System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting personal data; means for analyzing the collected personal data using a generative AI model; means for generating a recommendation list based on an analysis result; and means for notifying user terminals of the recommendation list.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditionally, many people spend a lot of time using Google Maps and other apps to search for restaurants and interesting shops. Furthermore, it is extremely difficult to choose a restaurant that satisfies all participants when gathering with friends or colleagues. Therefore, there is a need for a method to efficiently recommend suitable places by utilizing individual social media accounts and activity histories. Furthermore, when visiting a specific location, manually creating a schedule that includes nearby spots is time-consuming. Therefore, a system that can solve these issues is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. Specifically, it provides a system including a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, a means for generating a recommendation list based on the analysis results, and a means for notifying a user terminal of the recommendation list. Furthermore, by including data from social networking services, behavioral history, and impression data as personal data, highly accurate recommendations are realized. Furthermore, by including a means for a user to input a visit plan, a means for acquiring information on spots nearby the planned visit, a means for generating an automatic schedule based on the visit plan and information on nearby spots, and a means for notifying a user terminal of the automatic schedule, it is possible to provide spot information and a schedule that are optimal for the user's visit plan.

[0006] "Personal data" is a general term for personal information such as data on social networking services related to a user, behavioral history, and impression data.

[0007] "Social networking service data" refers collectively to information such as posts, check-ins, and photos generated by users on social networking platforms.

[0008] "Behavioral history" refers to information about the places a user visits and the length of time they stay there.

[0009] A "generative AI model" is an artificial intelligence algorithm that learns from a specific dataset and generates recommendations based on user behavior and sensibilities.

[0010] A "recommendation list" is a list of restaurants and spots selected based on a user's preferences and behavior.

[0011] "Analysis results" refers to analytical information obtained after the generative AI model processes collected personal data.

[0012] "User terminal" refers to hardware devices such as mobile devices, tablets, and PCs used by users.

[0013] "Visit schedule" refers to information about places that the user plans to visit in the future and the scheduled dates and times.

[0014] "Nearby spot information" refers to information about interesting places and facilities near the place the user has set as a planned visit location.

[0015] An "automatic schedule" is a timetable that is automatically created by a generative AI model based on planned visits and information about related nearby spots. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10]1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The system of the present invention collects personal data from users, analyzes it using a generative AI model, and recommends optimal locations. Furthermore, it is possible to automatically generate and propose schedules for specific planned visits. Specific embodiments for implementing the present invention are described in detail below.

[0038] Data collection and analysis

[0039] Social media data collection

[0040] User: The user installs the application and connects their social media account, which grants access to the data that is collected.

[0041] Device: Obtains authentication information for the linked SNS and sends it to the server.

[0042] Server: Uses SNS APIs to collect user posts, photos, and check-in information and store it in a database for analysis.

[0043] Collecting behavioral history

[0044] User: Starts collecting location information by granting location permission to the application.

[0045] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[0046] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[0047] Collecting feedback data

[0048] Users: Enter their impressions and ratings of the places they visit within the app.

[0049] Terminal: Sends the inputted impression data to the server.

[0050] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[0051] Recommendation generation

[0052] User data integration and analysis

[0053] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0054] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[0055] Generating a recommendation list

[0056] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[0057] Server: Sends the generated recommendation list to the user's device and notifies them.

[0058] Recommendation notifications

[0059] On the device: The received recommendation list is notified to the user and displayed within the app.

[0060] User: Select a place of interest from the recommended list.

[0061] Automatic schedule generation

[0062] Schedule a visit

[0063] User: Enter plans to visit specific locations in the app and schedule the visit.

[0064] Terminal: Sends the scheduled visit information to the server.

[0065] Suggestions for nearby spots

[0066] Server: Analyzes and suggests points of interest near the location you plan to visit.

[0067] Server: Sends the proposal to the user's device and notifies them.

[0068] On the device: Display the suggested spot and ask the user for confirmation.

[0069] User: Review the suggested spots and select the one they want to go to.

[0070] Automatic Schedule Generation

[0071] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0072] Server: The completed schedule is sent to the user's terminal and notified.

[0073] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[0074] Specific examples

[0075] The user installs the application and connects to a social media account (e.g., Twitter). Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0076] In this way, by specifically implementing the present invention, it is possible to recommend efficient and appropriate locations to users and propose planned schedules.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[0080] Step 2:

[0081] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[0082] Step 3:

[0083] Server: Uses the SNS API to collect data such as user posts, photos, and check-in information and store it in a database.

[0084] Step 4:

[0085] User: Allows the application to use location information.

[0086] Step 5:

[0087] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[0088] Step 6:

[0089] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[0090] Step 7:

[0091] Users: Write their thoughts about the places they visited within the app.

[0092] Step 8:

[0093] Terminal: Sends the inputted impression data to the server.

[0094] Step 9:

[0095] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[0096] Step 10:

[0097] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[0098] Step 11:

[0099] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[0100] Step 12:

[0101] Server: Based on the analysis results, a generative AI model is used to select the best restaurants and spots for the user and their friends.

[0102] Step 13:

[0103] Server: Sends the generated recommendation list to the user's device.

[0104] Step 14:

[0105] On the device: The received recommendation list is notified to the user and displayed within the app.

[0106] Step 15:

[0107] User: Select a place of interest from the recommended list.

[0108] Step 16:

[0109] User: Enters an appointment in the app, setting the locations and dates they want to visit.

[0110] Step 17:

[0111] Terminal: Sends the scheduled visit information to the server.

[0112] Step 18:

[0113] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[0114] Step 19:

[0115] Server: Sends information about nearby spots to the user's device.

[0116] Step 20:

[0117] On the device: The suggested spots are notified to the user and displayed within the app.

[0118] Step 21:

[0119] User: Review the suggested spots and select the places that interest them.

[0120] Step 22:

[0121] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0122] Step 23:

[0123] Server: Sends the generated schedule to the user's terminal.

[0124] Step 24:

[0125] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[0126] Through this series of steps, users can efficiently receive recommendations for the best places and generate a detailed schedule based on their planned visits.

[0127] Example 1

[0128] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0129] Conventional systems have difficulty generating recommendations based on users' interests. They also lack the functionality to automatically generate and propose optimal schedules for planned visits, requiring users to make their own plans. Furthermore, they were unable to efficiently collect and analyze various distributed data sources (social media data, behavioral history, and opinion data) and provide recommendations based on that data.

[0130] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0131] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the generation of a highly accurate recommendation list based on the user's interests and concerns. The server also includes a means for collecting the user's location information and recording their behavioral history, a means for collecting and classifying impression data, and a means for generating an automatic schedule based on the user's planned visits and information on nearby spots. This allows the user to automatically receive an optimal visit plan based on their behavioral history and impression data, enabling them to visit various places efficiently and in a planned manner.

[0132] "Personal data" is a general term for personal information, behavioral data, impression data, etc. related to a user.

[0133] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate and analyze data.

[0134] "Analysis" is the process of using collected data to find patterns or extract specific information.

[0135] A "recommendation list" is a list of places and services suggested based on a user's interests.

[0136] "Social networking services," abbreviated as SNS, are services that allow people to share information and interact with each other via the Internet.

[0137] "Behavioral history" is a record of a user's location information and visited destinations.

[0138] "Opinion data" is data that includes evaluations and opinions of places visited by users and services experienced by users.

[0139] "Planned visits" is information about places the user wants to visit in the future and events the user is planning.

[0140] "Neighborhood spot information" is information about places and facilities of interest in the vicinity of a destination that the user has set as a visiting schedule.

[0141] An "automatic schedule" is a schedule that automatically generates the optimal order of visits and time allocation based on the input visit plans and information on nearby spots.

[0142] "User terminal" is a general term for electronic devices that can be directly operated by a user, such as smartphones and tablets.

[0143] "Notification" is the act of displaying a message or alert to convey information to the user.

[0144] The system of the present invention collects personal data from users, analyzes it with a generative AI model, and recommends optimal locations. It also makes it possible to automatically generate and propose schedules for specific visits.

[0145] Data collection and analysis

[0146] Social media data collection

[0147] User: A user installs an application and connects their social network account (e.g., Twitter), which allows the application to access the user's social network data.

[0148] Device: The device obtains authentication information for the linked SNS and sends that information to the server.

[0149] Server: The server uses social media APIs (e.g., Twitter API) to collect user posts, photos, and check-in information, and stores this data in a database for analysis.

[0150] Collecting behavioral history

[0151] User: The user grants the application permission to use and collect location information.

[0152] Device: The device continuously collects GPS data and records the locations the user has visited and the time spent there.

[0153] Server: The server analyzes the location data to identify places the user frequently visits and stores that cater to specific genres of interest.

[0154] Collecting feedback data

[0155] User: The user enters their impressions and ratings of the places they visit into the application.

[0156] Terminal: The terminal sends the impression data entered by the user to the server.

[0157] Server: The server analyzes the sentiment data using a natural language processing algorithm (e.g., Python's NLTK library) and classifies the content as positive or negative.

[0158] Generating a recommendation list

[0159] User data integration and analysis

[0160] Server: The server integrates social media data, behavioral history, and opinion data to generate a profile that reflects the user's interests and preferences. It also extracts common interests among multiple users.

[0161] Recommendation generation

[0162] Server: The server uses a generative AI model (e.g., OpenAI's GPT-4 model) to generate a recommendation list based on the profile.

[0163] Server: Sends the generated recommendation list to the user's device and notifies them.

[0164] Recommendation notifications

[0165] Device: The device notifies the user of the received recommendation list and displays the list within the app.

[0166] User: The user selects the place they want to visit from the displayed list.

[0167] Automatic schedule generation

[0168] Schedule a visit

[0169] User: The user enters their plans to visit a specific location in the application and schedules the visit.

[0170] Terminal: The terminal sends the set visit schedule to the server.

[0171] Suggestions for nearby spots

[0172] Server: The server analyzes and suggests points of interest near the location you plan to visit.

[0173] Server: Sends the proposal to the user's device and notifies them.

[0174] Terminal: The terminal displays the suggested spots and asks the user for confirmation.

[0175] User: The user reviews the suggested spots and selects the place they want to go.

[0176] Automatic Schedule Generation

[0177] Server: The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[0178] Server: Sends the completed schedule to the user's terminal and notifies them.

[0179] Device: The device will notify the user of the generated schedule and allow them to add it to their calendar.

[0180] Specific examples

[0181] The user installs the application and connects their Twitter account. Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0182] Example of a prompt for the proposed AI model

[0183] "Generate a list of recommendations that are optimal for each user based on their social media data, location information, and impressions of their visit. For example, if a user plans to go strawberry picking this weekend, suggest nearby cafes and hot springs."

[0184] In this way, the present invention can recommend efficient and appropriate locations to users and propose well-planned schedules.

[0185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0186] Step 1: User connects social media account

[0187] Specific behavior:

[0188] The user installs the application and connects their social media account (e.g., Twitter).

[0189] Input: Social media account credentials (e.g., OAuth token).

[0190] The device obtains authentication information from the linked SNS and uses it to authorize access to the necessary data.

[0191] Output: The social media credentials are sent to the server.

[0192] Step 2: Collect social media data

[0193] Specific behavior:

[0194] The server uses the SNS API to collect user posts, photos, check-in information, etc.

[0195] Input: The SNS credentials received by the server.

[0196] The server stores this data in a database for analysis.

[0197] Output: Saved social media data.

[0198] Step 3: Location Permissions and Collection

[0199] Specific behavior:

[0200] The user allows the application to use location information.

[0201] Input: User permission to use location information.

[0202] The device continuously collects GPS data and records the user's past visits and time spent there.

[0203] Output: Collected GPS data is sent to a server.

[0204] Step 4: Analyzing behavioral history

[0205] Specific behavior:

[0206] The server analyzes the received location data to identify frequently visited locations and stores of interest.

[0207] Input: GPS data received by the server.

[0208] The server applies data analysis algorithms to extract visitation patterns.

[0209] Output: Analysis results (frequently visited places and trends).

[0210] Step 5: Enter and submit your feedback

[0211] Specific behavior:

[0212] Users enter their impressions and ratings of the places they visit into the application.

[0213] Input: User-entered feedback and ratings.

[0214] The terminal transmits the input impression data to the server.

[0215] Output: The feedback data sent to the server.

[0216] Step 6: Analyze the sentiment data

[0217] Specific behavior:

[0218] The server analyzes the feedback data using a natural language processing algorithm and classifies the content as positive or negative.

[0219] Input: The sentiment data sent to the server.

[0220] The server uses Python's NLTK library to classify the data.

[0221] Output: Classified sentiment data (positive / negative).

[0222] Step 7: Create a user profile

[0223] Specific behavior:

[0224] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0225] Input: Stored social media data, analyzed behavioral history, and classified opinion data.

[0226] The server aggregates this data to create a profile that reflects the user's interests and concerns.

[0227] Output: User profile.

[0228] Step 8: Generate a recommendation list

[0229] Specific behavior:

[0230] The server uses a generative AI model (e.g., GPT-4) to generate a recommendation list from the user profile.

[0231] Input: User profile.

[0232] The server creates a prompt for the AI ​​model and inputs it into the model.

[0233] Example prompt: "Generate a list of recommendations that are optimal for the user based on their social media data, location information, and impressions of their visit. For example, the user is planning to go strawberry picking this weekend. Suggest nearby cafes, hot springs, etc."

[0234] Output: The generated recommendation list.

[0235] Step 9: Notification of recommendation list

[0236] Specific behavior:

[0237] The server sends the generated recommendation list to the user's terminal and notifies the user.

[0238] Input: The generated recommendation list.

[0239] The terminal receives the recommendation list and notifies the user.

[0240] Output: Notification of recommendation list.

[0241] Step 10: Schedule a visit

[0242] Specific behavior:

[0243] The application allows users to input plans to visit specific locations and schedule visits.

[0244] Enter: Visit planned.

[0245] The terminal transmits the set visit schedule to the server.

[0246] Output: The visit schedule sent to the server.

[0247] Step 11: Suggest nearby spots

[0248] Specific behavior:

[0249] The server analyzes and suggests points of interest near the place you plan to visit.

[0250] Input: Visit schedule information.

[0251] The server uses an AI model to analyze points of interest and generate suggestions.

[0252] Output: Suggested points of interest are sent to the device.

[0253] Step 12: Generate an automatic schedule

[0254] Specific behavior:

[0255] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[0256] Input: Planned visits and nearby spot information.

[0257] The server uses a schedule generation algorithm to create an optimal schedule.

[0258] Output: The generated automatic schedule.

[0259] Step 13: Auto-Schedule Notifications

[0260] Specific behavior:

[0261] The server transmits the completed schedule to the user terminal and notifies it.

[0262] Input: The generated automatic schedule.

[0263] The terminal notifies the user of the received schedule so that the user can add it to their calendar.

[0264] Output: Auto-schedule notifications.

[0265] Through the above steps, the system of the present invention can recommend places based on the user's interests and automatically generate an efficient visiting schedule.

[0266] (Application example 1)

[0267] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0268] Conventional food delivery services have been unable to fully utilize users' personal data, making it difficult to provide optimal services tailored to individual preferences and schedules. Furthermore, they lacked functionality to improve the user experience, such as suggesting optimal delivery times based on planned visits and automatically generating schedules. This created a need for a new system that would significantly improve user convenience.

[0269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0270] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the provision of a delivery service optimized for the user's preferences and schedule. The server also includes a means for proposing the optimal service delivery timing based on the user's schedule, a means for generating a schedule based on the schedule, and a means for notifying the user terminal of the automatic schedule. This enables the delivery service optimized for the user's schedule and the generation of an automatic schedule, significantly improving the user experience.

[0271] "Personal data" refers to a user's personal information, including data from social networking services, behavioral history, and impression data.

[0272] A "generative AI model" is an artificial intelligence model that analyzes collected personal data and generates the optimal recommendation list for the user.

[0273] A "recommendation list" is a list of optimal services and places suggested to a user based on analyzed personal data.

[0274] "User terminal" is a general term for electronic devices used by users, including smartphones, tablets, etc.

[0275] "Location information" refers to data about a user's current location and past visited locations obtained using GPS or other technologies.

[0276] An "automatic schedule" is a schedule that the system automatically generates based on the user's schedule.

[0277] "Service provision timing" refers to the time for providing the service at the optimal timing according to the user's schedule and activities.

[0278] The system of the present invention is a food delivery assistant that collects personal data from users, analyzes it using a generative AI model, and generates an optimal recommendation list and schedule. This system uses a smartphone as its primary device and has multiple means to improve the user experience.

[0279] Data collection and analysis

[0280] Social media data collection

[0281] User: The user installs the application and connects their social networking service (SNS) account, thereby granting permission for data collection.

[0282] Device: Obtains authentication information for the linked SNS and sends it to the server.

[0283] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database for analysis.

[0284] Collecting behavioral history

[0285] User: Starts collecting location information by granting location permission to the application.

[0286] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[0287] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[0288] Collecting feedback data

[0289] Users: Enter their impressions and ratings within the app about places they visit and food they order.

[0290] Terminal: Sends the inputted impression data to the server.

[0291] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[0292] Recommendation generation

[0293] User data integration and analysis

[0294] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0295] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[0296] Generating a recommendation list

[0297] Server: Uses a generative AI model to analyze each user's tastes and preferences and generate a list of delivery restaurants and menus that are best suited for the user and their friends.

[0298] Server: Sends the generated recommendation list to the user's device and notifies them.

[0299] Automatic schedule generation

[0300] Schedule a visit

[0301] User: Enter plans to visit specific locations in the app and schedule the visit.

[0302] Terminal: Sends the scheduled visit information to the server.

