine analyzes the acquired data and identifies the user's emotional state. Using software such as Microsoft Azure Cognitive Services, it performs the analysis and outputs the results as an emotional state such as "joy," "interest," or "surprise."

[0385] Step 3:

[0386] The server matches the user's desired conditions with the emotional state obtained in step 2 against the database and generates a list of installation locations using the Recommendation Engine. Using desired conditions and emotional state as input, it lists appropriate installation locations based on the analysis results.

[0387] Step 4:

[0388] The server creates image data using a generative AI model. It takes user preferences, emotional states, and installation location data as input to output an image that simulates the experience at the installation location. Image generation is performed using TensorFlow or PyTorch.

[0389] Step 5:

[0390] The terminal displays a list of installation locations and image files received from the server to the user. This display is done via a user interface, allowing the user to visually review the images and select a more appropriate installation location based on emotional information.

[0391] Step 6:

[0392] The terminal proceeds with the reservation process for the installation location selected by the user. At this stage, the server confirms the reservation on the cloud system in response to the user's request and outputs a completion message to the terminal.

[0393] Step 7:

[0394] The server collects user feedback and stores it in a database. This helps improve the accuracy of the Recommendation Engine and emotion recognition engine, contributing to overall system improvement. This process will lead to improved user experience in the future.

[0395] The processing steps described above enable a personalized experience based on the user's emotions and preferences.

[0396] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0397] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0399] [Third Embodiment]

[0400] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0401] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0402] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0403] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0404] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0405] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0406] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0407] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0408] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0409] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0410] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0411] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0412] As one embodiment of the present invention, an AI agent-based system for supporting the selection of wedding venues is provided. This system includes a process of selecting the most suitable venue for the user's needs using the user's desired wedding conditions and video data, and then making a reservation.

[0413] First, users input information such as location, style, and budget as their desired wedding conditions via a terminal. In addition, users upload photos and related video data to the system. This allows the system to identify the user's individual needs and gather the necessary materials to generate a concrete image.

[0414] Next, the server receives these input conditions and video data and matches them against wedding venue data in the database. In this step, a recommendation engine is used to suggest several optimal venues based on past data and the preferences of similar users.

[0415] Subsequently, the server uses image generation AI to create wedding ceremony images for each proposed venue based on the video data provided by the user. This allows the user to visually confirm a concrete image of the wedding ceremony.

[0416] The suggested information is provided to the user through the terminal's user interface. Based on the displayed information, the user can determine which venue best matches their ideal and view detailed information. If the user wishes to make a reservation for their chosen venue, the server will automatically proceed with the reservation process based on instructions from the terminal. Once the reservation is complete, the server will notify the user of the details and update the reservation information.

[0417] Finally, after using the service, users can submit feedback via their device. This feedback is analyzed on the server and used to improve the accuracy of the recommendation engine and enhance the service.

[0418] This system allows users to efficiently discover, visualize, and book wedding venues that meet their preferences. This integrated service process significantly simplifies the traditional, time-consuming process of choosing a venue, improving user convenience.

[0419] The following describes the processing flow.

[0420] Step 1:

[0421] Users enter their desired wedding conditions (location, style, budget) via their device and upload photos and related video data. The entered information is then sent to the server.

[0422] Step 2:

[0423] The server receives data from the user and stores it in the database. It validates the entered conditions and returns error messages to the terminal as needed.

[0424] Step 3:

[0425] The server's recommendation engine searches the database for wedding venue information based on the user's preferences, selects several suitable venues, and lists them.

[0426] Step 4:

[0427] The server uses image generation AI to create wedding images for each proposed venue based on the user's facial photograph. These generated images are temporarily stored.

[0428] Step 5:

[0429] The terminal displays a list of wedding venues received from the server, along with generated image files, to the user. It provides an interface for the user to select a venue of interest and view details.

[0430] Step 6:

[0431] If a user wishes to make a reservation for a wedding venue they have selected, they submit a reservation request from their device. The server receives this request and begins the reservation process with the venue.

[0432] Step 7:

[0433] If a reservation is secured, the server notifies the user of its details. At the same time, it records the user's reservation information in the database.

[0434] Step 8:

[0435] After using the service, users submit feedback from their devices. The server collects this feedback and uses it to improve the recommendation engine and the overall system.

[0436] (Example 1)

[0437] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0438] In recent years, there has been a growing demand for facility selection based on individualized criteria, and recommending facilities that accurately meet the needs of users is particularly difficult for important events such as weddings. Furthermore, there is a lack of systems that enable users to form a concrete image of what they want based on the information provided and make selections accordingly. In addition, there is a need to provide a smooth way to make reservations at selected facilities.

[0439] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0440] In this invention, the server includes means for acquiring information data and desired conditions, means equipped with a computing device for recommending appropriate facilities, means including a learning algorithm, means for utilizing a generative model, and means for automatically performing processing on facilities. This enables the recommendation of optimal facilities based on the user's desired conditions and the formation of concrete images utilizing the generated visual images, and then enables rapid reservation processing for the selected facilities.

[0441] "Information data" refers to all data, including user-provided preferences and video materials.

[0442] "Desired conditions" refer to information that represents the specific requirements and attributes of the facilities and services that the user is looking for.

[0443] "Computing equipment" refers to devices including computers and their peripherals used for data processing and analysis.

[0444] A "learning algorithm" is a mathematical method or model used to find patterns in data and predict the optimal outcome.

[0445] A "generative model" refers to a technology that includes algorithms for generating new data or images based on input data.

[0446] "Processing a facility" refers to a series of operations, including making reservations and arrangements for the facility selected by the user.

[0447] This invention is implemented as a system for users to efficiently select and reserve facilities that meet their specific requirements. Users first input their desired conditions and video data via a terminal. This information is then transmitted to a server.

[0448] The server first receives this information data and then uses computing devices to analyze it. Specifically, it processes the input data using learning algorithms and compares it with past user data in the database to identify the appropriate facility. This calculation uses machine learning libraries and database management systems, and is often implemented using software such as Python or SQL.

[0449] Next, the server uses a generative model to generate visual images from the video data. This generation process utilizes a generative AI model to concretize the visual representation of events at the target facility. The generative AI models used include image generation tools and APIs provided as open-source libraries.

[0450] As a concrete example, suppose a couple inputs conditions such as "a garden-style wedding in Tokyo, with a budget of under 3 million yen." The server receives these conditions as a prompt and presents them to the generative model in the form of "generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo."