[0303] Suggestions for nearby spots

[0304] Server: Analyzes and suggests points of interest near the location you plan to visit.

[0305] Server: Sends the proposal to the user's device and notifies them.

[0306] On the device: Display the suggested spot and ask the user for confirmation.

[0307] User: Review the suggested spots and select the one they want to go to.

[0308] Automatic Schedule Generation

[0309] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0310] Server: The completed schedule is sent to the user's terminal and notified.

[0311] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[0312] Hardware and software used

[0313] The system includes the following hardware and software:

[0314] Smartphone (used as user device)

[0315] Server (data analysis and storage)

[0316] GPS module (acquisition of location information)

[0317] SNS API (acquiring data from social networking services)

[0318] Natural language processing algorithms (analysis of sentiment data, Transformers, etc.)

[0319] Generative AI model (recommendation list generation)

[0320] Calendar app (schedule notification and management)

[0321] Examples of specific examples and prompts

[0322] Specific examples

[0323] The user installs the application and connects their social media account. Next, they allow the use of location information and enter their thoughts on dishes they have previously ordered. The server collects and analyzes this data. If the user selects "I'm going on a picnic with friends this weekend," the server will suggest nearby delivery restaurants and new menus and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0324] Prompt Sentence Examples

[0325] user_id = "example_user"

[0326] visit_plan = "2023-12-31 18:00:00"

[0327] main(user_id, visit_plan)

[0328] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0329] Step 1:

[0330] Collection of Personal Data

[0331] Users install the application and connect their SNS account. This allows the server to collect user posts, photos, and check-in information via the SNS API. Specifically, the server obtains user data from the SNS API and stores it in a database.

[0332] Step 2:

[0333] Location information collection

[0334] Users allow applications to use their location information. The device continuously collects GPS data and sends it to a server, which records the places visited and the time spent there, and stores it in a database.

[0335] Step 3:

[0336] Inputting feedback data

[0337] Users input their impressions and ratings of the places they visited and the food they ordered into the application. The device sends the input impression data to the server and stores it in a database.

[0338] Step 4:

[0339] Data integration and analysis

[0340] The server integrates the collected social media data, location information, and opinion data to generate a user profile. Using a generative AI model, this data is analyzed to identify the user's preferences. The integrated data is used as input, and the generative AI model analyzes it, outputting user preference data.

[0341] Step 5:

[0342] Generating a recommendation list

[0343] Based on the analysis results, the server generates a recommendation list of delivery restaurants and menus that best suit the user's preferences. Using the preference data as input, the generative AI model generates a recommendation list, which is then output.

[0344] Step 6:

[0345] Recommendation list notification

[0346] The server transmits the generated recommendation list to the user's terminal, and the terminal displays the received recommendation list to the user within the application.

[0347] Step 7:

[0348] Schedule a visit

[0349] The user enters a visit schedule for a specific location and time in the application, and the device sends the visit schedule to the server and stores it in a database.

[0350] Step 8:

[0351] Obtaining and suggesting information about nearby spots

[0352] The server analyzes and suggests interesting spots near the location the user plans to visit. The analysis results are sent to the user's device, which displays the suggestions to the user. The user then checks the suggested spots and selects the ones they want to visit.

[0353] Step 9:

[0354] Automatic Schedule Generation

[0355] The server automatically generates a schedule based on the visit schedule and the nearby spot information selected by the user. The optimal delivery time and visit schedule are generated and sent to the user's terminal.

[0356] Step 10:

[0357] Schedule notification and management

[0358] The device notifies the user of the generated schedule and allows the user to add it to applications such as a calendar, allowing the user to use the delivery service according to an optimal schedule.

[0359] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0360] The present invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. The present invention also incorporates an emotion engine that recognizes the user's emotions, allowing the system to flexibly adjust the recommendation list based on the user's emotional state. Specific embodiments for implementing the present invention are described in detail below.

[0361] Data collection and analysis

[0362] Social media data collection

[0363] User: The user installs the application and connects their social media account, which grants them access to the data that is collected.

[0364] Device: Obtains authentication information for the linked SNS and sends it to the server.

[0365] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database.

[0366] Collecting behavioral history

[0367] User: Grants location permission to the application.

[0368] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[0369] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[0370] Collecting feedback data

[0371] Users: Write their thoughts about the places they visited within the app.

[0372] Terminal: Sends the inputted impression data to the server.

[0373] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[0374] Analysis by emotion engine

[0375] Server: Analyzes social media data and sentiment data and runs an emotion engine to identify the user's emotional state.

[0376] Server: Stores the emotional states identified by the emotion engine in a database.

[0377] Recommendation generation and tuning

[0378] User data integration and analysis

[0379] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0380] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[0381] Generating a recommendation list

[0382] Server: Uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of restaurants and spots that are best suited for the user and their friends.

[0383] Server: Sends the generated recommendation list to the user's device and notifies them.

[0384] Recommendation notifications

[0385] On the device: The received recommendation list is notified to the user and displayed within the app.

[0386] User: Select a place of interest from the recommended list.

[0387] Automatic schedule generation

[0388] Schedule a visit

[0389] User: Enter plans to visit specific locations in the app and schedule the visit.

[0390] Terminal: Sends the scheduled visit information to the server.

[0391] Suggestions for nearby spots

[0392] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[0393] Server: Sends the proposal to the user's device and notifies them.

[0394] On the device: Display the suggested spot and ask the user for confirmation.

[0395] User: Review the suggested spots and select the one they want to go to.

[0396] Automatic Schedule Generation

[0397] Server: Automatically generate a schedule based on planned visits and selected nearby spots.

[0398] Server: Sends the completed schedule to the user's terminal and notifies them.

[0399] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[0400] Specific examples

[0401] The user installs the application and connects their social media account (e.g., Twitter). Next, they allow the use of location information and enter their thoughts about cafes they have visited in the past. If the emotion engine detects from social media data that the user is feeling stressed, the server will prioritize recommendations of relaxing cafes and quiet restaurants. If the user selects "I'm going strawberry picking on the weekend," the server will suggest nearby spots (e.g., relaxing cafes and hot springs) and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0402] In this way, by specifically implementing the present invention, it is possible to provide flexible recommendations according to the user's emotional state and propose planned schedules.

[0403] The processing flow will be explained below.

[0404] Step 1:

[0405] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[0406] Step 2:

[0407] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[0408] Step 3:

[0409] Server: Uses SNS APIs to collect data such as user posts, photos, and check-in information and store it in a database.

[0410] Step 4:

[0411] User: Allows the application to use location information.

[0412] Step 5:

[0413] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[0414] Step 6:

[0415] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[0416] Step 7:

[0417] Users: Write their thoughts about the places they visited within the app.

[0418] Step 8:

[0419] Terminal: Sends the inputted impression data to the server.

[0420] Step 9:

[0421] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[0422] Step 10:

[0423] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[0424] Step 11:

[0425] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[0426] Step 12:

[0427] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[0428] Step 13:

[0429] Server: Sends the generated recommendation list to the user's device.

[0430] Step 14:

[0431] On the device: The received recommendation list is notified to the user and displayed within the app.

[0432] Analysis and adjustment by emotion engine

[0433] Step 15:

[0434] Server: Uses an emotion engine to analyze social media data and sentiment data to identify the user's emotional state.

[0435] Step 16:

[0436] Server: Stores the emotional states identified by the emotion engine in a database.

[0437] Step 17:

[0438] Server: Adjust and regenerate the recommendation list depending on the emotional state.

[0439] Step 18:

[0440] Server: Sends the tailored recommendation list to the user's device.

[0441] Automatic schedule generation

[0442] Step 19:

[0443] User: Enter plans to visit specific locations in the app and schedule the visit.

[0444] Step 20:

[0445] Terminal: Sends the scheduled visit information to the server.

[0446] Step 21:

[0447] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[0448] Step 22:

[0449] Server: Sends the proposal to the user's device and notifies them.

[0450] Step 23:

[0451] On the device: Display the suggested spot and ask the user for confirmation.

[0452] Step 24:

[0453] User: Review the suggested spots and select the one they want to go to.

[0454] Step 25:

[0455] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0456] Step 26:

[0457] Server: Sends the generated schedule to the user's terminal.

[0458] Step 27:

[0459] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[0460] Through this series of steps, users can efficiently receive recommendations for the best places to visit and generate a detailed schedule based on their planned visits. By combining this with an emotion engine, it is also possible to flexibly adjust the schedule according to the user's emotional state.

[0461] Example 2

[0462] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0463] In modern society, recommendation systems that meet the needs of individual users are extremely important, but conventional systems have had difficulty making recommendations that take into account the emotional state of each user. In particular, although recommending places that reduce users' stress and emotional anxiety would be effective, there were a lack of methods to achieve this. Furthermore, generating and proposing flexible and efficient schedules based on planned visits was also difficult.

[0464] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0465] In this invention, the server includes means for collecting personal data of users, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results, means for notifying the user terminal of the recommendation list, means for using an emotion engine to analyze the user's emotional state, and means for flexibly adjusting the recommendation list based on the analysis results. This makes it possible to provide a flexible recommendation list tailored to the user's emotions and automatically generate an efficient schedule based on the user's planned visits.

[0466] "Personal data" refers to information specific to an individual user, such as the user's behavior, interests, and impressions, and includes data from social networking services, behavioral history, and impression data.

[0467] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze user data and generate appropriate information or suggestions based on the results. Specific examples include natural language generation models.

[0468] An "emotion engine" refers to an algorithm that analyzes a user's emotional state from collected data, and this is achieved using emotion analysis tools and APIs.

[0469] A "recommendation list" refers to a list of places, products, etc. recommended to a user, generated based on analyzed data.

[0470] A "visit plan" refers to a plan to visit a particular location in the future that a user inputs into the application.

[0471] "Nearby spot information" refers to information about interesting places and facilities located around the place you plan to visit.

[0472] "Automatic schedule" refers to a schedule of activities that is automatically generated by an algorithm based on the user's planned visits and information about nearby spots.

[0473] "User terminal" refers to a digital device that is directly used by a user, such as a smartphone or tablet.

[0474] "Notification" refers to the act of conveying information from the system to the user, including push notifications and in-app displays.

[0475] "Analysis results" refers to the analytical conclusions and insights obtained after processing collected data using generative AI models and emotion engines.

[0476] "Flexible adjustment" refers to dynamically changing the recommendation list and suggestions depending on the user's emotions and situation.

[0477] This invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. It also incorporates an emotion engine that recognizes the user's emotional state and has the ability to flexibly adjust the recommendation list based on the user's emotional state.

[0478] Hardware and software used in data collection

[0479] Social media data collection

[0480] A user installs the application and connects their social media account, which allows access to the data that is collected.

[0481] The terminal acquires the user's SNS authentication information and sends it to the server.

[0482] The server uses SNS APIs (e.g., Twitter API) to collect user posts, photos, and check-in information. This data is stored in a database.

[0483] Collecting behavioral history

[0484] The user grants the application permission to use location information.

[0485] The device collects GPS data in real time and records the places you visit and the time you stay there.

[0486] The server analyzes the collected location data and stores the frequency of visits and length of stay in a database.

[0487] Collecting feedback data

[0488] Users enter their thoughts about the places they visited within the app.

[0489] The terminal transmits the input impression data to the server.

[0490] The server receives the data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), and evaluates it as positive or negative. The evaluation results are also stored in a database.

[0491] Analysis by emotion engine

[0492] The server analyzes the social media data and sentiment data, and runs an emotion engine (e.g., IBM Watson) algorithm to identify the user's emotional state. The analysis results are stored in a database.

[0493] Recommendation generation and notification

[0494] Generating a recommendation list

[0495] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[0496] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[0497] The server transmits the generated recommendation list to the user's terminal.

[0498] Recommendation list notification

[0499] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[0500] The user selects a place of interest from the displayed recommendation list.

[0501] Automatic schedule generation

[0502] Schedule a visit

[0503] Through the application, the user inputs plans to visit specific locations and schedules the visit.

[0504] The terminal transmits the set visiting schedule to the server.

[0505] Suggestions for nearby spots

[0506] The server analyzes points of interest near the planned visit location and selects suggestions.

[0507] The server sends the proposal content to the user terminal and notifies the user via push notification.

[0508] The terminal displays the suggested spots and asks the user for confirmation.

[0509] The user checks the suggested spots and selects the place they want to go.

[0510] Automatic Schedule Generation

[0511] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[0512] The server stores the generated schedule in a database and transmits it to the user terminal.

[0513] Schedule notifications and additions

[0514] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[0515] The user adds the schedule to the calendar using the options provided.

[0516] As described above, by implementing the present invention, it is possible to provide a flexible recommendation list according to the emotional state of the user and to automatically generate an efficient schedule based on the planned visits.

[0517] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0518] Step 1:

[0519] Application installation and integration settings

[0520] Users install the application on their smartphones, and then when they launch it for the first time, they link it to their social media accounts.

[0521] The terminal acquires the SNS authentication information entered by the user, generates an authentication token, and sends it to the server.

[0522] The server establishes communication with the SNS API based on the received authentication token and prepares to collect data.

[0523] Input: User's social media credentials

[0524] Output: Communication session with SNS API

[0525] Specific behavior: Attempts to connect to the SNS API and validates the token

[0526] Step 2:

[0527] Social media data collection

[0528] The server uses an SNS API (e.g., an API provided by an SNS service) to collect user posts, photos, and check-in information.

[0529] Input: SNS authentication token

[0530] Output: Posts, photos, and check-ins

[0531] Specific behavior: Requests to API endpoints and analysis of responses

[0532] Step 3:

[0533] Collecting behavioral history

[0534] The user gives permission for the application to use location information.

[0535] The device collects and records location information obtained from the GPS sensor in real time.

[0536] The terminal transmits the collected location information data to the server.

[0537] The server analyzes the received location data and stores the frequency of visits and length of stay in a database.

[0538] Input: Location data

[0539] Output: Visit frequency and duration data

[0540] Specific operation: GPS data analysis and statistical processing

[0541] Step 4:

[0542] Collecting feedback data

[0543] Users enter text within the app to share their thoughts about the places they visit.

[0544] The terminal transmits the input impression data to the server.

[0545] The server receives the opinion data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), rates it positively or negatively, and stores the results in a database.

[0546] Input: Impression data

[0547] Output: Positive / negative rating

[0548] Specific behavior: Text data analysis and emotion evaluation

[0549] Step 5:

[0550] Emotional state analysis using emotion engine

[0551] The server analyzes the SNS data and sentiment data, and executes the algorithm of the emotion engine (e.g., API of the emotion analysis service) to identify the user's emotional state. The analysis results are stored in a database.

[0552] Input: SNS data, opinion data

[0553] Output: User's emotional state

[0554] Specific operation: Running a sentiment analysis algorithm and saving the results

[0555] Step 6:

[0556] Generating a recommendation list

[0557] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[0558] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[0559] The server transmits the generated recommendation list to the user's terminal.

[0560] Input: Social media data, behavioral history, impression data, prompt text

[0561] Output: Recommendation list

[0562] What it does: Combines data and runs AI models to generate a list

[0563] Step 7:

[0564] Recommendation list notification

[0565] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[0566] The user selects a place of interest from the displayed recommendation list.

[0567] Input: Recommendation list

[0568] Output: User's choice

[0569] Specific behavior: Displaying notifications and recording user choices

[0570] Step 8:

[0571] Schedule a visit

[0572] The user enters plans to visit specific locations in the application and schedules the visit.

[0573] The terminal transmits the set visiting schedule to the server.

[0574] Input: Visit Schedule

[0575] Output: Visit schedule data

[0576] Specific behavior: Save and send a visit appointment

[0577] Step 9:

[0578] Suggestions for nearby spots

[0579] The server analyzes points of interest near the planned visit location and selects suggestions.

[0580] The server sends the proposal content to the user terminal and notifies the user via push notification.

[0581] The terminal displays the suggested spots and asks the user for confirmation.

[0582] The user checks the suggested spots and selects the place they want to go.

[0583] Input: Visit schedule data, nearby spot information

[0584] Output: Proposal, user's choice

[0585] Specific behavior: Spot analysis and suggestion notification

[0586] Step 10:

[0587] Automatic Schedule Generation

[0588] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[0589] The server stores the generated schedule in a database and transmits it to the user terminal.

[0590] Input: Planned visit, selected nearby spots

[0591] Output: Auto-generated schedule

[0592] Specific behavior: Automatically generate and save schedules

[0593] Step 11:

[0594] Schedule notifications and additions

[0595] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[0596] The user adds the generated schedule to their calendar using the options provided.

[0597] Input: Auto-generated schedule

[0598] Output: Add to calendar

[0599] Specific operation: Schedule notification and calendar update options provided

[0600] (Application example 2)

[0601] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0602] Conventional recommendation systems make recommendations based on a user's behavioral history and personal data, but because they cannot take the user's emotional state into account, it is difficult to provide highly satisfying recommendations that address the user's current psychological needs. Furthermore, existing systems automatically generate schedules based solely on the user's plans, failing to reflect the user's emotional state, resulting in incomplete plans. There is a need to solve these issues and realize optimal recommendations and automatic schedule generation that reflect the user's psychological state.

[0603] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results and the user's emotional state, means for inputting the user's visit plans, means for acquiring information on spots near the planned visits, means for generating an automatic schedule based on the planned visits and the information on nearby spots, means for notifying the user terminal of the recommendation list and the automatic schedule, and means for adjusting the schedule based on the user's emotional state. This enables flexible and satisfying recommendations that take the user's emotional state into consideration and automatic generation of a schedule that suits the user's psychological state.