[0451] The visual images generated in this way are presented to the user via the device and serve as information to support the optimal selection. If the user selects a facility they like, the server automatically initiates the reservation process for that facility, providing a smooth user experience.

[0452] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0453] Step 1:

[0454] The user uses a terminal to input wedding details (e.g., region, style, budget) and video data (e.g., portraits). This data is sent from the terminal to the server. The input data arrives on the server as text and image data and is then sent directly to the next processing step.

[0455] Step 2:

[0456] The server analyzes the received information data. Using a computing device, it matches the desired conditions with past user data in the database and generates a list of optimal facilities based on this. This process utilizes machine learning algorithms to score facilities that meet the conditions and outputs the results.

[0457] Step 3:

[0458] The server uses a generative AI model to generate visual images based on video data provided by the user. A prompt (e.g., "Generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo") is input to the generative AI model, and the model outputs an image that combines the video data with the given conditions.

[0459] Step 4:

[0460] The server sends the generated visual image and a list of facilities to the terminal. The terminal then presents this information to the user, who selects facilities while viewing the visual image. The selection results are sent back to the server via the terminal.

[0461] Step 5:

[0462] When a user wishes to make a reservation for a selected facility, they send that information to the server via their device. The server receives the reservation information and automatically proceeds with the reservation process for the selected facility. This process includes confirming and registering the date, time, and user information, and outputs the results as a notification.

[0463] Step 6:

[0464] Once the reservation is complete, the server will notify the user of the details (e.g., reservation number, date and time). This information will be sent via the terminal, allowing the user to confirm the reservation details.

[0465] (Application Example 1)

[0466] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0467] In e-commerce and service selection, users typically spend considerable time and effort choosing the right option from a multitude of choices. Furthermore, a lack of consistent and efficient payment processing methods for selected services and products can detract from the user experience. There is a need to address these challenges and provide a system that enables quick and efficient service selection and payment processes.

[0468] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0469] In this invention, the server includes means for acquiring video information and desired requirements, means for recommending appropriate facilities according to the desired requirements, means for generating an image based on the video information, and means for performing an automatic payment procedure according to the user's selection. This enables the user to efficiently and easily select the desired service and perform a seamless payment procedure.

[0470] "Visual information" refers to visual data such as facial photos and videos provided by users, and is used to clarify individual needs and images when selecting services or products.

[0471] "Desired requirements" refer to specific conditions such as the user's preferred region, style, and budget, and are used as criteria when selecting recommended services and products.

[0472] "Means of recommending appropriate facilities" refers to an internal system function that identifies and suggests the most suitable facility or service from a number of options based on the user's desired requirements.

[0473] "Means of generating images" refers to image generation technologies and processes used to visualize specific usage scenarios in proposed facilities and services based on video information provided by the user.

[0474] "Means of processing reservations" refers to the procedures that the system automatically performs to confirm and secure the date, time, and conditions for the facility or service selected by the user.

[0475] "Means of performing automatic payment procedures" refers to a processing function that automatically completes payment for the service selected by the user using pre-registered payment information.

[0476] This invention is a system for efficiently enabling users to select desired services or products and complete payment procedures. The server first receives video information and desired requirements from the user's terminal. The video information consists of visual data such as facial photos and videos provided by the user, while the desired requirements include specific conditions such as region, style, and budget.

[0477] Next, the server recommends suitable facilities based on the acquired preferences. This involves a process that uses a recommendation engine to refer to past data and the preferences of similar users to identify the best options. Furthermore, a generative AI model is used to generate images that visualize specific usage scenarios for the suggested facilities and services based on the video information.

[0478] The user then reviews and selects the options presented through the terminal. The server processes the reservation and automatic payment for the facility or service based on the user's selection. At this stage, an appropriate payment gateway is used to securely process the registered payment information.

[0479] As a concrete example, consider a scenario where a user uses a travel booking app to plan their honeymoon. The user inputs their destination, budget, and preferred style of stay, and the app uses AI to suggest options for sightseeing, accommodation, and activities. The user then reviews a visualized image of their chosen honeymoon, and the booking and payment are completed instantly.

[0480] Examples of prompts for a generative AI model:

[0481] "Please choose from the following honeymoon packages: Island Resort Package, City Sightseeing Package, or Mountain Retreat Package. We will then process your payment quickly."

[0482] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0483] Step 1:

[0484] Users input video information and desired requirements into the system using a terminal. The input includes the user's facial photograph and video data (video information), as well as desired conditions such as region, style, and budget. This data is sent from the terminal to the server, where its integrity is first verified. This information is then used as the basic data for system operation.

[0485] Step 2:

[0486] The server recommends appropriate facilities and services based on the received preferences. At this stage, a recommendation engine is used, matching the entered preferences with past data and similar cases in the database. This extracts the best service options and generates a list of recommendations to present to the user.

[0487] Step 3:

[0488] The server uses a generative AI model to generate images based on video information provided by the user. In this process, the received video information is used as material to generate images of specific usage scenarios at recommended facilities and services. This step utilizes image generation algorithms to create visually impressive content.

[0489] Step 4:

[0490] The user reviews the server-generated image and recommended options through their terminal. This is where the user interface comes into play, enabling the user to make choices easily and intuitively. The interface displays images, clarifies the user's options, and guides them to the next step.

[0491] Step 5:

[0492] Once the user makes a selection, the server automatically initiates the booking process for the selected facility or service. Simultaneously, an automated payment process is initiated using the registered payment information. The server uses a secure payment gateway to ensure reliable settlement. This confirms the booking, and the user is notified of its details.

[0493] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0494] As an embodiment of the present invention, a system is provided that combines an AI agent-based support system for selecting a wedding venue with an emotion engine that recognizes the user's emotions. This system can propose facilities that meet the user's preferences and carry out the entire process, from selection to booking, while taking emotional information into consideration.

[0495] First, the user enters their desired wedding conditions through their device and uploads photos and video data. Additionally, the device's built-in camera and microphone are used by an emotion engine to analyze the user's facial expressions and voice in real time, recognizing their current emotional state. This data, along with the user's desired conditions, is then sent to the server.

[0496] The server matches the received conditions and emotion data with wedding venue information in the database. The recommendation engine generates a list of suitable venues based on the user's preferences and emotions. Emotional information is also used to adjust the recommendations; for example, if the user feels joy, the system suggests elements that further emphasize that emotion.

[0497] The server uses image generation AI to create wedding images for suggested venues based on the user's facial photo and emotions. These images reflect emotional information; for example, if the user is judged to be satisfied, a brighter tone and more emotionally charged presentation can be set.

[0498] The generated list of wedding venues and their images are displayed to the user via their device. The user can visually confirm concrete images and, based on the presented information, select a venue, allowing for a more satisfying decision. Furthermore, if the user's emotions change during the selection process, the server can detect this and immediately adjust the suggestions.

[0499] The user requests a reservation from their terminal for the wedding venue they have selected. The server processes the reservation accordingly and notifies the user upon completion. Furthermore, the feedback received can be used to improve the overall system and enhance the accuracy of the emotion engine.

[0500] Through this format, a personalized venue selection experience that takes user emotions into account is provided, enabling users to make more satisfying choices.

[0501] The following describes the processing flow.

[0502] Step 1:

[0503] Users input their wedding preferences (location, style, budget) through their device and upload photos and related video data. The input from the device is transmitted to the server, and at the same time, the device uses its camera and microphone to collect the user's facial expressions and voice, generating emotion data in real time.

[0504] Step 2:

[0505] The server collects user preferences, video data, and emotional data received from the user and stores them in a database. This allows for data integration and lays the foundation for further processing.

[0506] Step 3:

[0507] The recommendation engine on the server searches the database, taking into account the user's preferences and emotional state. Emotional data is used for scoring to determine which venue best matches the user's current emotional state, and a list of recommended venues is generated.

[0508] Step 4:

[0509] The server's image generation AI creates wedding images for each proposed venue based on the user's facial photo and emotional data. Based on the emotional information, the image is adjusted; for example, if the user is nervous, a relaxed atmosphere is emphasized.

[0510] Step 5:

[0511] The terminal displays a list of suggested venues received from the server, along with generated image files, to the user. The user receives visual feedback, selects the venue they are most interested in, and is provided with an interactive interface to view detailed information and suggestions.

[0512] Step 6:

[0513] If a user wishes to make a reservation for a selected venue, they submit a reservation request from their device. The server accepts this request and proceeds with the reservation process with the relevant venue. Once the reservation is complete, the server notifies the user of the details.

[0514] Step 7:

[0515] After using the system, users provide feedback on the service through their device. This feedback is sent to the server and used to improve the accuracy of the sentiment engine and recommendation engine.

[0516] (Example 2)

[0517] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0518] Traditional venue selection and booking systems simply offered suggestions based on conditions, without considering the user's emotional state. As a result, they failed to make choices that suited the user's feelings and desires, leading to decreased satisfaction. Furthermore, the lack of visual representation made it difficult for users to form concrete images of their choices.

[0519] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0520] In this invention, the server includes means for acquiring video information and specification conditions, means for analyzing emotional states using a terminal, and means for recommending appropriate locations based on the user's specification conditions and emotional state. This enables personalized facility selection that takes into account the user's emotions and allows for highly satisfying choices.

[0521] "Video information" refers to facial images and video data acquired by the device, and is used to analyze the user's emotional state.

[0522] "Specification conditions" refer to information about desired facilities and conditions entered by the user, and are factors that influence the recommendation results.

[0523] "Device" refers to a device used by a user to input information or analyze emotional data, and includes smartphones and tablets.

[0524] "Emotional state" refers to the user's facial expressions and voice, which are analyzed in real time by the emotion engine, and is a useful element for customizing recommendation results.

[0525] A "suitable location" refers to a facility recommended by the server based on the user's specifications and emotional state, with the aim of increasing user satisfaction.

[0526] "Visual information" refers to images created by a generative AI model based on video information and emotional states, enabling users to form a concrete image of the facility.

[0527] "Reservation processing" refers to the procedure in which the server confirms a reservation for a specified location based on the user's selection, and has the function of notifying the user of the result.

[0528] "Opinions" refers to feedback from users, including evaluations and suggestions for improvement regarding recommendations and visual information.

[0529] This invention is a system to support personalized wedding venue selection that takes into account the user's emotions. Based on the user's desired conditions and emotional state, this system suggests suitable wedding venues and supports the booking process.

[0530] First, the user uses the device to input their specific wedding preferences. These preferences include specifications such as "a venue by the sea" and "accommodates up to 100 people." The device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine to determine their current emotional state. If the user is smiling, the system recognizes this as "enjoying themselves."

[0531] This information is sent directly to the server. The server then compares the received specifications and emotional state with a database in the cloud. A recommendation engine then operates to suggest appropriate facilities, generating a list of facilities tailored to the user's conditions and emotions. Specifically, if the user desires a calm atmosphere, it will recommend places where they can relax.

[0532] Next, the server utilizes a generative AI model to create a wedding image at the suggested wedding venue, based on the user's facial photo and emotional information. This image reflects the user's emotional state, such as enjoyment, and for example, a visual with bright colors is generated.

[0533] The generated list of venues and visual information are presented to the user via the terminal. The user can select a venue based on this visual information. An example of a prompt message that can be input to the generating AI model is, "I'm looking for a wedding venue with a natural and homey atmosphere. I'm very happy right now. Please generate images of a wedding that meets these criteria."

[0534] Once a facility is selected, the user submits a reservation request from their terminal, and the server processes the reservation. The system also collects user feedback to improve the overall system and enhance the accuracy of the sentiment engine. This allows users to make more satisfying choices.

[0535] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0536] Step 1:

[0537] The user enters their desired wedding conditions through a terminal. This input includes specific specifications such as "a venue by the sea" or "a casual atmosphere." The input data is retrieved through the terminal's interface and converted into a format that can be processed.

[0538] Step 2:

[0539] The device uses its built-in camera and microphone to record the user's facial expressions and voice in real time. Based on this, an emotion engine analyzes the data and recognizes the user's emotional state. For example, if the user is smiling, it generates emotion data indicating "enjoying themselves." This analysis result is then prepared to be sent to the server as output.

[0540] Step 3:

[0541] The server receives specification conditions and emotional data sent from the terminal. This input data is used to compare it with wedding venue information in the database. The recommendation engine analyzes this and selects venues that are suitable for the specification conditions and emotional state. For example, if the user is looking for a relaxed atmosphere, the server will generate a list of such venues.

[0542] Step 4:

[0543] The server utilizes a generative AI model to generate specific wedding images based on the user's facial photograph and emotional data. This calculation is based on the facial photograph; for example, if the user has positive emotions, the generated image will also have bright colors. The result is output as an image file and sent to the terminal.