[0604] "Personal data" refers to information about individual users, including data from social networking services, behavioral history, and impression data.

[0605] A "generative AI model" refers to an algorithm or mechanism that uses artificial intelligence to analyze data and generate new information or recommendations.

[0606] The "emotional state" indicates the psychological state of the user, and includes an evaluation of emotions such as positive or negative.

[0607] A "recommendation list" refers to a list of recommended places, products, etc. for a user, which is generated based on collected and analyzed personal data and emotional state.

[0608] "User terminal" refers to a device used by a user, such as a computer, smartphone, tablet, or biometric input device.

[0609] "Visiting Plans" indicates plans such as places the user wants to visit or events the user wants to attend in the future.

[0610] "Neighborhood spot information" refers to information about spots located in the vicinity of a place that the user plans to visit.

[0611] "Automatic schedule" refers to a user's action plan that is automatically generated based on planned visits and information on nearby spots.

[0612] The "notification means" refers to a method or device for transmitting specific information to a user terminal and informing the user of that information.

[0613] "Adjustment measures" refer to methods and mechanisms for changing or modifying plans such as schedules and lists based on specific conditions.

[0614] This invention is a system that provides an optimal recommendation list and schedule by collecting personal data of a user and analyzing the data with a generative AI model. The system includes the following means.

[0615] Data collection and analysis

[0616] Social media data collection

[0617] Users install the application and connect their social media accounts, which grants them access to the data that is collected.

[0618] The device obtains the SNS authentication information and sends it to the server.

[0619] The server uses the SNS API to collect user posts, photos, and check-in information and store them in a database.

[0620] Collecting behavioral history

[0621] The user gives permission for the application to use location information.

[0622] The device collects GPS data in real time, recording the places you visit and the time you stay there.

[0623] The server receives the collected location data and analyzes the frequency of visits and the length of time spent at specific locations.

[0624] Collecting feedback data

[0625] Users enter their impressions of the places they visit within the app.

[0626] The terminal transmits the input impression data to the server.

[0627] The server receives the sentiment data, analyzes the content using natural language processing algorithms (e.g., NLTK or SpaCy), and assigns a positive or negative rating.

[0628] Analysis by emotion engine

[0629] The server analyzes the SNS data and sentiment data and runs an emotion engine to identify the user's emotional state.

[0630] The server stores the emotional states identified by the emotion engine in a database.

[0631] Recommendation generation and tuning

[0632] User data integration and analysis

[0633] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0634] The server integrates the profiles of multiple users, extracts common interests, and performs analysis.

[0635] Generating a recommendation list

[0636] The server uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of products and spots that are best suited for the user and their friends.

[0637] The server sends the generated recommendation list to the user's terminal and notifies the user.

[0638] Automatic schedule generation

[0639] Schedule a visit

[0640] The application allows users to input plans to visit specific locations and schedule visits.

[0641] The terminal transmits the set visit schedule to the server.

[0642] Suggestions for nearby spots

[0643] The server analyzes points of interest near the planned visit and selects suggestions.

[0644] The server transmits the proposal contents to the user terminal and notifies it.

[0645] The terminal displays the suggested spots and asks the user for confirmation.

[0646] The user checks the suggested spots and selects the place they want to go.

[0647] Automatic Schedule Generation

[0648] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[0649] The server transmits the generated schedule to the user terminal and notifies it.

[0650] The terminal notifies the user of the generated schedule so that the user can add it to a calendar, etc.

[0651] Specific examples

[0652] The user installs the application and connects their social media account. Next, they allow the use of their location information and enter their thoughts about shops they have visited in the past. If the emotion engine detects the user's current psychological state from the social media data, for example, if it determines that the user is feeling stressed, the server will prioritize recommendations of items that will help them relax.

[0653] Example prompts for generative AI models

[0654] An example of a prompt is shown below.

[0655] Recommend shopping items based on the user's emotional state.

[0656] User social media data: ["I'm busy and stressed today", "I want to try out a new gadget"]

[0657] Emotional state: Negative

[0658] User profile: {"interests": ["relaxation", "gadgets"]}

[0659] Recommendation list: ["Relaxation furniture", "Aroma candles", "Massage machine"]

[0660] By setting prompt sentences in this way, the generative AI model can provide a recommendation list that is optimal for the user's psychological state.

[0661] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0662] Step 1:

[0663] A user installs the application and links their SNS account. This linking allows the application to obtain authorization to access the user's SNS data. Once the user authorizes the linking, the device sends the SNS authentication information to the server. The input is the SNS authentication information, and the output is a request containing the authentication information.

[0664] Step 2:

[0665] The server uses SNS APIs to collect user posts, photos, and check-in information. The collected data is stored in a database. The input is user data obtained through the SNS API, and the output is personal data stored in the database.

[0666] Step 3:

[0667] The user gives permission for the application to use location information. The device collects GPS data in real time and records the places visited and the duration of stay. This data is periodically sent to the server. The input is real-time GPS data, and the output is visit history data sent to the server.

[0668] Step 4:

[0669] The user enters their thoughts about the places they visited in the app. The device sends the entered thoughts to the server. The server uses a natural language processing algorithm (e.g., NLTK or SpaCy) to analyze the thoughts and evaluate their emotions. The input is the thoughts entered by the user, and the output is the analyzed emotional state data.

[0670] Step 5:

[0671] The server analyzes the collected SNS data and sentiment data and runs an emotion engine to identify the user's emotional state. The emotion engine uses the analysis results to identify the user's emotional state and stores the data in a database. The input is SNS data and sentiment data, and the output is emotional state data.

[0672] Step 6:

[0673] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user. It integrates the profiles of multiple users, extracts common interests, and performs analysis. The input is the integrated user data, and the output is each user's profile data.

[0674] Step 7:

[0675] The server uses a generative AI model to generate a recommendation list based on the user's profile and emotional state. The program inputs a prompt into the generative AI model to create a recommendation list. The input is the user's profile and emotional state data, and the output is a recommendation list.

[0676] Step 8:

[0677] The server sends the generated recommendation list to the user's device and notifies them. The device displays the recommendation list to the user. The input is the recommendation list, and the output is a notification to the user.

[0678] Step 9:

[0679] The user enters plans to visit specific locations in the application and sets up a visit schedule. The device sends the set visit schedule to the server. This data is stored on the server as visit schedule data. The input is the visit schedule, and the output is the data sent to the server.

[0680] Step 10:

[0681] The server analyzes the places of interest near the planned visit location and selects suggestions. The suggestions are sent to the user's device and notified. The input is the planned visit data, and the output is the suggested nearby spot information.

[0682] Step 11:

[0683] The terminal displays the suggested spots and asks the user for confirmation. The user confirms the suggested spots and selects the place they want to go. This selection information is sent back to the server. The input is the suggested spot information, and the output is the user's selection data.

[0684] Step 12:

[0685] The server automatically generates a schedule based on the visit plan and the selected nearby spots. The generated schedule is sent to the user's terminal and notified. The input is the visit plan and nearby spot information, and the output is the automatically generated schedule.

[0686] Step 13:

[0687] The device notifies the user of the generated schedule and allows them to add it to their calendar, etc. The user can then check the schedule and adjust it as necessary. The input is the automatically generated schedule, and the output is the adjusted schedule information.

[0688] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0689] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0690] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0691] [Second embodiment]

[0692] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0693] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0694] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0695] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0696] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0697] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0698] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0699] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0700] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0701] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0702] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0703] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0704] The system of the present invention collects personal data from users, analyzes it using a generative AI model, and recommends optimal locations. Furthermore, it is possible to automatically generate and propose schedules for specific planned visits. Specific embodiments for implementing the present invention are described in detail below.

[0705] Data collection and analysis

[0706] Social media data collection

[0707] User: The user installs the application and connects their social media account, which grants access to the data that is collected.

[0708] Device: Obtains authentication information for the linked SNS and sends it to the server.

[0709] Server: Uses SNS APIs to collect user posts, photos, and check-in information and store it in a database for analysis.

[0710] Collecting behavioral history

[0711] User: Starts collecting location information by granting location permission to the application.

[0712] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[0713] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[0714] Collecting feedback data

[0715] Users: Enter their impressions and ratings of the places they visit within the app.

[0716] Terminal: Sends the inputted impression data to the server.

[0717] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[0718] Recommendation generation

[0719] User data integration and analysis

[0720] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0721] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[0722] Generating a recommendation list

[0723] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[0724] Server: Sends the generated recommendation list to the user's device and notifies them.

[0725] Recommendation notifications

[0726] On the device: The received recommendation list is notified to the user and displayed within the app.

[0727] User: Select a place of interest from the recommended list.

[0728] Automatic schedule generation

[0729] Schedule a visit

[0730] User: Enter plans to visit specific locations in the app and schedule the visit.

[0731] Terminal: Sends the scheduled visit information to the server.

[0732] Suggestions for nearby spots

[0733] Server: Analyzes and suggests points of interest near the location you plan to visit.

[0734] Server: Sends the proposal to the user's device and notifies them.

[0735] On the device: Display the suggested spot and ask the user for confirmation.

[0736] User: Review the suggested spots and select the one they want to go to.

[0737] Automatic Schedule Generation

[0738] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0739] Server: The completed schedule is sent to the user's terminal and notified.

[0740] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[0741] Specific examples

[0742] The user installs the application and connects to a social media account (e.g., Twitter). Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0743] In this way, by specifically implementing the present invention, it is possible to recommend efficient and appropriate locations to users and propose planned schedules.

[0744] The processing flow will be explained below.

[0745] Step 1:

[0746] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[0747] Step 2:

[0748] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[0749] Step 3:

[0750] Server: Uses the SNS API to collect data such as user posts, photos, and check-in information and store it in a database.

[0751] Step 4:

[0752] User: Allows the application to use location information.

[0753] Step 5:

[0754] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[0755] Step 6:

[0756] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[0757] Step 7:

[0758] Users: Write their thoughts about the places they visited within the app.

[0759] Step 8:

[0760] Terminal: Sends the inputted impression data to the server.

[0761] Step 9:

[0762] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[0763] Step 10:

[0764] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[0765] Step 11:

[0766] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[0767] Step 12:

[0768] Server: Based on the analysis results, a generative AI model is used to select the best restaurants and spots for the user and their friends.

[0769] Step 13:

[0770] Server: Sends the generated recommendation list to the user's device.

[0771] Step 14:

[0772] On the device: The received recommendation list is notified to the user and displayed within the app.

[0773] Step 15:

[0774] User: Select a place of interest from the recommended list.

[0775] Step 16:

[0776] User: Enters an appointment in the app, setting the locations and dates they want to visit.

[0777] Step 17:

[0778] Terminal: Sends the scheduled visit information to the server.

[0779] Step 18:

[0780] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[0781] Step 19:

[0782] Server: Sends information about nearby spots to the user's device.

[0783] Step 20:

[0784] On the device: The suggested spots are notified to the user and displayed within the app.

[0785] Step 21:

[0786] User: Review the suggested spots and select the places that interest them.

[0787] Step 22:

[0788] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0789] Step 23:

[0790] Server: Sends the generated schedule to the user's terminal.

[0791] Step 24:

[0792] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[0793] Through this series of steps, users can efficiently receive recommendations for the best places and generate a detailed schedule based on their planned visits.

[0794] Example 1

[0795] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0796] Conventional systems have difficulty generating recommendations based on users' interests. They also lack the functionality to automatically generate and propose optimal schedules for planned visits, requiring users to make their own plans. Furthermore, they were unable to efficiently collect and analyze various distributed data sources (social media data, behavioral history, and opinion data) and provide recommendations based on that data.

[0797] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0798] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the generation of a highly accurate recommendation list based on the user's interests and concerns. The server also includes a means for collecting the user's location information and recording their behavioral history, a means for collecting and classifying impression data, and a means for generating an automatic schedule based on the user's planned visits and information on nearby spots. This allows the user to automatically receive an optimal visit plan based on their behavioral history and impression data, enabling them to visit various places efficiently and in a planned manner.

[0799] "Personal data" is a general term for personal information, behavioral data, impression data, etc. related to a user.

[0800] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate and analyze data.

[0801] "Analysis" is the process of using collected data to find patterns or extract specific information.

[0802] A "recommendation list" is a list of places and services suggested based on a user's interests.

[0803] "Social networking services," abbreviated as SNS, are services that allow people to share information and interact with each other via the Internet.

[0804] "Behavioral history" is a record of a user's location information and visited destinations.

[0805] "Opinion data" is data that includes evaluations and opinions of places visited by users and services experienced by users.

[0806] "Planned visits" is information about places the user wants to visit in the future and events the user is planning.

[0807] "Neighborhood spot information" is information about places and facilities of interest in the vicinity of a destination that the user has set as a visiting schedule.

[0808] An "automatic schedule" is a schedule that automatically generates the optimal order of visits and time allocation based on the input visit plans and information on nearby spots.

[0809] "User terminal" is a general term for electronic devices that can be directly operated by a user, such as smartphones and tablets.

[0810] "Notification" is the act of displaying a message or alert to convey information to the user.

[0811] The system of the present invention collects personal data from users, analyzes it with a generative AI model, and recommends optimal locations. It also makes it possible to automatically generate and propose schedules for specific visits.

[0812] Data collection and analysis

[0813] Social media data collection

[0814] User: A user installs an application and connects their social network account (e.g., Twitter), which allows the application to access the user's social network data.

[0815] Device: The device obtains authentication information for the linked SNS and sends that information to the server.

[0816] Server: The server uses social media APIs (e.g., Twitter API) to collect user posts, photos, and check-in information, and stores this data in a database for analysis.

[0817] Collecting behavioral history

[0818] User: The user grants the application permission to use and collect location information.

[0819] Device: The device continuously collects GPS data and records the locations the user has visited and the time spent there.

[0820] Server: The server analyzes the location data to identify places the user frequently visits and stores that cater to specific genres of interest.

[0821] Collecting feedback data

[0822] User: The user enters their impressions and ratings of the places they visit into the application.

[0823] Terminal: The terminal sends the impression data entered by the user to the server.

[0824] Server: The server analyzes the sentiment data using a natural language processing algorithm (e.g., Python's NLTK library) and classifies the content as positive or negative.

[0825] Generating a recommendation list

[0826] User data integration and analysis

[0827] Server: The server integrates social media data, behavioral history, and opinion data to generate a profile that reflects the user's interests and preferences. It also extracts common interests among multiple users.

[0828] Recommendation generation

[0829] Server: The server uses a generative AI model (e.g., OpenAI's GPT-4 model) to generate a recommendation list based on the profile.

[0830] Server: Sends the generated recommendation list to the user's device and notifies them.

[0831] Recommendation notifications

[0832] Device: The device notifies the user of the received recommendation list and displays the list within the app.

[0833] User: The user selects the place they want to visit from the displayed list.

[0834] Automatic schedule generation

[0835] Schedule a visit

[0836] User: The user enters their plans to visit a specific location in the application and schedules the visit.

[0837] Terminal: The terminal sends the set visit schedule to the server.

[0838] Suggestions for nearby spots

[0839] Server: The server analyzes and suggests points of interest near the location you plan to visit.

[0840] Server: Sends the proposal to the user's device and notifies them.

[0841] Terminal: The terminal displays the suggested spots and asks the user for confirmation.

[0842] User: The user reviews the suggested spots and selects the place they want to go.

[0843] Automatic Schedule Generation

[0844] Server: The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[0845] Server: Sends the completed schedule to the user's terminal and notifies them.

[0846] Device: The device will notify the user of the generated schedule and allow them to add it to their calendar.

[0847] Specific examples

[0848] The user installs the application and connects their Twitter account. Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0849] Example of a prompt for the proposed AI model

[0850] "Generate a list of recommendations that are optimal for each user based on their social media data, location information, and impressions of their visit. For example, if a user plans to go strawberry picking this weekend, suggest nearby cafes and hot springs."

[0851] In this way, the present invention can recommend efficient and appropriate locations to users and propose well-planned schedules.

[0852] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0853] Step 1: User connects social media account

[0854] Specific behavior:

[0855] The user installs the application and connects their social media account (e.g., Twitter).

[0856] Input: Social media account credentials (e.g., OAuth token).

[0857] The device obtains authentication information from the linked SNS and uses it to authorize access to the necessary data.

[0858] Output: The social media credentials are sent to the server.

[0859] Step 2: Collect social media data

[0860] Specific behavior:

[0861] The server uses the SNS API to collect user posts, photos, check-in information, etc.

[0862] Input: The SNS credentials received by the server.

[0863] The server stores this data in a database for analysis.

[0864] Output: Saved social media data.

[0865] Step 3: Location Permissions and Collection

[0866] Specific behavior:

[0867] The user allows the application to use location information.

[0868] Input: User permission to use location information.

[0869] The device continuously collects GPS data and records the user's past visits and time spent there.

[0870] Output: Collected GPS data is sent to a server.

[0871] Step 4: Analyzing behavioral history

[0872] Specific behavior:

[0873] The server analyzes the received location data to identify frequently visited locations and stores of interest.

[0874] Input: GPS data received by the server.

[0875] The server applies data analysis algorithms to extract visitation patterns.

[0876] Output: Analysis results (frequently visited places and trends).

[0877] Step 5: Enter and submit your feedback

[0878] Specific behavior:

[0879] Users enter their impressions and ratings of the places they visit into the application.

[0880] Input: User-entered feedback and ratings.

[0881] The terminal transmits the input impression data to the server.

[0882] Output: The feedback data sent to the server.

[0883] Step 6: Analyze the sentiment data

[0884] Specific behavior:

[0885] The server analyzes the feedback data using a natural language processing algorithm and classifies the content as positive or negative.