[0544] Step 5:

[0545] The terminal displays a list of facilities and wedding ceremony images sent from the server to the user. The user makes a decision based on this information and notifies the system of their selected facility. For example, if a bright wedding ceremony image with the sea as a background is presented, the user will proceed with their selection accordingly.

[0546] Step 6:

[0547] The user sends a reservation request from their device to the facility they selected. The server receives this request and processes the reservation with the facility. Once the process is complete, the user is notified of the result via a confirmation message.

[0548] Step 7:

[0549] After a reservation is confirmed, the server collects feedback from the user. This feedback is used to improve user satisfaction and the accuracy of suggestions, and helps to improve the sentiment engine and recommendation engine.

[0550] (Application Example 2)

[0551] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0552] In the modern shopping experience, providing personalized recommendations that reflect users' emotions and preferences is challenging. Current technologies have limitations in accurately assessing a user's emotional state and incorporating that feedback in real time. This results in users having very limited information to make the best choices, leading to a lower quality of the experience.

[0553] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0554] In this invention, the server includes means for acquiring video data and desired conditions, means for recommending an appropriate installation location according to the desired conditions, means for generating an image based on the video data, means for analyzing the user's emotional state, means for adjusting the recommendation content based on the analysis results, and means for processing a reservation for the installation location. This enables dynamic recommendations that respond to the user's emotional state, providing a more personalized purchasing experience.

[0555] "Video data" refers to visual information acquired to analyze the user's emotional state.

[0556] "Desired conditions" refer to the requirements and preferences specified by the user when using the system, and are used in selecting recommended installation locations.

[0557] "Installation location" refers to facilities or stores recommended based on the user's preferences and emotional state.

[0558] An "image rendering" is generated based on acquired video data and provides a visual representation of the experience and product at the installation location.

[0559] "Emotional state" refers to the user's psychological state, identified by analyzing their facial expressions and tone of voice.

[0560] "Recommendations" refer to appropriate installation locations and product information presented based on the user's desired conditions and analyzed emotional state.

[0561] "Reservation processing" refers to the process of handling procedures and confirmations related to the installation location selected by the user.

[0562] In this configuration, when a user accesses the service via a smart device, the device first uses its built-in camera and microphone to acquire video and audio data. This data is then sent to an emotion recognition engine, which analyzes the user's emotional state based on their facial expressions and voice pitch. Software such as Affectiva or Microsoft Azure Cognitive Services is used for emotion recognition.

[0563] Next, the server receives this data in real time, along with the user's input preferences, and performs analysis to recommend the optimal installation location. During this process, a Recommendation Engine (e.g., Apache Mahout) is used to provide dynamic recommendations tailored to the user's preferences and emotions.

[0564] The server uses a generative AI model based on the acquired video data to synthesize imagery that realistically recreates the experience at the installation site. This allows users to have a more concrete and visual experience. For example, this could be done using Python with TensorFlow or PyTorch.

[0565] This image is displayed on a smart device's screen, and the user selects an installation location based on the presented content through emotion recognition. Once the selection is made, the server executes a reservation procedure for the selected installation location. This process is hosted on a cloud system.

[0566] For example, in a virtual bookstore, the system could capture the emotions of users who show interest in the cover of a book they are browsing and display recommended books from related genres and publishers. This also allows for personalized promotions based on those emotions.

[0567] An example of a prompt for a generative AI model might be: "Create a script that suggests related products for items in which the user has shown a joyful expression, and provide the most appealing product information in real time based on the user's emotional data."

[0568] This invention makes it possible to provide users with personalized experiences and achieve higher satisfaction levels.

[0569] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0570] Step 1:

[0571] The device uses its camera and microphone to acquire video and audio data of the user in real time. This data is prepared as input for the emotion recognition engine. Specifically, it captures the user's facial expressions and voice pitch, and uses this data during the session without saving it to a database.

[0572] Step 2:

[0573] The device sends the acquired video and audio data to an emotion recognition engine. This engine analyzes the acquired data and identifies the user's emotional state. Using software such as Microsoft Azure Cognitive Services, it performs the analysis and outputs the results as an emotional state such as "joy," "interest," or "surprise."

[0574] Step 3:

[0575] The server matches the user's desired conditions with the emotional state obtained in step 2 against the database and generates a list of installation locations using the Recommendation Engine. Using desired conditions and emotional state as input, it lists appropriate installation locations based on the analysis results.

[0576] Step 4:

[0577] The server creates image data using a generative AI model. It takes user preferences, emotional states, and installation location data as input to output an image that simulates the experience at the installation location. Image generation is performed using TensorFlow or PyTorch.

[0578] Step 5:

[0579] The terminal displays a list of installation locations and image files received from the server to the user. This display is done via a user interface, allowing the user to visually review the images and select a more appropriate installation location based on emotional information.

[0580] Step 6:

[0581] The terminal proceeds with the reservation process for the installation location selected by the user. At this stage, the server confirms the reservation on the cloud system in response to the user's request and outputs a completion message to the terminal.

[0582] Step 7:

[0583] The server collects user feedback and stores it in a database. This helps improve the accuracy of the Recommendation Engine and emotion recognition engine, contributing to overall system improvement. This process will lead to improved user experience in the future.

[0584] The processing steps described above enable a personalized experience based on the user's emotions and preferences.

[0585] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0586] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0587] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0588] [Fourth Embodiment]

[0589] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0590] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0591] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0592] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0593] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0594] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0595] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0596] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0597] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0598] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0599] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0600] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0601] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0602] As one embodiment of the present invention, an AI agent-based system for supporting the selection of wedding venues is provided. This system includes a process of selecting the most suitable venue for the user's needs using the user's desired wedding conditions and video data, and then making a reservation.

[0603] First, users input information such as location, style, and budget as their desired wedding conditions via a terminal. In addition, users upload photos and related video data to the system. This allows the system to identify the user's individual needs and gather the necessary materials to generate a concrete image.

[0604] Next, the server receives these input conditions and video data and matches them against wedding venue data in the database. In this step, a recommendation engine is used to suggest several optimal venues based on past data and the preferences of similar users.

[0605] Subsequently, the server uses image generation AI to create wedding ceremony images for each proposed venue based on the video data provided by the user. This allows the user to visually confirm a concrete image of the wedding ceremony.

[0606] The suggested information is provided to the user through the terminal's user interface. Based on the displayed information, the user can determine which venue best matches their ideal and view detailed information. If the user wishes to make a reservation for their chosen venue, the server will automatically proceed with the reservation process based on instructions from the terminal. Once the reservation is complete, the server will notify the user of the details and update the reservation information.

[0607] Finally, after using the service, users can submit feedback via their device. This feedback is analyzed on the server and used to improve the accuracy of the recommendation engine and enhance the service.

[0608] This system allows users to efficiently discover, visualize, and book wedding venues that meet their preferences. This integrated service process significantly simplifies the traditional, time-consuming process of choosing a venue, improving user convenience.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] Users enter their desired wedding conditions (location, style, budget) via their device and upload photos and related video data. The entered information is then sent to the server.

[0612] Step 2:

[0613] The server receives data from the user and stores it in the database. It validates the entered conditions and returns error messages to the terminal as needed.

[0614] Step 3:

[0615] The server's recommendation engine searches the database for wedding venue information based on the user's preferences, selects several suitable venues, and lists them.

[0616] Step 4:

[0617] The server uses image generation AI to create wedding images for each proposed venue based on the user's facial photograph. These generated images are temporarily stored.

[0618] Step 5:

[0619] The terminal displays a list of wedding venues received from the server, along with generated image files, to the user. It provides an interface for the user to select a venue of interest and view details.

[0620] Step 6:

[0621] If a user wishes to make a reservation for a wedding venue they have selected, they submit a reservation request from their device. The server receives this request and begins the reservation process with the venue.

[0622] Step 7:

[0623] If a reservation is secured, the server notifies the user of its details. At the same time, it records the user's reservation information in the database.

[0624] Step 8:

[0625] After using the service, users submit feedback from their devices. The server collects this feedback and uses it to improve the recommendation engine and the overall system.

[0626] (Example 1)

[0627] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0628] In recent years, there has been a growing demand for facility selection based on individualized criteria, and recommending facilities that accurately meet the needs of users is particularly difficult for important events such as weddings. Furthermore, there is a lack of systems that enable users to form a concrete image of what they want based on the information provided and make selections accordingly. In addition, there is a need to provide a smooth way to make reservations at selected facilities.

[0629] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0630] In this invention, the server includes means for acquiring information data and desired conditions, means equipped with a computing device for recommending appropriate facilities, means including a learning algorithm, means for utilizing a generative model, and means for automatically performing processing on facilities. This enables the recommendation of optimal facilities based on the user's desired conditions and the formation of concrete images utilizing the generated visual images, and then enables rapid reservation processing for the selected facilities.

[0631] "Information data" refers to all data, including user-provided preferences and video materials.

[0632] "Desired conditions" refer to information that represents the specific requirements and attributes of the facilities and services that the user is looking for.

[0633] "Computing equipment" refers to devices including computers and their peripherals used for data processing and analysis.

[0634] A "learning algorithm" is a mathematical method or model used to find patterns in data and predict the optimal outcome.

[0635] A "generative model" refers to a technology that includes algorithms for generating new data or images based on input data.

[0636] "Processing a facility" refers to a series of operations, including making reservations and arrangements for the facility selected by the user.

[0637] This invention is implemented as a system for users to efficiently select and reserve facilities that meet their specific requirements. Users first input their desired conditions and video data via a terminal. This information is then transmitted to a server.

[0638] The server first receives this information data and then uses computing devices to analyze it. Specifically, it processes the input data using learning algorithms and compares it with past user data in the database to identify the appropriate facility. This calculation uses machine learning libraries and database management systems, and is often implemented using software such as Python or SQL.

[0639] Next, the server uses a generative model to generate visual images from the video data. This generation process utilizes a generative AI model to concretize the visual representation of events at the target facility. The generative AI models used include image generation tools and APIs provided as open-source libraries.

[0640] As a concrete example, suppose a couple inputs conditions such as "a garden-style wedding in Tokyo, with a budget of under 3 million yen." The server receives these conditions as a prompt and presents them to the generative model in the form of "generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo."

[0641] The visual images generated in this way are presented to the user via the device and serve as information to support the optimal selection. If the user selects a facility they like, the server automatically initiates the reservation process for that facility, providing a smooth user experience.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] The user uses a terminal to input wedding details (e.g., region, style, budget) and video data (e.g., portraits). This data is sent from the terminal to the server. The input data arrives on the server as text and image data and is then sent directly to the next processing step.

[0645] Step 2:

[0646] The server analyzes the received information data. Using a computing device, it matches the desired conditions with past user data in the database and generates a list of optimal facilities based on this. This process utilizes machine learning algorithms to score facilities that meet the conditions and outputs the results.

[0647] Step 3:

[0648] The server uses a generative AI model to generate visual images based on video data provided by the user. A prompt (e.g., "Generate an image of a wedding ceremony at a garden-style wedding venue in Tokyo") is input to the generative AI model, and the model outputs an image that combines the video data with the given conditions.

[0649] Step 4:

[0650] The server sends the generated visual image and a list of facilities to the terminal. The terminal then presents this information to the user, who selects facilities while viewing the visual image. The selection results are sent back to the server via the terminal.

[0651] Step 5:

[0652] When a user wishes to make a reservation for a selected facility, they send that information to the server via their device. The server receives the reservation information and automatically proceeds with the reservation process for the selected facility. This process includes confirming and registering the date, time, and user information, and outputs the results as a notification.

[0653] Step 6:

[0654] Once the reservation is complete, the server will notify the user of the details (e.g., reservation number, date and time). This information will be sent via the terminal, allowing the user to confirm the reservation details.

[0655] (Application Example 1)

[0656] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0657] In e-commerce and service selection, users typically spend considerable time and effort choosing the right option from a multitude of choices. Furthermore, a lack of consistent and efficient payment processing methods for selected services and products can detract from the user experience. There is a need to address these challenges and provide a system that enables quick and efficient service selection and payment processes.

[0658] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0659] In this invention, the server includes means for acquiring video information and desired requirements, means for recommending appropriate facilities according to the desired requirements, means for generating an image based on the video information, and means for performing an automatic payment procedure according to the user's selection. This enables the user to efficiently and easily select the desired service and perform a seamless payment procedure.

[0660] "Visual information" refers to visual data such as facial photos and videos provided by users, and is used to clarify individual needs and images when selecting services or products.

[0661] "Desired requirements" refer to specific conditions such as the user's preferred region, style, and budget, and are used as criteria when selecting recommended services and products.