[0886] Input: The sentiment data sent to the server.

[0887] The server uses Python's NLTK library to classify the data.

[0888] Output: Classified sentiment data (positive / negative).

[0889] Step 7: Create a user profile

[0890] Specific behavior:

[0891] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0892] Input: Stored social media data, analyzed behavioral history, and classified opinion data.

[0893] The server aggregates this data to create a profile that reflects the user's interests and concerns.

[0894] Output: User profile.

[0895] Step 8: Generate a recommendation list

[0896] Specific behavior:

[0897] The server uses a generative AI model (e.g., GPT-4) to generate a recommendation list from the user profile.

[0898] Input: User profile.

[0899] The server creates a prompt for the AI ​​model and inputs it into the model.

[0900] Example prompt: "Generate a list of recommendations that are optimal for the user based on their social media data, location information, and impressions of their visit. For example, the user is planning to go strawberry picking this weekend. Suggest nearby cafes, hot springs, etc."

[0901] Output: The generated recommendation list.

[0902] Step 9: Notification of recommendation list

[0903] Specific behavior:

[0904] The server sends the generated recommendation list to the user's terminal and notifies the user.

[0905] Input: The generated recommendation list.

[0906] The terminal receives the recommendation list and notifies the user.

[0907] Output: Notification of recommendation list.

[0908] Step 10: Schedule a visit

[0909] Specific behavior:

[0910] The application allows users to input plans to visit specific locations and schedule visits.

[0911] Enter: Visit planned.

[0912] The terminal transmits the set visit schedule to the server.

[0913] Output: The visit schedule sent to the server.

[0914] Step 11: Suggest nearby spots

[0915] Specific behavior:

[0916] The server analyzes and suggests points of interest near the place you plan to visit.

[0917] Input: Visit schedule information.

[0918] The server uses an AI model to analyze points of interest and generate suggestions.

[0919] Output: Suggested points of interest are sent to the device.

[0920] Step 12: Generate an automatic schedule

[0921] Specific behavior:

[0922] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[0923] Input: Planned visits and nearby spot information.

[0924] The server uses a schedule generation algorithm to create an optimal schedule.

[0925] Output: The generated automatic schedule.

[0926] Step 13: Auto-Schedule Notifications

[0927] Specific behavior:

[0928] The server transmits the completed schedule to the user terminal and notifies it.

[0929] Input: The generated automatic schedule.

[0930] The terminal notifies the user of the received schedule so that the user can add it to their calendar.

[0931] Output: Auto-schedule notifications.

[0932] Through the above steps, the system of the present invention can recommend places based on the user's interests and automatically generate an efficient visiting schedule.

[0933] (Application example 1)

[0934] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0935] Conventional food delivery services have been unable to fully utilize users' personal data, making it difficult to provide optimal services tailored to individual preferences and schedules. Furthermore, they lacked functionality to improve the user experience, such as suggesting optimal delivery times based on planned visits and automatically generating schedules. This created a need for a new system that would significantly improve user convenience.

[0936] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0937] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the provision of a delivery service optimized for the user's preferences and schedule. The server also includes a means for proposing the optimal service delivery timing based on the user's schedule, a means for generating a schedule based on the schedule, and a means for notifying the user terminal of the automatic schedule. This enables the delivery service optimized for the user's schedule and the generation of an automatic schedule, significantly improving the user experience.

[0938] "Personal data" refers to a user's personal information, including data from social networking services, behavioral history, and impression data.

[0939] A "generative AI model" is an artificial intelligence model that analyzes collected personal data and generates the optimal recommendation list for the user.

[0940] A "recommendation list" is a list of optimal services and places suggested to a user based on analyzed personal data.

[0941] "User terminal" is a general term for electronic devices used by users, including smartphones, tablets, etc.

[0942] "Location information" refers to data about a user's current location and past visited locations obtained using GPS or other technologies.

[0943] An "automatic schedule" is a schedule that the system automatically generates based on the user's schedule.

[0944] "Service provision timing" refers to the time for providing the service at the optimal timing according to the user's schedule and activities.

[0945] The system of the present invention is a food delivery assistant that collects personal data from users, analyzes it using a generative AI model, and generates an optimal recommendation list and schedule. This system uses a smartphone as its primary device and has multiple means to improve the user experience.

[0946] Data collection and analysis

[0947] Social media data collection

[0948] User: The user installs the application and connects their social networking service (SNS) account, thereby granting permission for data collection.

[0949] Device: Obtains authentication information for the linked SNS and sends it to the server.

[0950] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database for analysis.

[0951] Collecting behavioral history

[0952] User: Starts collecting location information by granting location permission to the application.

[0953] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[0954] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[0955] Collecting feedback data

[0956] Users: Enter their impressions and ratings within the app about places they visit and food they order.

[0957] Terminal: Sends the inputted impression data to the server.

[0958] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[0959] Recommendation generation

[0960] User data integration and analysis

[0961] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[0962] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[0963] Generating a recommendation list

[0964] Server: Uses a generative AI model to analyze each user's tastes and preferences and generate a list of delivery restaurants and menus that are best suited for the user and their friends.

[0965] Server: Sends the generated recommendation list to the user's device and notifies them.

[0966] Automatic schedule generation

[0967] Schedule a visit

[0968] User: Enter plans to visit specific locations in the app and schedule the visit.

[0969] Terminal: Sends the scheduled visit information to the server.

[0970] Suggestions for nearby spots

[0971] Server: Analyzes and suggests points of interest near the location you plan to visit.

[0972] Server: Sends the proposal to the user's device and notifies them.

[0973] On the device: Display the suggested spot and ask the user for confirmation.

[0974] User: Review the suggested spots and select the one they want to go to.

[0975] Automatic Schedule Generation

[0976] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[0977] Server: The completed schedule is sent to the user's terminal and notified.

[0978] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[0979] Hardware and software used

[0980] The system includes the following hardware and software:

[0981] Smartphone (used as user device)

[0982] Server (data analysis and storage)

[0983] GPS module (acquisition of location information)

[0984] SNS API (acquiring data from social networking services)

[0985] Natural language processing algorithms (analysis of sentiment data, Transformers, etc.)

[0986] Generative AI model (recommendation list generation)

[0987] Calendar app (schedule notification and management)

[0988] Examples of specific examples and prompts

[0989] Specific examples

[0990] The user installs the application and connects their social media account. Next, they allow the use of location information and enter their thoughts on dishes they have previously ordered. The server collects and analyzes this data. If the user selects "I'm going on a picnic with friends this weekend," the server will suggest nearby delivery restaurants and new menus and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[0991] Prompt Sentence Examples

[0992] user_id = "example_user"

[0993] visit_plan = "2023-12-31 18:00:00"

[0994] main(user_id, visit_plan)

[0995] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0996] Step 1:

[0997] Collection of Personal Data

[0998] Users install the application and connect their SNS account. This allows the server to collect user posts, photos, and check-in information via the SNS API. Specifically, the server obtains user data from the SNS API and stores it in a database.

[0999] Step 2:

[1000] Location information collection

[1001] Users allow applications to use their location information. The device continuously collects GPS data and sends it to a server, which records the places visited and the time spent there, and stores it in a database.

[1002] Step 3:

[1003] Inputting feedback data

[1004] Users input their impressions and ratings of the places they visited and the food they ordered into the application. The device sends the input impression data to the server and stores it in a database.

[1005] Step 4:

[1006] Data integration and analysis

[1007] The server integrates the collected social media data, location information, and opinion data to generate a user profile. Using a generative AI model, this data is analyzed to identify the user's preferences. The integrated data is used as input, and the generative AI model analyzes it, outputting user preference data.

[1008] Step 5:

[1009] Generating a recommendation list

[1010] Based on the analysis results, the server generates a recommendation list of delivery restaurants and menus that best suit the user's preferences. Using the preference data as input, the generative AI model generates a recommendation list, which is then output.

[1011] Step 6:

[1012] Recommendation list notification

[1013] The server transmits the generated recommendation list to the user's terminal, and the terminal displays the received recommendation list to the user within the application.

[1014] Step 7:

[1015] Schedule a visit

[1016] The user enters a visit schedule for a specific location and time in the application, and the device sends the visit schedule to the server and stores it in a database.

[1017] Step 8:

[1018] Obtaining and suggesting information about nearby spots

[1019] The server analyzes and suggests interesting spots near the location the user plans to visit. The analysis results are sent to the user's device, which displays the suggestions to the user. The user then checks the suggested spots and selects the ones they want to visit.

[1020] Step 9:

[1021] Automatic Schedule Generation

[1022] The server automatically generates a schedule based on the visit schedule and the nearby spot information selected by the user. The optimal delivery time and visit schedule are generated and sent to the user's terminal.

[1023] Step 10:

[1024] Schedule notification and management

[1025] The device notifies the user of the generated schedule and allows the user to add it to applications such as a calendar, allowing the user to use the delivery service according to an optimal schedule.

[1026] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1027] The present invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. The present invention also incorporates an emotion engine that recognizes the user's emotions, allowing the system to flexibly adjust the recommendation list based on the user's emotional state. Specific embodiments for implementing the present invention are described in detail below.

[1028] Data collection and analysis

[1029] Social media data collection

[1030] User: The user installs the application and connects their social media account, which grants them access to the data that is collected.

[1031] Device: Obtains authentication information for the linked SNS and sends it to the server.

[1032] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database.

[1033] Collecting behavioral history

[1034] User: Grants location permission to the application.

[1035] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[1036] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[1037] Collecting feedback data

[1038] Users: Write their thoughts about the places they visited within the app.

[1039] Terminal: Sends the inputted impression data to the server.

[1040] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[1041] Analysis by emotion engine

[1042] Server: Analyzes social media data and sentiment data and runs an emotion engine to identify the user's emotional state.

[1043] Server: Stores the emotional states identified by the emotion engine in a database.

[1044] Recommendation generation and tuning

[1045] User data integration and analysis

[1046] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1047] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1048] Generating a recommendation list

[1049] Server: Uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of restaurants and spots that are best suited for the user and their friends.

[1050] Server: Sends the generated recommendation list to the user's device and notifies them.

[1051] Recommendation notifications

[1052] On the device: The received recommendation list is notified to the user and displayed within the app.

[1053] User: Select a place of interest from the recommended list.

[1054] Automatic schedule generation

[1055] Schedule a visit

[1056] User: Enter plans to visit specific locations in the app and schedule the visit.

[1057] Terminal: Sends the scheduled visit information to the server.

[1058] Suggestions for nearby spots

[1059] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[1060] Server: Sends the proposal to the user's device and notifies them.

[1061] On the device: Display the suggested spot and ask the user for confirmation.

[1062] User: Review the suggested spots and select the one they want to go to.

[1063] Automatic Schedule Generation

[1064] Server: Automatically generate a schedule based on planned visits and selected nearby spots.

[1065] Server: Sends the completed schedule to the user's terminal and notifies them.

[1066] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[1067] Specific examples

[1068] The user installs the application and connects their social media account (e.g., Twitter). Next, they allow the use of location information and enter their thoughts about cafes they have visited in the past. If the emotion engine detects from social media data that the user is feeling stressed, the server will prioritize recommendations of relaxing cafes and quiet restaurants. If the user selects "I'm going strawberry picking on the weekend," the server will suggest nearby spots (e.g., relaxing cafes and hot springs) and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[1069] In this way, by specifically implementing the present invention, it is possible to provide flexible recommendations according to the user's emotional state and propose planned schedules.

[1070] The processing flow will be explained below.

[1071] Step 1:

[1072] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[1073] Step 2:

[1074] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[1075] Step 3:

[1076] Server: Uses SNS APIs to collect data such as user posts, photos, and check-in information and store it in a database.

[1077] Step 4:

[1078] User: Allows the application to use location information.

[1079] Step 5:

[1080] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[1081] Step 6:

[1082] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[1083] Step 7:

[1084] Users: Write their thoughts about the places they visited within the app.

[1085] Step 8:

[1086] Terminal: Sends the inputted impression data to the server.

[1087] Step 9:

[1088] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[1089] Step 10:

[1090] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[1091] Step 11:

[1092] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1093] Step 12:

[1094] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[1095] Step 13:

[1096] Server: Sends the generated recommendation list to the user's device.

[1097] Step 14:

[1098] On the device: The received recommendation list is notified to the user and displayed within the app.

[1099] Analysis and adjustment by emotion engine

[1100] Step 15:

[1101] Server: Uses an emotion engine to analyze social media data and sentiment data to identify the user's emotional state.

[1102] Step 16:

[1103] Server: Stores the emotional states identified by the emotion engine in a database.

[1104] Step 17:

[1105] Server: Adjust and regenerate the recommendation list depending on the emotional state.

[1106] Step 18:

[1107] Server: Sends the tailored recommendation list to the user's device.

[1108] Automatic schedule generation

[1109] Step 19:

[1110] User: Enter plans to visit specific locations in the app and schedule the visit.

[1111] Step 20:

[1112] Terminal: Sends the scheduled visit information to the server.

[1113] Step 21:

[1114] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[1115] Step 22:

[1116] Server: Sends the proposal to the user's device and notifies them.

[1117] Step 23:

[1118] On the device: Display the suggested spot and ask the user for confirmation.

[1119] Step 24:

[1120] User: Review the suggested spots and select the one they want to go to.

[1121] Step 25:

[1122] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[1123] Step 26:

[1124] Server: Sends the generated schedule to the user's terminal.

[1125] Step 27:

[1126] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[1127] Through this series of steps, users can efficiently receive recommendations for the best places to visit and generate a detailed schedule based on their planned visits. By combining this with an emotion engine, it is also possible to flexibly adjust the schedule according to the user's emotional state.

[1128] Example 2

[1129] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1130] In modern society, recommendation systems that meet the needs of individual users are extremely important, but conventional systems have had difficulty making recommendations that take into account the emotional state of each user. In particular, although recommending places that reduce users' stress and emotional anxiety would be effective, there were a lack of methods to achieve this. Furthermore, generating and proposing flexible and efficient schedules based on planned visits was also difficult.

[1131] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1132] In this invention, the server includes means for collecting personal data of users, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results, means for notifying the user terminal of the recommendation list, means for using an emotion engine to analyze the user's emotional state, and means for flexibly adjusting the recommendation list based on the analysis results. This makes it possible to provide a flexible recommendation list tailored to the user's emotions and automatically generate an efficient schedule based on the user's planned visits.

[1133] "Personal data" refers to information specific to an individual user, such as the user's behavior, interests, and impressions, and includes data from social networking services, behavioral history, and impression data.

[1134] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze user data and generate appropriate information or suggestions based on the results. Specific examples include natural language generation models.

[1135] An "emotion engine" refers to an algorithm that analyzes a user's emotional state from collected data, and this is achieved using emotion analysis tools and APIs.

[1136] A "recommendation list" refers to a list of places, products, etc. recommended to a user, generated based on analyzed data.

[1137] A "visit plan" refers to a plan to visit a particular location in the future that a user inputs into the application.

[1138] "Nearby spot information" refers to information about interesting places and facilities located around the place you plan to visit.

[1139] "Automatic schedule" refers to a schedule of activities that is automatically generated by an algorithm based on the user's planned visits and information about nearby spots.

[1140] "User terminal" refers to a digital device that is directly used by a user, such as a smartphone or tablet.

[1141] "Notification" refers to the act of conveying information from the system to the user, including push notifications and in-app displays.

[1142] "Analysis results" refers to the analytical conclusions and insights obtained after processing collected data using generative AI models and emotion engines.

[1143] "Flexible adjustment" refers to dynamically changing the recommendation list and suggestions depending on the user's emotions and situation.

[1144] This invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. It also incorporates an emotion engine that recognizes the user's emotional state and has the ability to flexibly adjust the recommendation list based on the user's emotional state.

[1145] Hardware and software used in data collection

[1146] Social media data collection

[1147] A user installs the application and connects their social media account, which allows access to the data that is collected.

[1148] The terminal acquires the user's SNS authentication information and sends it to the server.

[1149] The server uses SNS APIs (e.g., Twitter API) to collect user posts, photos, and check-in information. This data is stored in a database.

[1150] Collecting behavioral history

[1151] The user grants the application permission to use location information.

[1152] The device collects GPS data in real time and records the places you visit and the time you stay there.

[1153] The server analyzes the collected location data and stores the frequency of visits and length of stay in a database.

[1154] Collecting feedback data

[1155] Users enter their thoughts about the places they visited within the app.

[1156] The terminal transmits the input impression data to the server.

[1157] The server receives the data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), and evaluates it as positive or negative. The evaluation results are also stored in a database.

[1158] Analysis by emotion engine

[1159] The server analyzes the social media data and sentiment data, and runs an emotion engine (e.g., IBM Watson) algorithm to identify the user's emotional state. The analysis results are stored in a database.

[1160] Recommendation generation and notification

[1161] Generating a recommendation list

[1162] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[1163] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[1164] The server transmits the generated recommendation list to the user's terminal.

[1165] Recommendation list notification

[1166] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[1167] The user selects a place of interest from the displayed recommendation list.

[1168] Automatic schedule generation

[1169] Schedule a visit

[1170] Through the application, the user inputs plans to visit specific locations and schedules the visit.

[1171] The terminal transmits the set visiting schedule to the server.

[1172] Suggestions for nearby spots

[1173] The server analyzes points of interest near the planned visit location and selects suggestions.

[1174] The server sends the proposal content to the user terminal and notifies the user via push notification.

[1175] The terminal displays the suggested spots and asks the user for confirmation.

[1176] The user checks the suggested spots and selects the place they want to go.

[1177] Automatic Schedule Generation

[1178] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[1179] The server stores the generated schedule in a database and transmits it to the user terminal.

[1180] Schedule notifications and additions

[1181] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[1182] The user adds the schedule to the calendar using the options provided.

[1183] As described above, by implementing the present invention, it is possible to provide a flexible recommendation list according to the emotional state of the user and to automatically generate an efficient schedule based on the planned visits.

[1184] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1185] Step 1:

[1186] Application installation and integration settings

[1187] Users install the application on their smartphones, and then when they launch it for the first time, they link it to their social media accounts.

[1188] The terminal acquires the SNS authentication information entered by the user, generates an authentication token, and sends it to the server.

[1189] The server establishes communication with the SNS API based on the received authentication token and prepares to collect data.

[1190] Input: User's social media credentials

[1191] Output: Communication session with SNS API

[1192] Specific behavior: Attempts to connect to the SNS API and validates the token

[1193] Step 2:

[1194] Social media data collection

[1195] The server uses an SNS API (e.g., an API provided by an SNS service) to collect user posts, photos, and check-in information.

[1196] Input: SNS authentication token

[1197] Output: Posts, photos, and check-ins

[1198] Specific behavior: Requests to API endpoints and analysis of responses

[1199] Step 3:

[1200] Collecting behavioral history

[1201] The user gives permission for the application to use location information.

[1202] The device collects and records location information obtained from the GPS sensor in real time.

[1203] The terminal transmits the collected location information data to the server.

[1204] The server analyzes the received location data and stores the frequency of visits and length of stay in a database.

[1205] Input: Location data

[1206] Output: Visit frequency and duration data

[1207] Specific operation: GPS data analysis and statistical processing

[1208] Step 4:

[1209] Collecting feedback data

[1210] Users enter text within the app to share their thoughts about the places they visit.

[1211] The terminal transmits the input impression data to the server.

[1212] The server receives the opinion data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), rates it positively or negatively, and stores the results in a database.

[1213] Input: Impression data

[1214] Output: Positive / negative rating

[1215] Specific behavior: Text data analysis and emotion evaluation

[1216] Step 5:

[1217] Emotional state analysis using emotion engine

[1218] The server analyzes the SNS data and sentiment data, and executes the algorithm of the emotion engine (e.g., API of the emotion analysis service) to identify the user's emotional state. The analysis results are stored in a database.

[1219] Input: SNS data, opinion data

[1220] Output: User's emotional state

[1221] Specific operation: Running a sentiment analysis algorithm and saving the results

[1222] Step 6:

[1223] Generating a recommendation list

[1224] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[1225] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[1226] The server transmits the generated recommendation list to the user's terminal.

[1227] Input: Social media data, behavioral history, impression data, prompt text

[1228] Output: Recommendation list

[1229] What it does: Combines data and runs AI models to generate a list

[1230] Step 7:

[1231] Recommendation list notification

[1232] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[1233] The user selects a place of interest from the displayed recommendation list.

[1234] Input: Recommendation list

[1235] Output: User's choice

[1236] Specific behavior: Displaying notifications and recording user choices

[1237] Step 8:

[1238] Schedule a visit

[1239] The user enters plans to visit specific locations in the application and schedules the visit.

[1240] The terminal transmits the set visiting schedule to the server.

[1241] Input: Visit Schedule

[1242] Output: Visit schedule data

[1243] Specific behavior: Save and send a visit appointment

[1244] Step 9:

[1245] Suggestions for nearby spots

[1246] The server analyzes points of interest near the planned visit location and selects suggestions.

[1247] The server sends the proposal content to the user terminal and notifies the user via push notification.

[1248] The terminal displays the suggested spots and asks the user for confirmation.

[1249] The user checks the suggested spots and selects the place they want to go.

[1250] Input: Visit schedule data, nearby spot information

[1251] Output: Proposal, user's choice

[1252] Specific behavior: Spot analysis and suggestion notification

[1253] Step 10:

[1254] Automatic Schedule Generation

[1255] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[1256] The server stores the generated schedule in a database and transmits it to the user terminal.

[1257] Input: Planned visit, selected nearby spots

[1258] Output: Auto-generated schedule

[1259] Specific behavior: Automatically generate and save schedules

[1260] Step 11:

[1261] Schedule notifications and additions

[1262] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[1263] The user adds the generated schedule to their calendar using the options provided.

[1264] Input: Auto-generated schedule

[1265] Output: Add to calendar

[1266] Specific operation: Schedule notification and calendar update options provided

[1267] (Application example 2)

[1268] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1269] Conventional recommendation systems make recommendations based on a user's behavioral history and personal data, but because they cannot take the user's emotional state into account, it is difficult to provide highly satisfying recommendations that address the user's current psychological needs. Furthermore, existing systems automatically generate schedules based solely on the user's plans, failing to reflect the user's emotional state, resulting in incomplete plans. There is a need to solve these issues and realize optimal recommendations and automatic schedule generation that reflect the user's psychological state.

[1270] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results and the user's emotional state, means for inputting the user's visit plans, means for acquiring information on spots near the planned visits, means for generating an automatic schedule based on the planned visits and the information on nearby spots, means for notifying the user terminal of the recommendation list and the automatic schedule, and means for adjusting the schedule based on the user's emotional state. This enables flexible and satisfying recommendations that take the user's emotional state into consideration and automatic generation of a schedule that suits the user's psychological state.

[1271] "Personal data" refers to information about individual users, including data from social networking services, behavioral history, and impression data.

[1272] A "generative AI model" refers to an algorithm or mechanism that uses artificial intelligence to analyze data and generate new information or recommendations.

[1273] The "emotional state" indicates the psychological state of the user, and includes an evaluation of emotions such as positive or negative.

[1274] A "recommendation list" refers to a list of recommended places, products, etc. for a user, which is generated based on collected and analyzed personal data and emotional state.

[1275] "User terminal" refers to a device used by a user, such as a computer, smartphone, tablet, or biometric input device.

[1276] "Visiting Plans" indicates plans such as places the user wants to visit or events the user wants to attend in the future.

[1277] "Neighborhood spot information" refers to information about spots located in the vicinity of a place that the user plans to visit.

[1278] "Automatic schedule" refers to a user's action plan that is automatically generated based on planned visits and information on nearby spots.

[1279] The "notification means" refers to a method or device for transmitting specific information to a user terminal and informing the user of that information.

[1280] "Adjustment measures" refer to methods and mechanisms for changing or modifying plans such as schedules and lists based on specific conditions.

[1281] This invention is a system that provides an optimal recommendation list and schedule by collecting personal data of a user and analyzing the data with a generative AI model. The system includes the following means.

[1282] Data collection and analysis

[1283] Social media data collection

[1284] Users install the application and connect their social media accounts, which grants them access to the data that is collected.

[1285] The device obtains the SNS authentication information and sends it to the server.

[1286] The server uses the SNS API to collect user posts, photos, and check-in information and store them in a database.

[1287] Collecting behavioral history

[1288] The user gives permission for the application to use location information.

[1289] The device collects GPS data in real time, recording the places you visit and the time you stay there.

[1290] The server receives the collected location data and analyzes the frequency of visits and the length of time spent at specific locations.

[1291] Collecting feedback data

[1292] Users enter their impressions of the places they visit within the app.

[1293] The terminal transmits the input impression data to the server.

[1294] The server receives the sentiment data, analyzes the content using natural language processing algorithms (e.g., NLTK or SpaCy), and assigns a positive or negative rating.

[1295] Analysis by emotion engine

[1296] The server analyzes the SNS data and sentiment data and runs an emotion engine to identify the user's emotional state.

[1297] The server stores the emotional states identified by the emotion engine in a database.

[1298] Recommendation generation and tuning

[1299] User data integration and analysis

[1300] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1301] The server integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1302] Generating a recommendation list

[1303] The server uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of products and spots that are best suited for the user and their friends.

[1304] The server sends the generated recommendation list to the user's terminal and notifies the user.

[1305] Automatic schedule generation

[1306] Schedule a visit

[1307] The application allows users to input plans to visit specific locations and schedule visits.

[1308] The terminal transmits the set visit schedule to the server.

[1309] Suggestions for nearby spots

[1310] The server analyzes points of interest near the planned visit and selects suggestions.

[1311] The server transmits the proposal contents to the user terminal and notifies it.

[1312] The terminal displays the suggested spots and asks the user for confirmation.

[1313] The user checks the suggested spots and selects the place they want to go.

[1314] Automatic Schedule Generation

[1315] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[1316] The server transmits the generated schedule to the user terminal and notifies it.

[1317] The terminal notifies the user of the generated schedule so that the user can add it to a calendar, etc.

[1318] Specific examples

[1319] The user installs the application and connects their social media account. Next, they allow the use of their location information and enter their thoughts about shops they have visited in the past. If the emotion engine detects the user's current psychological state from the social media data, for example, if it determines that the user is feeling stressed, the server will prioritize recommendations of items that will help them relax.

[1320] Example prompts for generative AI models

[1321] An example of a prompt is shown below.

[1322] Recommend shopping items based on the user's emotional state.

[1323] User social media data: ["I'm busy and stressed today", "I want to try out a new gadget"]

[1324] Emotional state: Negative

[1325] User profile: {"interests": ["relaxation", "gadgets"]}

[1326] Recommendation list: ["Relaxation furniture", "Aroma candles", "Massage machine"]

[1327] By setting prompt sentences in this way, the generative AI model can provide a recommendation list that is optimal for the user's psychological state.

[1328] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1329] Step 1:

[1330] A user installs the application and links their SNS account. This linking allows the application to obtain authorization to access the user's SNS data. Once the user authorizes the linking, the device sends the SNS authentication information to the server. The input is the SNS authentication information, and the output is a request containing the authentication information.

[1331] Step 2:

[1332] The server uses SNS APIs to collect user posts, photos, and check-in information. The collected data is stored in a database. The input is user data obtained through the SNS API, and the output is personal data stored in the database.

[1333] Step 3:

[1334] The user gives permission for the application to use location information. The device collects GPS data in real time and records the places visited and the duration of stay. This data is periodically sent to the server. The input is real-time GPS data, and the output is visit history data sent to the server.

[1335] Step 4:

[1336] The user enters their thoughts about the places they visited in the app. The device sends the entered thoughts to the server. The server uses a natural language processing algorithm (e.g., NLTK or SpaCy) to analyze the thoughts and evaluate their emotions. The input is the thoughts entered by the user, and the output is the analyzed emotional state data.

[1337] Step 5:

[1338] The server analyzes the collected SNS data and sentiment data and runs an emotion engine to identify the user's emotional state. The emotion engine uses the analysis results to identify the user's emotional state and stores the data in a database. The input is SNS data and sentiment data, and the output is emotional state data.

[1339] Step 6:

[1340] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user. It integrates the profiles of multiple users, extracts common interests, and performs analysis. The input is the integrated user data, and the output is each user's profile data.

[1341] Step 7:

[1342] The server uses a generative AI model to generate a recommendation list based on the user's profile and emotional state. The program inputs a prompt into the generative AI model to create a recommendation list. The input is the user's profile and emotional state data, and the output is a recommendation list.

[1343] Step 8:

[1344] The server sends the generated recommendation list to the user's device and notifies them. The device displays the recommendation list to the user. The input is the recommendation list, and the output is a notification to the user.

[1345] Step 9:

[1346] The user enters plans to visit specific locations in the application and sets up a visit schedule. The device sends the set visit schedule to the server. This data is stored on the server as visit schedule data. The input is the visit schedule, and the output is the data sent to the server.

[1347] Step 10:

[1348] The server analyzes the places of interest near the planned visit location and selects suggestions. The suggestions are sent to the user's device and notified. The input is the planned visit data, and the output is the suggested nearby spot information.

[1349] Step 11:

[1350] The terminal displays the suggested spots and asks the user for confirmation. The user confirms the suggested spots and selects the place they want to go. This selection information is sent back to the server. The input is the suggested spot information, and the output is the user's selection data.

[1351] Step 12:

[1352] The server automatically generates a schedule based on the visit plan and the selected nearby spots. The generated schedule is sent to the user's terminal and notified. The input is the visit plan and nearby spot information, and the output is the automatically generated schedule.

[1353] Step 13:

[1354] The device notifies the user of the generated schedule and allows them to add it to their calendar, etc. The user can then check the schedule and adjust it as necessary. The input is the automatically generated schedule, and the output is the adjusted schedule information.

[1355] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1356] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1357] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1358] [Third embodiment]

[1359] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1360] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1361] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1362] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1363] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1364] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1365] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1366] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1367] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1368] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1369] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1370] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1371] The system of the present invention collects personal data from users, analyzes it using a generative AI model, and recommends optimal locations. Furthermore, it is possible to automatically generate and propose schedules for specific planned visits. Specific embodiments for implementing the present invention are described in detail below.

[1372] Data collection and analysis

[1373] Social media data collection

[1374] User: The user installs the application and connects their social media account, which grants access to the data that is collected.

[1375] Device: Obtains authentication information for the linked SNS and sends it to the server.

[1376] Server: Uses SNS APIs to collect user posts, photos, and check-in information and store it in a database for analysis.

[1377] Collecting behavioral history

[1378] User: Starts collecting location information by granting location permission to the application.

[1379] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[1380] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[1381] Collecting feedback data

[1382] Users: Enter their impressions and ratings of the places they visit within the app.

[1383] Terminal: Sends the inputted impression data to the server.

[1384] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[1385] Recommendation generation

[1386] User data integration and analysis

[1387] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1388] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[1389] Generating a recommendation list

[1390] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[1391] Server: Sends the generated recommendation list to the user's device and notifies them.

[1392] Recommendation notifications

[1393] On the device: The received recommendation list is notified to the user and displayed within the app.

[1394] User: Select a place of interest from the recommended list.

[1395] Automatic schedule generation

[1396] Schedule a visit

[1397] User: Enter plans to visit specific locations in the app and schedule the visit.

[1398] Terminal: Sends the scheduled visit information to the server.

[1399] Suggestions for nearby spots

[1400] Server: Analyzes and suggests points of interest near the location you plan to visit.

[1401] Server: Sends the proposal to the user's device and notifies them.

[1402] On the device: Display the suggested spot and ask the user for confirmation.

[1403] User: Review the suggested spots and select the one they want to go to.

[1404] Automatic Schedule Generation

[1405] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[1406] Server: The completed schedule is sent to the user's terminal and notified.

[1407] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[1408] Specific examples

[1409] The user installs the application and connects to a social media account (e.g., Twitter). Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[1410] In this way, by specifically implementing the present invention, it is possible to recommend efficient and appropriate locations to users and propose planned schedules.

[1411] The processing flow will be explained below.

[1412] Step 1:

[1413] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[1414] Step 2:

[1415] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[1416] Step 3:

[1417] Server: Uses the SNS API to collect data such as user posts, photos, and check-in information and store it in a database.

[1418] Step 4:

[1419] User: Allows the application to use location information.

[1420] Step 5:

[1421] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[1422] Step 6:

[1423] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[1424] Step 7:

[1425] Users: Write their thoughts about the places they visited within the app.

[1426] Step 8:

[1427] Terminal: Sends the inputted impression data to the server.

[1428] Step 9:

[1429] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[1430] Step 10:

[1431] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[1432] Step 11:

[1433] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1434] Step 12:

[1435] Server: Based on the analysis results, a generative AI model is used to select the best restaurants and spots for the user and their friends.

[1436] Step 13:

[1437] Server: Sends the generated recommendation list to the user's device.

[1438] Step 14:

[1439] On the device: The received recommendation list is notified to the user and displayed within the app.

[1440] Step 15:

[1441] User: Select a place of interest from the recommended list.

[1442] Step 16:

[1443] User: Enters an appointment in the app, setting the locations and dates they want to visit.

[1444] Step 17:

[1445] Terminal: Sends the scheduled visit information to the server.

[1446] Step 18:

[1447] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[1448] Step 19:

[1449] Server: Sends information about nearby spots to the user's device.

[1450] Step 20:

[1451] On the device: The suggested spots are notified to the user and displayed within the app.

[1452] Step 21:

[1453] User: Review the suggested spots and select the places that interest them.

[1454] Step 22:

[1455] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[1456] Step 23:

[1457] Server: Sends the generated schedule to the user's terminal.

[1458] Step 24:

[1459] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[1460] Through this series of steps, users can efficiently receive recommendations for the best places and generate a detailed schedule based on their planned visits.

[1461] Example 1

[1462] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1463] Conventional systems have difficulty generating recommendations based on users' interests. They also lack the functionality to automatically generate and propose optimal schedules for planned visits, requiring users to make their own plans. Furthermore, they were unable to efficiently collect and analyze various distributed data sources (social media data, behavioral history, and opinion data) and provide recommendations based on that data.

[1464] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1465] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the generation of a highly accurate recommendation list based on the user's interests and concerns. The server also includes a means for collecting the user's location information and recording their behavioral history, a means for collecting and classifying impression data, and a means for generating an automatic schedule based on the user's planned visits and information on nearby spots. This allows the user to automatically receive an optimal visit plan based on their behavioral history and impression data, enabling them to visit various places efficiently and in a planned manner.

[1466] "Personal data" is a general term for personal information, behavioral data, impression data, etc. related to a user.

[1467] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate and analyze data.

[1468] "Analysis" is the process of using collected data to find patterns or extract specific information.

[1469] A "recommendation list" is a list of places and services suggested based on a user's interests.

[1470] "Social networking services," abbreviated as SNS, are services that allow people to share information and interact with each other via the Internet.

[1471] "Behavioral history" is a record of a user's location information and visited destinations.

[1472] "Opinion data" is data that includes evaluations and opinions of places visited by users and services experienced by users.