[0662] "Means of recommending appropriate facilities" refers to an internal system function that identifies and suggests the most suitable facility or service from a number of options based on the user's desired requirements.

[0663] "Means of generating images" refers to image generation technologies and processes used to visualize specific usage scenarios in proposed facilities and services based on video information provided by the user.

[0664] "Means of processing reservations" refers to the procedures that the system automatically performs to confirm and secure the date, time, and conditions for the facility or service selected by the user.

[0665] "Means of performing automatic payment procedures" refers to a processing function that automatically completes payment for the service selected by the user using pre-registered payment information.

[0666] This invention is a system for efficiently enabling users to select desired services or products and complete payment procedures. The server first receives video information and desired requirements from the user's terminal. The video information consists of visual data such as facial photos and videos provided by the user, while the desired requirements include specific conditions such as region, style, and budget.

[0667] Next, the server recommends suitable facilities based on the acquired preferences. This involves a process that uses a recommendation engine to refer to past data and the preferences of similar users to identify the best options. Furthermore, a generative AI model is used to generate images that visualize specific usage scenarios for the suggested facilities and services based on the video information.

[0668] The user then reviews and selects the options presented through the terminal. The server processes the reservation and automatic payment for the facility or service based on the user's selection. At this stage, an appropriate payment gateway is used to securely process the registered payment information.

[0669] As a concrete example, consider a scenario where a user uses a travel booking app to plan their honeymoon. The user inputs their destination, budget, and preferred style of stay, and the app uses AI to suggest options for sightseeing, accommodation, and activities. The user then reviews a visualized image of their chosen honeymoon, and the booking and payment are completed instantly.

[0670] Examples of prompts for a generative AI model:

[0671] "Please choose from the following honeymoon packages: Island Resort Package, City Sightseeing Package, or Mountain Retreat Package. We will then process your payment quickly."

[0672] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0673] Step 1:

[0674] Users input video information and desired requirements into the system using a terminal. The input includes the user's facial photograph and video data (video information), as well as desired conditions such as region, style, and budget. This data is sent from the terminal to the server, where its integrity is first verified. This information is then used as the basic data for system operation.

[0675] Step 2:

[0676] The server recommends appropriate facilities and services based on the received preferences. At this stage, a recommendation engine is used, matching the entered preferences with past data and similar cases in the database. This extracts the best service options and generates a list of recommendations to present to the user.

[0677] Step 3:

[0678] The server uses a generative AI model to generate images based on video information provided by the user. In this process, the received video information is used as material to generate images of specific usage scenarios at recommended facilities and services. This step utilizes image generation algorithms to create visually impressive content.

[0679] Step 4:

[0680] The user reviews the server-generated image and recommended options through their terminal. This is where the user interface comes into play, enabling the user to make choices easily and intuitively. The interface displays images, clarifies the user's options, and guides them to the next step.

[0681] Step 5:

[0682] Once the user makes a selection, the server automatically initiates the booking process for the selected facility or service. Simultaneously, an automated payment process is initiated using the registered payment information. The server uses a secure payment gateway to ensure reliable settlement. This confirms the booking, and the user is notified of its details.

[0683] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0684] As an embodiment of the present invention, a system is provided that combines an AI agent-based support system for selecting a wedding venue with an emotion engine that recognizes the user's emotions. This system can propose facilities that meet the user's preferences and carry out the entire process, from selection to booking, while taking emotional information into consideration.

[0685] First, the user enters their desired wedding conditions through their device and uploads photos and video data. Additionally, the device's built-in camera and microphone are used by an emotion engine to analyze the user's facial expressions and voice in real time, recognizing their current emotional state. This data, along with the user's desired conditions, is then sent to the server.

[0686] The server matches the received conditions and emotion data with wedding venue information in the database. The recommendation engine generates a list of suitable venues based on the user's preferences and emotions. Emotional information is also used to adjust the recommendations; for example, if the user feels joy, the system suggests elements that further emphasize that emotion.

[0687] The server uses image generation AI to create wedding images for suggested venues based on the user's facial photo and emotions. These images reflect emotional information; for example, if the user is judged to be satisfied, a brighter tone and more emotionally charged presentation can be set.

[0688] The generated list of wedding venues and their images are displayed to the user via their device. The user can visually confirm concrete images and, based on the presented information, select a venue, allowing for a more satisfying decision. Furthermore, if the user's emotions change during the selection process, the server can detect this and immediately adjust the suggestions.

[0689] The user requests a reservation from their terminal for the wedding venue they have selected. The server processes the reservation accordingly and notifies the user upon completion. Furthermore, the feedback received can be used to improve the overall system and enhance the accuracy of the emotion engine.

[0690] Through this format, a personalized venue selection experience that takes user emotions into account is provided, enabling users to make more satisfying choices.

[0691] The following describes the processing flow.

[0692] Step 1:

[0693] Users input their wedding preferences (location, style, budget) through their device and upload photos and related video data. The input from the device is transmitted to the server, and at the same time, the device uses its camera and microphone to collect the user's facial expressions and voice, generating emotion data in real time.

[0694] Step 2:

[0695] The server collects user preferences, video data, and emotional data received from the user and stores them in a database. This allows for data integration and lays the foundation for further processing.

[0696] Step 3:

[0697] The recommendation engine on the server searches the database, taking into account the user's preferences and emotional state. Emotional data is used for scoring to determine which venue best matches the user's current emotional state, and a list of recommended venues is generated.

[0698] Step 4:

[0699] The server's image generation AI creates wedding images for each proposed venue based on the user's facial photo and emotional data. Based on the emotional information, the image is adjusted; for example, if the user is nervous, a relaxed atmosphere is emphasized.

[0700] Step 5:

[0701] The terminal displays a list of suggested venues received from the server, along with generated image files, to the user. The user receives visual feedback, selects the venue they are most interested in, and is provided with an interactive interface to view detailed information and suggestions.

[0702] Step 6:

[0703] If a user wishes to make a reservation for a selected venue, they submit a reservation request from their device. The server accepts this request and proceeds with the reservation process with the relevant venue. Once the reservation is complete, the server notifies the user of the details.

[0704] Step 7:

[0705] After using the system, users provide feedback on the service through their device. This feedback is sent to the server and used to improve the accuracy of the sentiment engine and recommendation engine.