[1473] "Planned visits" is information about places the user wants to visit in the future and events the user is planning.

[1474] "Neighborhood spot information" is information about places and facilities of interest in the vicinity of a destination that the user has set as a visiting schedule.

[1475] An "automatic schedule" is a schedule that automatically generates the optimal order of visits and time allocation based on the input visit plans and information on nearby spots.

[1476] "User terminal" is a general term for electronic devices that can be directly operated by a user, such as smartphones and tablets.

[1477] "Notification" is the act of displaying a message or alert to convey information to the user.

[1478] The system of the present invention collects personal data from users, analyzes it with a generative AI model, and recommends optimal locations. It also makes it possible to automatically generate and propose schedules for specific visits.

[1479] Data collection and analysis

[1480] Social media data collection

[1481] User: A user installs an application and connects their social network account (e.g., Twitter), which allows the application to access the user's social network data.

[1482] Device: The device obtains authentication information for the linked SNS and sends that information to the server.

[1483] Server: The server uses social media APIs (e.g., Twitter API) to collect user posts, photos, and check-in information, and stores this data in a database for analysis.

[1484] Collecting behavioral history

[1485] User: The user grants the application permission to use and collect location information.

[1486] Device: The device continuously collects GPS data and records the locations the user has visited and the time spent there.

[1487] Server: The server analyzes the location data to identify places the user frequently visits and stores that cater to specific genres of interest.

[1488] Collecting feedback data

[1489] User: The user enters their impressions and ratings of the places they visit into the application.

[1490] Terminal: The terminal sends the impression data entered by the user to the server.

[1491] Server: The server analyzes the sentiment data using a natural language processing algorithm (e.g., Python's NLTK library) and classifies the content as positive or negative.

[1492] Generating a recommendation list

[1493] User data integration and analysis

[1494] Server: The server integrates social media data, behavioral history, and opinion data to generate a profile that reflects the user's interests and preferences. It also extracts common interests among multiple users.

[1495] Recommendation generation

[1496] Server: The server uses a generative AI model (e.g., OpenAI's GPT-4 model) to generate a recommendation list based on the profile.

[1497] Server: Sends the generated recommendation list to the user's device and notifies them.

[1498] Recommendation notifications

[1499] Device: The device notifies the user of the received recommendation list and displays the list within the app.

[1500] User: The user selects the place they want to visit from the displayed list.

[1501] Automatic schedule generation

[1502] Schedule a visit

[1503] User: The user enters their plans to visit a specific location in the application and schedules the visit.

[1504] Terminal: The terminal sends the set visit schedule to the server.

[1505] Suggestions for nearby spots

[1506] Server: The server analyzes and suggests points of interest near the location you plan to visit.

[1507] Server: Sends the proposal to the user's device and notifies them.

[1508] Terminal: The terminal displays the suggested spots and asks the user for confirmation.

[1509] User: The user reviews the suggested spots and selects the place they want to go.

[1510] Automatic Schedule Generation

[1511] Server: The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[1512] Server: Sends the completed schedule to the user's terminal and notifies them.

[1513] Device: The device will notify the user of the generated schedule and allow them to add it to their calendar.

[1514] Specific examples

[1515] The user installs the application and connects their Twitter account. Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[1516] Example of a prompt for the proposed AI model

[1517] "Generate a list of recommendations that are optimal for each user based on their social media data, location information, and impressions of their visit. For example, if a user plans to go strawberry picking this weekend, suggest nearby cafes and hot springs."

[1518] In this way, the present invention can recommend efficient and appropriate locations to users and propose well-planned schedules.

[1519] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1520] Step 1: User connects social media account

[1521] Specific behavior:

[1522] The user installs the application and connects their social media account (e.g., Twitter).

[1523] Input: Social media account credentials (e.g., OAuth token).

[1524] The device obtains authentication information from the linked SNS and uses it to authorize access to the necessary data.

[1525] Output: The social media credentials are sent to the server.

[1526] Step 2: Collect social media data

[1527] Specific behavior:

[1528] The server uses the SNS API to collect user posts, photos, check-in information, etc.

[1529] Input: The SNS credentials received by the server.

[1530] The server stores this data in a database for analysis.

[1531] Output: Saved social media data.

[1532] Step 3: Location Permissions and Collection

[1533] Specific behavior:

[1534] The user allows the application to use location information.

[1535] Input: User permission to use location information.

[1536] The device continuously collects GPS data and records the user's past visits and time spent there.

[1537] Output: Collected GPS data is sent to a server.

[1538] Step 4: Analyzing behavioral history

[1539] Specific behavior:

[1540] The server analyzes the received location data to identify frequently visited locations and stores of interest.

[1541] Input: GPS data received by the server.

[1542] The server applies data analysis algorithms to extract visitation patterns.

[1543] Output: Analysis results (frequently visited places and trends).

[1544] Step 5: Enter and submit your feedback

[1545] Specific behavior:

[1546] Users enter their impressions and ratings of the places they visit into the application.

[1547] Input: User-entered feedback and ratings.

[1548] The terminal transmits the input impression data to the server.

[1549] Output: The feedback data sent to the server.

[1550] Step 6: Analyze the sentiment data

[1551] Specific behavior:

[1552] The server analyzes the feedback data using a natural language processing algorithm and classifies the content as positive or negative.

[1553] Input: The sentiment data sent to the server.

[1554] The server uses Python's NLTK library to classify the data.

[1555] Output: Classified sentiment data (positive / negative).

[1556] Step 7: Create a user profile

[1557] Specific behavior:

[1558] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1559] Input: Stored social media data, analyzed behavioral history, and classified opinion data.

[1560] The server aggregates this data to create a profile that reflects the user's interests and concerns.

[1561] Output: User profile.

[1562] Step 8: Generate a recommendation list

[1563] Specific behavior:

[1564] The server uses a generative AI model (e.g., GPT-4) to generate a recommendation list from the user profile.

[1565] Input: User profile.

[1566] The server creates a prompt for the AI ​​model and inputs it into the model.

[1567] Example prompt: "Generate a list of recommendations that are optimal for the user based on their social media data, location information, and impressions of their visit. For example, the user is planning to go strawberry picking this weekend. Suggest nearby cafes, hot springs, etc."

[1568] Output: The generated recommendation list.

[1569] Step 9: Notification of recommendation list

[1570] Specific behavior:

[1571] The server sends the generated recommendation list to the user's terminal and notifies the user.

[1572] Input: The generated recommendation list.

[1573] The terminal receives the recommendation list and notifies the user.

[1574] Output: Notification of recommendation list.

[1575] Step 10: Schedule a visit

[1576] Specific behavior:

[1577] The application allows users to input plans to visit specific locations and schedule visits.

[1578] Enter: Visit planned.

[1579] The terminal transmits the set visit schedule to the server.

[1580] Output: The visit schedule sent to the server.

[1581] Step 11: Suggest nearby spots

[1582] Specific behavior:

[1583] The server analyzes and suggests points of interest near the place you plan to visit.

[1584] Input: Visit schedule information.

[1585] The server uses an AI model to analyze points of interest and generate suggestions.

[1586] Output: Suggested points of interest are sent to the device.

[1587] Step 12: Generate an automatic schedule

[1588] Specific behavior:

[1589] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[1590] Input: Planned visits and nearby spot information.

[1591] The server uses a schedule generation algorithm to create an optimal schedule.

[1592] Output: The generated automatic schedule.

[1593] Step 13: Auto-Schedule Notifications

[1594] Specific behavior:

[1595] The server transmits the completed schedule to the user terminal and notifies it.

[1596] Input: The generated automatic schedule.

[1597] The terminal notifies the user of the received schedule so that the user can add it to their calendar.

[1598] Output: Auto-schedule notifications.

[1599] Through the above steps, the system of the present invention can recommend places based on the user's interests and automatically generate an efficient visiting schedule.

[1600] (Application example 1)

[1601] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1602] Conventional food delivery services have been unable to fully utilize users' personal data, making it difficult to provide optimal services tailored to individual preferences and schedules. Furthermore, they lacked functionality to improve the user experience, such as suggesting optimal delivery times based on planned visits and automatically generating schedules. This created a need for a new system that would significantly improve user convenience.

[1603] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1604] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the provision of a delivery service optimized for the user's preferences and schedule. The server also includes a means for proposing the optimal service delivery timing based on the user's schedule, a means for generating a schedule based on the schedule, and a means for notifying the user terminal of the automatic schedule. This enables the delivery service optimized for the user's schedule and the generation of an automatic schedule, significantly improving the user experience.

[1605] "Personal data" refers to a user's personal information, including data from social networking services, behavioral history, and impression data.

[1606] A "generative AI model" is an artificial intelligence model that analyzes collected personal data and generates the optimal recommendation list for the user.

[1607] A "recommendation list" is a list of optimal services and places suggested to a user based on analyzed personal data.

[1608] "User terminal" is a general term for electronic devices used by users, including smartphones, tablets, etc.

[1609] "Location information" refers to data about a user's current location and past visited locations obtained using GPS or other technologies.

[1610] An "automatic schedule" is a schedule that the system automatically generates based on the user's schedule.

[1611] "Service provision timing" refers to the time for providing the service at the optimal timing according to the user's schedule and activities.

[1612] The system of the present invention is a food delivery assistant that collects personal data from users, analyzes it using a generative AI model, and generates an optimal recommendation list and schedule. This system uses a smartphone as its primary device and has multiple means to improve the user experience.

[1613] Data collection and analysis

[1614] Social media data collection

[1615] User: The user installs the application and connects their social networking service (SNS) account, thereby granting permission for data collection.

[1616] Device: Obtains authentication information for the linked SNS and sends it to the server.

[1617] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database for analysis.

[1618] Collecting behavioral history

[1619] User: Starts collecting location information by granting location permission to the application.

[1620] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[1621] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[1622] Collecting feedback data

[1623] Users: Enter their impressions and ratings within the app about places they visit and food they order.

[1624] Terminal: Sends the inputted impression data to the server.

[1625] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[1626] Recommendation generation

[1627] User data integration and analysis

[1628] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1629] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[1630] Generating a recommendation list

[1631] Server: Uses a generative AI model to analyze each user's tastes and preferences and generate a list of delivery restaurants and menus that are best suited for the user and their friends.

[1632] Server: Sends the generated recommendation list to the user's device and notifies them.

[1633] Automatic schedule generation

[1634] Schedule a visit

[1635] User: Enter plans to visit specific locations in the app and schedule the visit.

[1636] Terminal: Sends the scheduled visit information to the server.

[1637] Suggestions for nearby spots

[1638] Server: Analyzes and suggests points of interest near the location you plan to visit.

[1639] Server: Sends the proposal to the user's device and notifies them.

[1640] On the device: Display the suggested spot and ask the user for confirmation.

[1641] User: Review the suggested spots and select the one they want to go to.

[1642] Automatic Schedule Generation

[1643] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[1644] Server: The completed schedule is sent to the user's terminal and notified.

[1645] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[1646] Hardware and software used

[1647] The system includes the following hardware and software:

[1648] Smartphone (used as user device)

[1649] Server (data analysis and storage)

[1650] GPS module (acquisition of location information)

[1651] SNS API (acquiring data from social networking services)

[1652] Natural language processing algorithms (analysis of sentiment data, Transformers, etc.)

[1653] Generative AI model (recommendation list generation)

[1654] Calendar app (schedule notification and management)

[1655] Examples of specific examples and prompts

[1656] Specific examples

[1657] The user installs the application and connects their social media account. Next, they allow the use of location information and enter their thoughts on dishes they have previously ordered. The server collects and analyzes this data. If the user selects "I'm going on a picnic with friends this weekend," the server will suggest nearby delivery restaurants and new menus and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[1658] Prompt Sentence Examples

[1659] user_id = "example_user"

[1660] visit_plan = "2023-12-31 18:00:00"

[1661] main(user_id, visit_plan)

[1662] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1663] Step 1:

[1664] Collection of Personal Data

[1665] Users install the application and connect their SNS account. This allows the server to collect user posts, photos, and check-in information via the SNS API. Specifically, the server obtains user data from the SNS API and stores it in a database.

[1666] Step 2:

[1667] Location information collection

[1668] Users allow applications to use their location information. The device continuously collects GPS data and sends it to a server, which records the places visited and the time spent there, and stores it in a database.

[1669] Step 3:

[1670] Inputting feedback data

[1671] Users input their impressions and ratings of the places they visited and the food they ordered into the application. The device sends the input impression data to the server and stores it in a database.

[1672] Step 4:

[1673] Data integration and analysis

[1674] The server integrates the collected social media data, location information, and opinion data to generate a user profile. Using a generative AI model, this data is analyzed to identify the user's preferences. The integrated data is used as input, and the generative AI model analyzes it, outputting user preference data.

[1675] Step 5:

[1676] Generating a recommendation list

[1677] Based on the analysis results, the server generates a recommendation list of delivery restaurants and menus that best suit the user's preferences. Using the preference data as input, the generative AI model generates a recommendation list, which is then output.

[1678] Step 6:

[1679] Recommendation list notification

[1680] The server transmits the generated recommendation list to the user's terminal, and the terminal displays the received recommendation list to the user within the application.

[1681] Step 7:

[1682] Schedule a visit

[1683] The user enters a visit schedule for a specific location and time in the application, and the device sends the visit schedule to the server and stores it in a database.

[1684] Step 8:

[1685] Obtaining and suggesting information about nearby spots

[1686] The server analyzes and suggests interesting spots near the location the user plans to visit. The analysis results are sent to the user's device, which displays the suggestions to the user. The user then checks the suggested spots and selects the ones they want to visit.

[1687] Step 9:

[1688] Automatic Schedule Generation

[1689] The server automatically generates a schedule based on the visit schedule and the nearby spot information selected by the user. The optimal delivery time and visit schedule are generated and sent to the user's terminal.

[1690] Step 10:

[1691] Schedule notification and management

[1692] The device notifies the user of the generated schedule and allows the user to add it to applications such as a calendar, allowing the user to use the delivery service according to an optimal schedule.

[1693] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1694] The present invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. The present invention also incorporates an emotion engine that recognizes the user's emotions, allowing the system to flexibly adjust the recommendation list based on the user's emotional state. Specific embodiments for implementing the present invention are described in detail below.

[1695] Data collection and analysis

[1696] Social media data collection

[1697] User: The user installs the application and connects their social media account, which grants them access to the data that is collected.

[1698] Device: Obtains authentication information for the linked SNS and sends it to the server.

[1699] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database.

[1700] Collecting behavioral history

[1701] User: Grants location permission to the application.

[1702] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[1703] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[1704] Collecting feedback data

[1705] Users: Write their thoughts about the places they visited within the app.

[1706] Terminal: Sends the inputted impression data to the server.

[1707] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[1708] Analysis by emotion engine

[1709] Server: Analyzes social media data and sentiment data and runs an emotion engine to identify the user's emotional state.

[1710] Server: Stores the emotional states identified by the emotion engine in a database.

[1711] Recommendation generation and tuning

[1712] User data integration and analysis

[1713] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1714] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1715] Generating a recommendation list

[1716] Server: Uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of restaurants and spots that are best suited for the user and their friends.

[1717] Server: Sends the generated recommendation list to the user's device and notifies them.

[1718] Recommendation notifications

[1719] On the device: The received recommendation list is notified to the user and displayed within the app.

[1720] User: Select a place of interest from the recommended list.

[1721] Automatic schedule generation

[1722] Schedule a visit

[1723] User: Enter plans to visit specific locations in the app and schedule the visit.

[1724] Terminal: Sends the scheduled visit information to the server.

[1725] Suggestions for nearby spots

[1726] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[1727] Server: Sends the proposal to the user's device and notifies them.

[1728] On the device: Display the suggested spot and ask the user for confirmation.

[1729] User: Review the suggested spots and select the one they want to go to.

[1730] Automatic Schedule Generation

[1731] Server: Automatically generate a schedule based on planned visits and selected nearby spots.

[1732] Server: Sends the completed schedule to the user's terminal and notifies them.

[1733] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[1734] Specific examples

[1735] The user installs the application and connects their social media account (e.g., Twitter). Next, they allow the use of location information and enter their thoughts about cafes they have visited in the past. If the emotion engine detects from social media data that the user is feeling stressed, the server will prioritize recommendations of relaxing cafes and quiet restaurants. If the user selects "I'm going strawberry picking on the weekend," the server will suggest nearby spots (e.g., relaxing cafes and hot springs) and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[1736] In this way, by specifically implementing the present invention, it is possible to provide flexible recommendations according to the user's emotional state and propose planned schedules.

[1737] The processing flow will be explained below.

[1738] Step 1:

[1739] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[1740] Step 2:

[1741] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[1742] Step 3:

[1743] Server: Uses SNS APIs to collect data such as user posts, photos, and check-in information and store it in a database.

[1744] Step 4:

[1745] User: Allows the application to use location information.

[1746] Step 5:

[1747] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[1748] Step 6:

[1749] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[1750] Step 7:

[1751] Users: Write their thoughts about the places they visited within the app.

[1752] Step 8:

[1753] Terminal: Sends the inputted impression data to the server.

[1754] Step 9:

[1755] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[1756] Step 10:

[1757] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[1758] Step 11:

[1759] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1760] Step 12:

[1761] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[1762] Step 13:

[1763] Server: Sends the generated recommendation list to the user's device.

[1764] Step 14:

[1765] On the device: The received recommendation list is notified to the user and displayed within the app.

[1766] Analysis and adjustment by emotion engine

[1767] Step 15:

[1768] Server: Uses an emotion engine to analyze social media data and sentiment data to identify the user's emotional state.

[1769] Step 16:

[1770] Server: Stores the emotional states identified by the emotion engine in a database.

[1771] Step 17:

[1772] Server: Adjust and regenerate the recommendation list depending on the emotional state.

[1773] Step 18:

[1774] Server: Sends the tailored recommendation list to the user's device.

[1775] Automatic schedule generation

[1776] Step 19:

[1777] User: Enter plans to visit specific locations in the app and schedule the visit.

[1778] Step 20:

[1779] Terminal: Sends the scheduled visit information to the server.

[1780] Step 21:

[1781] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[1782] Step 22:

[1783] Server: Sends the proposal to the user's device and notifies them.

[1784] Step 23:

[1785] On the device: Display the suggested spot and ask the user for confirmation.

[1786] Step 24:

[1787] User: Review the suggested spots and select the one they want to go to.

[1788] Step 25:

[1789] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[1790] Step 26:

[1791] Server: Sends the generated schedule to the user's terminal.

[1792] Step 27:

[1793] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[1794] Through this series of steps, users can efficiently receive recommendations for the best places to visit and generate a detailed schedule based on their planned visits. By combining this with an emotion engine, it is also possible to flexibly adjust the schedule according to the user's emotional state.

[1795] Example 2

[1796] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1797] In modern society, recommendation systems that meet the needs of individual users are extremely important, but conventional systems have had difficulty making recommendations that take into account the emotional state of each user. In particular, although recommending places that reduce users' stress and emotional anxiety would be effective, there were a lack of methods to achieve this. Furthermore, generating and proposing flexible and efficient schedules based on planned visits was also difficult.

[1798] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1799] In this invention, the server includes means for collecting personal data of users, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results, means for notifying the user terminal of the recommendation list, means for using an emotion engine to analyze the user's emotional state, and means for flexibly adjusting the recommendation list based on the analysis results. This makes it possible to provide a flexible recommendation list tailored to the user's emotions and automatically generate an efficient schedule based on the user's planned visits.

[1800] "Personal data" refers to information specific to an individual user, such as the user's behavior, interests, and impressions, and includes data from social networking services, behavioral history, and impression data.

[1801] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze user data and generate appropriate information or suggestions based on the results. Specific examples include natural language generation models.

[1802] An "emotion engine" refers to an algorithm that analyzes a user's emotional state from collected data, and this is achieved using emotion analysis tools and APIs.

[1803] A "recommendation list" refers to a list of places, products, etc. recommended to a user, generated based on analyzed data.

[1804] A "visit plan" refers to a plan to visit a particular location in the future that a user inputs into the application.

[1805] "Nearby spot information" refers to information about interesting places and facilities located around the place you plan to visit.

[1806] "Automatic schedule" refers to a schedule of activities that is automatically generated by an algorithm based on the user's planned visits and information about nearby spots.

[1807] "User terminal" refers to a digital device that is directly used by a user, such as a smartphone or tablet.

[1808] "Notification" refers to the act of conveying information from the system to the user, including push notifications and in-app displays.

[1809] "Analysis results" refers to the analytical conclusions and insights obtained after processing collected data using generative AI models and emotion engines.

[1810] "Flexible adjustment" refers to dynamically changing the recommendation list and suggestions depending on the user's emotions and situation.

[1811] This invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. It also incorporates an emotion engine that recognizes the user's emotional state and has the ability to flexibly adjust the recommendation list based on the user's emotional state.

[1812] Hardware and software used in data collection

[1813] Social media data collection

[1814] A user installs the application and connects their social media account, which allows access to the data that is collected.

[1815] The terminal acquires the user's SNS authentication information and sends it to the server.

[1816] The server uses SNS APIs (e.g., Twitter API) to collect user posts, photos, and check-in information. This data is stored in a database.

[1817] Collecting behavioral history

[1818] The user grants the application permission to use location information.

[1819] The device collects GPS data in real time and records the places you visit and the time you stay there.

[1820] The server analyzes the collected location data and stores the frequency of visits and length of stay in a database.

[1821] Collecting feedback data

[1822] Users enter their thoughts about the places they visited within the app.

[1823] The terminal transmits the input impression data to the server.

[1824] The server receives the data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), and evaluates it as positive or negative. The evaluation results are also stored in a database.

[1825] Analysis by emotion engine

[1826] The server analyzes the social media data and sentiment data, and runs an emotion engine (e.g., IBM Watson) algorithm to identify the user's emotional state. The analysis results are stored in a database.

[1827] Recommendation generation and notification

[1828] Generating a recommendation list

[1829] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[1830] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[1831] The server transmits the generated recommendation list to the user's terminal.

[1832] Recommendation list notification

[1833] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[1834] The user selects a place of interest from the displayed recommendation list.

[1835] Automatic schedule generation

[1836] Schedule a visit

[1837] Through the application, the user inputs plans to visit specific locations and schedules the visit.

[1838] The terminal transmits the set visiting schedule to the server.

[1839] Suggestions for nearby spots

[1840] The server analyzes points of interest near the planned visit location and selects suggestions.

[1841] The server sends the proposal content to the user terminal and notifies the user via push notification.

[1842] The terminal displays the suggested spots and asks the user for confirmation.

[1843] The user checks the suggested spots and selects the place they want to go.

[1844] Automatic Schedule Generation

[1845] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[1846] The server stores the generated schedule in a database and transmits it to the user terminal.

[1847] Schedule notifications and additions

[1848] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[1849] The user adds the schedule to the calendar using the options provided.

[1850] As described above, by implementing the present invention, it is possible to provide a flexible recommendation list according to the emotional state of the user and to automatically generate an efficient schedule based on the planned visits.

[1851] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1852] Step 1:

[1853] Application installation and integration settings

[1854] Users install the application on their smartphones, and then when they launch it for the first time, they link it to their social media accounts.

[1855] The terminal acquires the SNS authentication information entered by the user, generates an authentication token, and sends it to the server.

[1856] The server establishes communication with the SNS API based on the received authentication token and prepares to collect data.

[1857] Input: User's social media credentials

[1858] Output: Communication session with SNS API

[1859] Specific behavior: Attempts to connect to the SNS API and validates the token

[1860] Step 2:

[1861] Social media data collection

[1862] The server uses an SNS API (e.g., an API provided by an SNS service) to collect user posts, photos, and check-in information.

[1863] Input: SNS authentication token

[1864] Output: Posts, photos, and check-ins

[1865] Specific behavior: Requests to API endpoints and analysis of responses

[1866] Step 3:

[1867] Collecting behavioral history

[1868] The user gives permission for the application to use location information.

[1869] The device collects and records location information obtained from the GPS sensor in real time.

[1870] The terminal transmits the collected location information data to the server.

[1871] The server analyzes the received location data and stores the frequency of visits and length of stay in a database.

[1872] Input: Location data

[1873] Output: Visit frequency and duration data

[1874] Specific operation: GPS data analysis and statistical processing

[1875] Step 4:

[1876] Collecting feedback data

[1877] Users enter text within the app to share their thoughts about the places they visit.

[1878] The terminal transmits the input impression data to the server.

[1879] The server receives the opinion data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), rates it positively or negatively, and stores the results in a database.

[1880] Input: Impression data

[1881] Output: Positive / negative rating

[1882] Specific behavior: Text data analysis and emotion evaluation

[1883] Step 5:

[1884] Emotional state analysis using emotion engine

[1885] The server analyzes the SNS data and sentiment data, and executes the algorithm of the emotion engine (e.g., API of the emotion analysis service) to identify the user's emotional state. The analysis results are stored in a database.

[1886] Input: SNS data, opinion data

[1887] Output: User's emotional state

[1888] Specific operation: Running a sentiment analysis algorithm and saving the results

[1889] Step 6:

[1890] Generating a recommendation list

[1891] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[1892] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[1893] The server transmits the generated recommendation list to the user's terminal.

[1894] Input: Social media data, behavioral history, impression data, prompt text

[1895] Output: Recommendation list

[1896] What it does: Combines data and runs AI models to generate a list

[1897] Step 7:

[1898] Recommendation list notification

[1899] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[1900] The user selects a place of interest from the displayed recommendation list.

[1901] Input: Recommendation list

[1902] Output: User's choice

[1903] Specific behavior: Displaying notifications and recording user choices

[1904] Step 8:

[1905] Schedule a visit

[1906] The user enters plans to visit specific locations in the application and schedules the visit.

[1907] The terminal transmits the set visiting schedule to the server.

[1908] Input: Visit Schedule

[1909] Output: Visit schedule data

[1910] Specific behavior: Save and send a visit appointment

[1911] Step 9:

[1912] Suggestions for nearby spots

[1913] The server analyzes points of interest near the planned visit location and selects suggestions.

[1914] The server sends the proposal content to the user terminal and notifies the user via push notification.

[1915] The terminal displays the suggested spots and asks the user for confirmation.

[1916] The user checks the suggested spots and selects the place they want to go.

[1917] Input: Visit schedule data, nearby spot information

[1918] Output: Proposal, user's choice

[1919] Specific behavior: Spot analysis and suggestion notification

[1920] Step 10:

[1921] Automatic Schedule Generation

[1922] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[1923] The server stores the generated schedule in a database and transmits it to the user terminal.

[1924] Input: Planned visit, selected nearby spots

[1925] Output: Auto-generated schedule

[1926] Specific behavior: Automatically generate and save schedules

[1927] Step 11:

[1928] Schedule notifications and additions

[1929] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[1930] The user adds the generated schedule to their calendar using the options provided.

[1931] Input: Auto-generated schedule

[1932] Output: Add to calendar

[1933] Specific operation: Schedule notification and calendar update options provided

[1934] (Application example 2)

[1935] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1936] Conventional recommendation systems make recommendations based on a user's behavioral history and personal data, but because they cannot take the user's emotional state into account, it is difficult to provide highly satisfying recommendations that address the user's current psychological needs. Furthermore, existing systems automatically generate schedules based solely on the user's plans, failing to reflect the user's emotional state, resulting in incomplete plans. There is a need to solve these issues and realize optimal recommendations and automatic schedule generation that reflect the user's psychological state.

[1937] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results and the user's emotional state, means for inputting the user's visit plans, means for acquiring information on spots near the planned visits, means for generating an automatic schedule based on the planned visits and the information on nearby spots, means for notifying the user terminal of the recommendation list and the automatic schedule, and means for adjusting the schedule based on the user's emotional state. This enables flexible and satisfying recommendations that take the user's emotional state into consideration and automatic generation of a schedule that suits the user's psychological state.

[1938] "Personal data" refers to information about individual users, including data from social networking services, behavioral history, and impression data.

[1939] A "generative AI model" refers to an algorithm or mechanism that uses artificial intelligence to analyze data and generate new information or recommendations.

[1940] The "emotional state" indicates the psychological state of the user, and includes an evaluation of emotions such as positive or negative.

[1941] A "recommendation list" refers to a list of recommended places, products, etc. for a user, which is generated based on collected and analyzed personal data and emotional state.

[1942] "User terminal" refers to a device used by a user, such as a computer, smartphone, tablet, or biometric input device.

[1943] "Visiting Plans" indicates plans such as places the user wants to visit or events the user wants to attend in the future.

[1944] "Neighborhood spot information" refers to information about spots located in the vicinity of a place that the user plans to visit.

[1945] "Automatic schedule" refers to a user's action plan that is automatically generated based on planned visits and information on nearby spots.

[1946] The "notification means" refers to a method or device for transmitting specific information to a user terminal and informing the user of that information.

[1947] "Adjustment measures" refer to methods and mechanisms for changing or modifying plans such as schedules and lists based on specific conditions.

[1948] This invention is a system that provides an optimal recommendation list and schedule by collecting personal data of a user and analyzing the data with a generative AI model. The system includes the following means.

[1949] Data collection and analysis

[1950] Social media data collection

[1951] Users install the application and connect their social media accounts, which grants them access to the data that is collected.

[1952] The device obtains the SNS authentication information and sends it to the server.

[1953] The server uses the SNS API to collect user posts, photos, and check-in information and store them in a database.

[1954] Collecting behavioral history

[1955] The user gives permission for the application to use location information.

[1956] The device collects GPS data in real time, recording the places you visit and the time you stay there.

[1957] The server receives the collected location data and analyzes the frequency of visits and the length of time spent at specific locations.

[1958] Collecting feedback data

[1959] Users enter their impressions of the places they visit within the app.

[1960] The terminal transmits the input impression data to the server.

[1961] The server receives the sentiment data, analyzes the content using natural language processing algorithms (e.g., NLTK or SpaCy), and assigns a positive or negative rating.

[1962] Analysis by emotion engine

[1963] The server analyzes the SNS data and sentiment data and runs an emotion engine to identify the user's emotional state.

[1964] The server stores the emotional states identified by the emotion engine in a database.

[1965] Recommendation generation and tuning

[1966] User data integration and analysis

[1967] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[1968] The server integrates the profiles of multiple users, extracts common interests, and performs analysis.

[1969] Generating a recommendation list

[1970] The server uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of products and spots that are best suited for the user and their friends.

[1971] The server sends the generated recommendation list to the user's terminal and notifies the user.

[1972] Automatic schedule generation

[1973] Schedule a visit

[1974] The application allows users to input plans to visit specific locations and schedule visits.

[1975] The terminal transmits the set visit schedule to the server.

[1976] Suggestions for nearby spots

[1977] The server analyzes points of interest near the planned visit and selects suggestions.

[1978] The server transmits the proposal contents to the user terminal and notifies it.

[1979] The terminal displays the suggested spots and asks the user for confirmation.

[1980] The user checks the suggested spots and selects the place they want to go.

[1981] Automatic Schedule Generation

[1982] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[1983] The server transmits the generated schedule to the user terminal and notifies it.

[1984] The terminal notifies the user of the generated schedule so that the user can add it to a calendar, etc.

[1985] Specific examples

[1986] The user installs the application and connects their social media account. Next, they allow the use of their location information and enter their thoughts about shops they have visited in the past. If the emotion engine detects the user's current psychological state from the social media data, for example, if it determines that the user is feeling stressed, the server will prioritize recommendations of items that will help them relax.

[1987] Example prompts for generative AI models

[1988] An example of a prompt is shown below.

[1989] Recommend shopping items based on the user's emotional state.

[1990] User social media data: ["I'm busy and stressed today", "I want to try out a new gadget"]

[1991] Emotional state: Negative

[1992] User profile: {"interests": ["relaxation", "gadgets"]}

[1993] Recommendation list: ["Relaxation furniture", "Aroma candles", "Massage machine"]

[1994] By setting prompt sentences in this way, the generative AI model can provide a recommendation list that is optimal for the user's psychological state.

[1995] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1996] Step 1:

[1997] A user installs the application and links their SNS account. This linking allows the application to obtain authorization to access the user's SNS data. Once the user authorizes the linking, the device sends the SNS authentication information to the server. The input is the SNS authentication information, and the output is a request containing the authentication information.

[1998] Step 2:

[1999] The server uses SNS APIs to collect user posts, photos, and check-in information. The collected data is stored in a database. The input is user data obtained through the SNS API, and the output is personal data stored in the database.

[2000] Step 3:

[2001] The user gives permission for the application to use location information. The device collects GPS data in real time and records the places visited and the duration of stay. This data is periodically sent to the server. The input is real-time GPS data, and the output is visit history data sent to the server.

[2002] Step 4:

[2003] The user enters their thoughts about the places they visited in the app. The device sends the entered thoughts to the server. The server uses a natural language processing algorithm (e.g., NLTK or SpaCy) to analyze the thoughts and evaluate their emotions. The input is the thoughts entered by the user, and the output is the analyzed emotional state data.

[2004] Step 5:

[2005] The server analyzes the collected SNS data and sentiment data and runs an emotion engine to identify the user's emotional state. The emotion engine uses the analysis results to identify the user's emotional state and stores the data in a database. The input is SNS data and sentiment data, and the output is emotional state data.

[2006] Step 6:

[2007] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user. It integrates the profiles of multiple users, extracts common interests, and performs analysis. The input is the integrated user data, and the output is each user's profile data.

[2008] Step 7:

[2009] The server uses a generative AI model to generate a recommendation list based on the user's profile and emotional state. The program inputs a prompt into the generative AI model to create a recommendation list. The input is the user's profile and emotional state data, and the output is a recommendation list.

[2010] Step 8:

[2011] The server sends the generated recommendation list to the user's device and notifies them. The device displays the recommendation list to the user. The input is the recommendation list, and the output is a notification to the user.

[2012] Step 9:

[2013] The user enters plans to visit specific locations in the application and sets up a visit schedule. The device sends the set visit schedule to the server. This data is stored on the server as visit schedule data. The input is the visit schedule, and the output is the data sent to the server.

[2014] Step 10:

[2015] The server analyzes the places of interest near the planned visit location and selects suggestions. The suggestions are sent to the user's device and notified. The input is the planned visit data, and the output is the suggested nearby spot information.

[2016] Step 11:

[2017] The terminal displays the suggested spots and asks the user for confirmation. The user confirms the suggested spots and selects the place they want to go. This selection information is sent back to the server. The input is the suggested spot information, and the output is the user's selection data.

[2018] Step 12:

[2019] The server automatically generates a schedule based on the visit plan and the selected nearby spots. The generated schedule is sent to the user's terminal and notified. The input is the visit plan and nearby spot information, and the output is the automatically generated schedule.

[2020] Step 13:

[2021] The device notifies the user of the generated schedule and allows them to add it to their calendar, etc. The user can then check the schedule and adjust it as necessary. The input is the automatically generated schedule, and the output is the adjusted schedule information.