[0706] (Example 2)

[0707] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0708] Traditional venue selection and booking systems simply offered suggestions based on conditions, without considering the user's emotional state. As a result, they failed to make choices that suited the user's feelings and desires, leading to decreased satisfaction. Furthermore, the lack of visual representation made it difficult for users to form concrete images of their choices.

[0709] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0710] In this invention, the server includes means for acquiring video information and specification conditions, means for analyzing emotional states using a terminal, and means for recommending appropriate locations based on the user's specification conditions and emotional state. This enables personalized facility selection that takes into account the user's emotions and allows for highly satisfying choices.

[0711] "Video information" refers to facial images and video data acquired by the device, and is used to analyze the user's emotional state.

[0712] "Specification conditions" refer to information about desired facilities and conditions entered by the user, and are factors that influence the recommendation results.

[0713] "Device" refers to a device used by a user to input information or analyze emotional data, and includes smartphones and tablets.

[0714] "Emotional state" refers to the user's facial expressions and voice, which are analyzed in real time by the emotion engine, and is a useful element for customizing recommendation results.

[0715] A "suitable location" refers to a facility recommended by the server based on the user's specifications and emotional state, with the aim of increasing user satisfaction.

[0716] "Visual information" refers to images created by a generative AI model based on video information and emotional states, enabling users to form a concrete image of the facility.

[0717] "Reservation processing" refers to the procedure in which the server confirms a reservation for a specified location based on the user's selection, and has the function of notifying the user of the result.

[0718] "Opinions" refers to feedback from users, including evaluations and suggestions for improvement regarding recommendations and visual information.

[0719] This invention is a system to support personalized wedding venue selection that takes into account the user's emotions. Based on the user's desired conditions and emotional state, this system suggests suitable wedding venues and supports the booking process.

[0720] First, the user uses the device to input their specific wedding preferences. These preferences include specifications such as "a venue by the sea" and "accommodates up to 100 people." The device uses its built-in camera and microphone to analyze the user's facial expressions and voice in real time using an emotion engine to determine their current emotional state. If the user is smiling, the system recognizes this as "enjoying themselves."

[0721] This information is sent directly to the server. The server then compares the received specifications and emotional state with a database in the cloud. A recommendation engine then operates to suggest appropriate facilities, generating a list of facilities tailored to the user's conditions and emotions. Specifically, if the user desires a calm atmosphere, it will recommend places where they can relax.

[0722] Next, the server utilizes a generative AI model to create a wedding image at the suggested wedding venue, based on the user's facial photo and emotional information. This image reflects the user's emotional state, such as enjoyment, and for example, a visual with bright colors is generated.

[0723] The generated list of venues and visual information are presented to the user via the terminal. The user can select a venue based on this visual information. An example of a prompt message that can be input to the generating AI model is, "I'm looking for a wedding venue with a natural and homey atmosphere. I'm very happy right now. Please generate images of a wedding that meets these criteria."

[0724] Once a facility is selected, the user submits a reservation request from their terminal, and the server processes the reservation. The system also collects user feedback to improve the overall system and enhance the accuracy of the sentiment engine. This allows users to make more satisfying choices.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] The user enters their desired wedding conditions through a terminal. This input includes specific specifications such as "a venue by the sea" or "a casual atmosphere." The input data is retrieved through the terminal's interface and converted into a format that can be processed.

[0728] Step 2:

[0729] The device uses its built-in camera and microphone to record the user's facial expressions and voice in real time. Based on this, an emotion engine analyzes the data and recognizes the user's emotional state. For example, if the user is smiling, it generates emotion data indicating "enjoying themselves." This analysis result is then prepared to be sent to the server as output.

[0730] Step 3:

[0731] The server receives specification conditions and emotional data sent from the terminal. This input data is used to compare it with wedding venue information in the database. The recommendation engine analyzes this and selects venues that are suitable for the specification conditions and emotional state. For example, if the user is looking for a relaxed atmosphere, the server will generate a list of such venues.

[0732] Step 4:

[0733] The server utilizes a generative AI model to generate specific wedding images based on the user's facial photograph and emotional data. This calculation is based on the facial photograph; for example, if the user has positive emotions, the generated image will also have bright colors. The result is output as an image file and sent to the terminal.

[0734] Step 5:

[0735] The terminal displays a list of facilities and wedding ceremony images sent from the server to the user. The user makes a decision based on this information and notifies the system of their selected facility. For example, if a bright wedding ceremony image with the sea as a background is presented, the user will proceed with their selection accordingly.

[0736] Step 6:

[0737] The user sends a reservation request from their device to the facility they selected. The server receives this request and processes the reservation with the facility. Once the process is complete, the user is notified of the result via a confirmation message.

[0738] Step 7:

[0739] After a reservation is confirmed, the server collects feedback from the user. This feedback is used to improve user satisfaction and the accuracy of suggestions, and helps to improve the sentiment engine and recommendation engine.

[0740] (Application Example 2)

[0741] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] In the modern shopping experience, providing personalized recommendations that reflect users' emotions and preferences is challenging. Current technologies have limitations in accurately assessing a user's emotional state and incorporating that feedback in real time. This results in users having very limited information to make the best choices, leading to a lower quality of the experience.

[0743] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0744] In this invention, the server includes means for acquiring video data and desired conditions, means for recommending an appropriate installation location according to the desired conditions, means for generating an image based on the video data, means for analyzing the user's emotional state, means for adjusting the recommendation content based on the analysis results, and means for processing a reservation for the installation location. This enables dynamic recommendations that respond to the user's emotional state, providing a more personalized purchasing experience.

[0745] "Video data" refers to visual information acquired to analyze the user's emotional state.

[0746] "Desired conditions" refer to the requirements and preferences specified by the user when using the system, and are used in selecting recommended installation locations.

[0747] "Installation location" refers to facilities or stores recommended based on the user's preferences and emotional state.

[0748] An "image rendering" is generated based on acquired video data and provides a visual representation of the experience and product at the installation location.

[0749] "Emotional state" refers to the user's psychological state, identified by analyzing their facial expressions and tone of voice.

[0750] "Recommendations" refer to appropriate installation locations and product information presented based on the user's desired conditions and analyzed emotional state.

[0751] "Reservation processing" refers to the process of handling procedures and confirmations related to the installation location selected by the user.

[0752] In this configuration, when a user accesses the service via a smart device, the device first uses its built-in camera and microphone to acquire video and audio data. This data is then sent to an emotion recognition engine, which analyzes the user's emotional state based on their facial expressions and voice pitch. Software such as Affectiva or Microsoft Azure Cognitive Services is used for emotion recognition.

[0753] Next, the server receives this data in real time, along with the user's input preferences, and performs analysis to recommend the optimal installation location. During this process, a Recommendation Engine (e.g., Apache Mahout) is used to provide dynamic recommendations tailored to the user's preferences and emotions.

[0754] The server uses a generative AI model based on the acquired video data to synthesize imagery that realistically recreates the experience at the installation site. This allows users to have a more concrete and visual experience. For example, this could be done using Python with TensorFlow or PyTorch.

[0755] This image is displayed on a smart device's screen, and the user selects an installation location based on the presented content through emotion recognition. Once the selection is made, the server executes a reservation procedure for the selected installation location. This process is hosted on a cloud system.

[0756] For example, in a virtual bookstore, the system could capture the emotions of users who show interest in the cover of a book they are browsing and display recommended books from related genres and publishers. This also allows for personalized promotions based on those emotions.

[0757] An example of a prompt for a generative AI model might be: "Create a script that suggests related products for items in which the user has shown a joyful expression, and provide the most appealing product information in real time based on the user's emotional data."

[0758] This invention makes it possible to provide users with personalized experiences and achieve higher satisfaction levels.

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] The device uses its camera and microphone to acquire video and audio data of the user in real time. This data is prepared as input for the emotion recognition engine. Specifically, it captures the user's facial expressions and voice pitch, and uses this data during the session without saving it to a database.

[0762] Step 2:

[0763] The device sends the acquired video and audio data to an emotion recognition engine. This engine analyzes the acquired data and identifies the user's emotional state. Using software such as Microsoft Azure Cognitive Services, it performs the analysis and outputs the results as an emotional state such as "joy," "interest," or "surprise."

[0764] Step 3:

[0765] The server matches the user's desired conditions with the emotional state obtained in step 2 against the database and generates a list of installation locations using the Recommendation Engine. Using desired conditions and emotional state as input, it lists appropriate installation locations based on the analysis results.

[0766] Step 4:

[0767] The server creates image data using a generative AI model. It takes user preferences, emotional states, and installation location data as input to output an image that simulates the experience at the installation location. Image generation is performed using TensorFlow or PyTorch.

[0768] Step 5:

[0769] The terminal displays a list of installation locations and image files received from the server to the user. This display is done via a user interface, allowing the user to visually review the images and select a more appropriate installation location based on emotional information.

[0770] Step 6:

[0771] The terminal proceeds with the reservation process for the installation location selected by the user. At this stage, the server confirms the reservation on the cloud system in response to the user's request and outputs a completion message to the terminal.

[0772] Step 7:

[0773] The server collects user feedback and stores it in a database. This helps improve the accuracy of the Recommendation Engine and emotion recognition engine, contributing to overall system improvement. This process will lead to improved user experience in the future.

[0774] The processing steps described above enable a personalized experience based on the user's emotions and preferences.

[0775] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0776] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0777] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0778] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0779] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0780] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0781] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0782] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0783] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0784] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0785] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0786] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0787] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0788] 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.

[0789] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0790] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0791] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0792] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0793] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0794] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0795] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0796] The following is further disclosed regarding the embodiments described above.

[0797] (Claim 1)

[0798] Means for acquiring video data and desired conditions,

[0799] A means of recommending appropriate facilities according to the desired conditions,

[0800] A means for generating an image based on the video data,

[0801] A means for processing reservations for the facility,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, further comprising means for presenting the aforementioned image to the user.

[0805] (Claim 3)

[0806] The system according to claim 1, further comprising means for collecting user feedback based on the aforementioned desired conditions and image.

[0807] "Example 1"

[0808] (Claim 1)

[0809] Means for obtaining information data and desired conditions,

[0810] A means equipped with a computing device for recommending appropriate facilities according to the desired conditions,

[0811] A means including a learning algorithm for recommending facilities based on past user data,

[0812] A means of using a generative model that generates a visual image based on the generated image,

[0813] A means for automatically performing processing on the said facility,

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, further comprising means for presenting the aforementioned visual image to a user and obtaining their evaluation.

[0817] (Claim 3)

[0818] The system according to claim 1, further comprising means for collecting and analyzing responses from users based on the aforementioned desired conditions and visual images.

[0819] "Application Example 1"

[0820] (Claim 1)

[0821] Means for obtaining video information and desired requirements,

[0822] A means of recommending appropriate facilities according to the desired requirements,

[0823] A means for generating an image based on the video information,

[0824] A means for processing reservations for the facility,

[0825] A means of automatically processing payments based on user selections,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, wherein the aforementioned image is presented to the user.

[0829] (Claim 3)

[0830] The system according to claim 1, which collects responses from users based on the aforementioned desired requirements and images.

[0831] "Example 2 of combining an emotion engine"

[0832] (Claim 1)

[0833] Means for acquiring video information and specification conditions,

[0834] A means of analyzing emotional states using a terminal,

[0835] A means of recommending an appropriate location based on the user's specifications and emotional state,

[0836] A means for generating visual information based on video information and emotional states,

[0837] Means for performing reception processing for the said location,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, further comprising means for presenting the aforementioned visual information to a user.

[0841] (Claim 3)

[0842] The system according to claim 1, further comprising means for collecting user feedback based on the aforementioned specifications and visual information.

[0843] "Application example 2 when combining with an emotional engine"

[0844] (Claim 1)

[0845] Means for acquiring video data and desired conditions,

[0846] A means of recommending an appropriate installation location according to the desired conditions,

[0847] A means for generating an image based on the video data,

[0848] A means of analyzing the emotional state of users,

[0849] A means of adjusting the recommendation content based on the analysis results,

[0850] A means for processing a reservation for the installation location,

[0851] A system that includes this.

[0852] (Claim 2)

[0853] The system according to claim 1, further comprising means for presenting the aforementioned image and information necessary for the user.

[0854] (Claim 3)

[0855] The system according to claim 1, further comprising means for collecting user opinions based on the aforementioned desired conditions, image data, and sentiment analysis results. [Explanation of Symbols]

[0856] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for acquiring video data and desired conditions, A means of recommending appropriate facilities according to the desired conditions, A means for generating an image based on the video data, A means for processing reservations for the facility, A system that includes this.

2. The system according to claim 1, further comprising means for presenting the aforementioned image to the user.

3. The system according to claim 1, further comprising means for collecting user feedback based on the aforementioned desired conditions and image.

Images