[2022] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[2023] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2024] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[2025] [Fourth embodiment]

[2026] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2027] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2029] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[2030] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[2031] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[2032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2033] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[2034] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[2035] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[2036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2037] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[2038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2039] The system of the present invention collects personal data from users, analyzes it using a generative AI model, and recommends optimal locations. Furthermore, it is possible to automatically generate and propose schedules for specific planned visits. Specific embodiments for implementing the present invention are described in detail below.

[2040] Data collection and analysis

[2041] Social media data collection

[2042] User: The user installs the application and connects their social media account, which grants access to the data that is collected.

[2043] Device: Obtains authentication information for the linked SNS and sends it to the server.

[2044] Server: Uses SNS APIs to collect user posts, photos, and check-in information and store it in a database for analysis.

[2045] Collecting behavioral history

[2046] User: Starts collecting location information by granting location permission to the application.

[2047] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[2048] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[2049] Collecting feedback data

[2050] Users: Enter their impressions and ratings of the places they visit within the app.

[2051] Terminal: Sends the inputted impression data to the server.

[2052] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[2053] Recommendation generation

[2054] User data integration and analysis

[2055] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[2056] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[2057] Generating a recommendation list

[2058] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[2059] Server: Sends the generated recommendation list to the user's device and notifies them.

[2060] Recommendation notifications

[2061] On the device: The received recommendation list is notified to the user and displayed within the app.

[2062] User: Select a place of interest from the recommended list.

[2063] Automatic schedule generation

[2064] Schedule a visit

[2065] User: Enter plans to visit specific locations in the app and schedule the visit.

[2066] Terminal: Sends the scheduled visit information to the server.

[2067] Suggestions for nearby spots

[2068] Server: Analyzes and suggests points of interest near the location you plan to visit.

[2069] Server: Sends the proposal to the user's device and notifies them.

[2070] On the device: Display the suggested spot and ask the user for confirmation.

[2071] User: Review the suggested spots and select the one they want to go to.

[2072] Automatic Schedule Generation

[2073] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[2074] Server: The completed schedule is sent to the user's terminal and notified.

[2075] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[2076] Specific examples

[2077] The user installs the application and connects to a social media account (e.g., Twitter). Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[2078] In this way, by specifically implementing the present invention, it is possible to recommend efficient and appropriate locations to users and propose planned schedules.

[2079] The processing flow will be explained below.

[2080] Step 1:

[2081] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[2082] Step 2:

[2083] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[2084] Step 3:

[2085] Server: Uses the SNS API to collect data such as user posts, photos, and check-in information and store it in a database.

[2086] Step 4:

[2087] User: Allows the application to use location information.

[2088] Step 5:

[2089] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[2090] Step 6:

[2091] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[2092] Step 7:

[2093] Users: Write their thoughts about the places they visited within the app.

[2094] Step 8:

[2095] Terminal: Sends the inputted impression data to the server.

[2096] Step 9:

[2097] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[2098] Step 10:

[2099] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[2100] Step 11:

[2101] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[2102] Step 12:

[2103] Server: Based on the analysis results, a generative AI model is used to select the best restaurants and spots for the user and their friends.

[2104] Step 13:

[2105] Server: Sends the generated recommendation list to the user's device.

[2106] Step 14:

[2107] On the device: The received recommendation list is notified to the user and displayed within the app.

[2108] Step 15:

[2109] User: Select a place of interest from the recommended list.

[2110] Step 16:

[2111] User: Enters an appointment in the app, setting the locations and dates they want to visit.

[2112] Step 17:

[2113] Terminal: Sends the scheduled visit information to the server.

[2114] Step 18:

[2115] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[2116] Step 19:

[2117] Server: Sends information about nearby spots to the user's device.

[2118] Step 20:

[2119] On the device: The suggested spots are notified to the user and displayed within the app.

[2120] Step 21:

[2121] User: Review the suggested spots and select the places that interest them.

[2122] Step 22:

[2123] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[2124] Step 23:

[2125] Server: Sends the generated schedule to the user's terminal.

[2126] Step 24:

[2127] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[2128] Through this series of steps, users can efficiently receive recommendations for the best places and generate a detailed schedule based on their planned visits.

[2129] Example 1

[2130] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2131] Conventional systems have difficulty generating recommendations based on users' interests. They also lack the functionality to automatically generate and propose optimal schedules for planned visits, requiring users to make their own plans. Furthermore, they were unable to efficiently collect and analyze various distributed data sources (social media data, behavioral history, and opinion data) and provide recommendations based on that data.

[2132] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2133] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the generation of a highly accurate recommendation list based on the user's interests and concerns. The server also includes a means for collecting the user's location information and recording their behavioral history, a means for collecting and classifying impression data, and a means for generating an automatic schedule based on the user's planned visits and information on nearby spots. This allows the user to automatically receive an optimal visit plan based on their behavioral history and impression data, enabling them to visit various places efficiently and in a planned manner.

[2134] "Personal data" is a general term for personal information, behavioral data, impression data, etc. related to a user.

[2135] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate and analyze data.

[2136] "Analysis" is the process of using collected data to find patterns or extract specific information.

[2137] A "recommendation list" is a list of places and services suggested based on a user's interests.

[2138] "Social networking services," abbreviated as SNS, are services that allow people to share information and interact with each other via the Internet.

[2139] "Behavioral history" is a record of a user's location information and visited destinations.

[2140] "Opinion data" is data that includes evaluations and opinions of places visited by users and services experienced by users.

[2141] "Planned visits" is information about places the user wants to visit in the future and events the user is planning.

[2142] "Neighborhood spot information" is information about places and facilities of interest in the vicinity of a destination that the user has set as a visiting schedule.

[2143] An "automatic schedule" is a schedule that automatically generates the optimal order of visits and time allocation based on the input visit plans and information on nearby spots.

[2144] "User terminal" is a general term for electronic devices that can be directly operated by a user, such as smartphones and tablets.

[2145] "Notification" is the act of displaying a message or alert to convey information to the user.

[2146] The system of the present invention collects personal data from users, analyzes it with a generative AI model, and recommends optimal locations. It also makes it possible to automatically generate and propose schedules for specific visits.

[2147] Data collection and analysis

[2148] Social media data collection

[2149] User: A user installs an application and connects their social network account (e.g., Twitter), which allows the application to access the user's social network data.

[2150] Device: The device obtains authentication information for the linked SNS and sends that information to the server.

[2151] Server: The server uses social media APIs (e.g., Twitter API) to collect user posts, photos, and check-in information, and stores this data in a database for analysis.

[2152] Collecting behavioral history

[2153] User: The user grants the application permission to use and collect location information.

[2154] Device: The device continuously collects GPS data and records the locations the user has visited and the time spent there.

[2155] Server: The server analyzes the location data to identify places the user frequently visits and stores that cater to specific genres of interest.

[2156] Collecting feedback data

[2157] User: The user enters their impressions and ratings of the places they visit into the application.

[2158] Terminal: The terminal sends the impression data entered by the user to the server.

[2159] Server: The server analyzes the sentiment data using a natural language processing algorithm (e.g., Python's NLTK library) and classifies the content as positive or negative.

[2160] Generating a recommendation list

[2161] User data integration and analysis

[2162] Server: The server integrates social media data, behavioral history, and opinion data to generate a profile that reflects the user's interests and preferences. It also extracts common interests among multiple users.

[2163] Recommendation generation

[2164] Server: The server uses a generative AI model (e.g., OpenAI's GPT-4 model) to generate a recommendation list based on the profile.

[2165] Server: Sends the generated recommendation list to the user's device and notifies them.

[2166] Recommendation notifications

[2167] Device: The device notifies the user of the received recommendation list and displays the list within the app.

[2168] User: The user selects the place they want to visit from the displayed list.

[2169] Automatic schedule generation

[2170] Schedule a visit

[2171] User: The user enters their plans to visit a specific location in the application and schedules the visit.

[2172] Terminal: The terminal sends the set visit schedule to the server.

[2173] Suggestions for nearby spots

[2174] Server: The server analyzes and suggests points of interest near the location you plan to visit.

[2175] Server: Sends the proposal to the user's device and notifies them.

[2176] Terminal: The terminal displays the suggested spots and asks the user for confirmation.

[2177] User: The user reviews the suggested spots and selects the place they want to go.

[2178] Automatic Schedule Generation

[2179] Server: The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[2180] Server: Sends the completed schedule to the user's terminal and notifies them.

[2181] Device: The device will notify the user of the generated schedule and allow them to add it to their calendar.

[2182] Specific examples

[2183] The user installs the application and connects their Twitter account. Next, they allow the use of location information and enter their impressions of cafes they have visited in the past. The server collects and analyzes this data. If the user selects "I'm going strawberry picking this weekend," the server will suggest nearby cafes and hot springs and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[2184] Example of a prompt for the proposed AI model

[2185] "Generate a list of recommendations that are optimal for each user based on their social media data, location information, and impressions of their visit. For example, if a user plans to go strawberry picking this weekend, suggest nearby cafes and hot springs."

[2186] In this way, the present invention can recommend efficient and appropriate locations to users and propose well-planned schedules.

[2187] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2188] Step 1: User connects social media account

[2189] Specific behavior:

[2190] The user installs the application and connects their social media account (e.g., Twitter).

[2191] Input: Social media account credentials (e.g., OAuth token).

[2192] The device obtains authentication information from the linked SNS and uses it to authorize access to the necessary data.

[2193] Output: The social media credentials are sent to the server.

[2194] Step 2: Collect social media data

[2195] Specific behavior:

[2196] The server uses the SNS API to collect user posts, photos, check-in information, etc.

[2197] Input: The SNS credentials received by the server.

[2198] The server stores this data in a database for analysis.

[2199] Output: Saved social media data.

[2200] Step 3: Location Permissions and Collection

[2201] Specific behavior:

[2202] The user allows the application to use location information.

[2203] Input: User permission to use location information.

[2204] The device continuously collects GPS data and records the user's past visits and time spent there.

[2205] Output: Collected GPS data is sent to a server.

[2206] Step 4: Analyzing behavioral history

[2207] Specific behavior:

[2208] The server analyzes the received location data to identify frequently visited locations and stores of interest.

[2209] Input: GPS data received by the server.

[2210] The server applies data analysis algorithms to extract visitation patterns.

[2211] Output: Analysis results (frequently visited places and trends).

[2212] Step 5: Enter and submit your feedback

[2213] Specific behavior:

[2214] Users enter their impressions and ratings of the places they visit into the application.

[2215] Input: User-entered feedback and ratings.

[2216] The terminal transmits the input impression data to the server.

[2217] Output: The feedback data sent to the server.

[2218] Step 6: Analyze the sentiment data

[2219] Specific behavior:

[2220] The server analyzes the feedback data using a natural language processing algorithm and classifies the content as positive or negative.

[2221] Input: The sentiment data sent to the server.

[2222] The server uses Python's NLTK library to classify the data.

[2223] Output: Classified sentiment data (positive / negative).

[2224] Step 7: Create a user profile

[2225] Specific behavior:

[2226] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[2227] Input: Stored social media data, analyzed behavioral history, and classified opinion data.

[2228] The server aggregates this data to create a profile that reflects the user's interests and concerns.

[2229] Output: User profile.

[2230] Step 8: Generate a recommendation list

[2231] Specific behavior:

[2232] The server uses a generative AI model (e.g., GPT-4) to generate a recommendation list from the user profile.

[2233] Input: User profile.

[2234] The server creates a prompt for the AI ​​model and inputs it into the model.

[2235] Example prompt: "Generate a list of recommendations that are optimal for the user based on their social media data, location information, and impressions of their visit. For example, the user is planning to go strawberry picking this weekend. Suggest nearby cafes, hot springs, etc."

[2236] Output: The generated recommendation list.

[2237] Step 9: Notification of recommendation list

[2238] Specific behavior:

[2239] The server sends the generated recommendation list to the user's terminal and notifies the user.

[2240] Input: The generated recommendation list.

[2241] The terminal receives the recommendation list and notifies the user.

[2242] Output: Notification of recommendation list.

[2243] Step 10: Schedule a visit

[2244] Specific behavior:

[2245] The application allows users to input plans to visit specific locations and schedule visits.

[2246] Enter: Visit planned.

[2247] The terminal transmits the set visit schedule to the server.

[2248] Output: The visit schedule sent to the server.

[2249] Step 11: Suggest nearby spots

[2250] Specific behavior:

[2251] The server analyzes and suggests points of interest near the place you plan to visit.

[2252] Input: Visit schedule information.

[2253] The server uses an AI model to analyze points of interest and generate suggestions.

[2254] Output: Suggested points of interest are sent to the device.

[2255] Step 12: Generate an automatic schedule

[2256] Specific behavior:

[2257] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[2258] Input: Planned visits and nearby spot information.

[2259] The server uses a schedule generation algorithm to create an optimal schedule.

[2260] Output: The generated automatic schedule.

[2261] Step 13: Auto-Schedule Notifications

[2262] Specific behavior:

[2263] The server transmits the completed schedule to the user terminal and notifies it.

[2264] Input: The generated automatic schedule.

[2265] The terminal notifies the user of the received schedule so that the user can add it to their calendar.

[2266] Output: Auto-schedule notifications.

[2267] Through the above steps, the system of the present invention can recommend places based on the user's interests and automatically generate an efficient visiting schedule.

[2268] (Application example 1)

[2269] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2270] Conventional food delivery services have been unable to fully utilize users' personal data, making it difficult to provide optimal services tailored to individual preferences and schedules. Furthermore, they lacked functionality to improve the user experience, such as suggesting optimal delivery times based on planned visits and automatically generating schedules. This created a need for a new system that would significantly improve user convenience.

[2271] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2272] In this invention, the server includes a means for collecting personal data, a means for analyzing the collected personal data using a generative AI model, and a means for generating a recommendation list based on the analysis results. This enables the provision of a delivery service optimized for the user's preferences and schedule. The server also includes a means for proposing the optimal service delivery timing based on the user's schedule, a means for generating a schedule based on the schedule, and a means for notifying the user terminal of the automatic schedule. This enables the delivery service optimized for the user's schedule and the generation of an automatic schedule, significantly improving the user experience.

[2273] "Personal data" refers to a user's personal information, including data from social networking services, behavioral history, and impression data.

[2274] A "generative AI model" is an artificial intelligence model that analyzes collected personal data and generates the optimal recommendation list for the user.

[2275] A "recommendation list" is a list of optimal services and places suggested to a user based on analyzed personal data.

[2276] "User terminal" is a general term for electronic devices used by users, including smartphones, tablets, etc.

[2277] "Location information" refers to data about a user's current location and past visited locations obtained using GPS or other technologies.

[2278] An "automatic schedule" is a schedule that the system automatically generates based on the user's schedule.

[2279] "Service provision timing" refers to the time for providing the service at the optimal timing according to the user's schedule and activities.

[2280] The system of the present invention is a food delivery assistant that collects personal data from users, analyzes it using a generative AI model, and generates an optimal recommendation list and schedule. This system uses a smartphone as its primary device and has multiple means to improve the user experience.

[2281] Data collection and analysis

[2282] Social media data collection

[2283] User: The user installs the application and connects their social networking service (SNS) account, thereby granting permission for data collection.

[2284] Device: Obtains authentication information for the linked SNS and sends it to the server.

[2285] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database for analysis.

[2286] Collecting behavioral history

[2287] User: Starts collecting location information by granting location permission to the application.

[2288] Device: Continuously collects GPS data to record the places you have visited and the time spent there.

[2289] Server: Analyzes location data to identify frequently visited locations and store trends for specific genres.

[2290] Collecting feedback data

[2291] Users: Enter their impressions and ratings within the app about places they visit and food they order.

[2292] Terminal: Sends the inputted impression data to the server.

[2293] Server: Analyzes the sentiment data using a natural language processing algorithm and classifies the content as positive or negative.

[2294] Recommendation generation

[2295] User data integration and analysis

[2296] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[2297] Server: Integrates profiles of multiple users (e.g., a group of friends) and extracts common interests.

[2298] Generating a recommendation list

[2299] Server: Uses a generative AI model to analyze each user's tastes and preferences and generate a list of delivery restaurants and menus that are best suited for the user and their friends.

[2300] Server: Sends the generated recommendation list to the user's device and notifies them.

[2301] Automatic schedule generation

[2302] Schedule a visit

[2303] User: Enter plans to visit specific locations in the app and schedule the visit.

[2304] Terminal: Sends the scheduled visit information to the server.

[2305] Suggestions for nearby spots

[2306] Server: Analyzes and suggests points of interest near the location you plan to visit.

[2307] Server: Sends the proposal to the user's device and notifies them.

[2308] On the device: Display the suggested spot and ask the user for confirmation.

[2309] User: Review the suggested spots and select the one they want to go to.

[2310] Automatic Schedule Generation

[2311] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[2312] Server: The completed schedule is sent to the user's terminal and notified.

[2313] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[2314] Hardware and software used

[2315] The system includes the following hardware and software:

[2316] Smartphone (used as user device)

[2317] Server (data analysis and storage)

[2318] GPS module (acquisition of location information)

[2319] SNS API (acquiring data from social networking services)

[2320] Natural language processing algorithms (analysis of sentiment data, Transformers, etc.)

[2321] Generative AI model (recommendation list generation)

[2322] Calendar app (schedule notification and management)

[2323] Examples of specific examples and prompts

[2324] Specific examples

[2325] The user installs the application and connects their social media account. Next, they allow the use of location information and enter their thoughts on dishes they have previously ordered. The server collects and analyzes this data. If the user selects "I'm going on a picnic with friends this weekend," the server will suggest nearby delivery restaurants and new menus and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[2326] Prompt Sentence Examples

[2327] user_id = "example_user"

[2328] visit_plan = "2023-12-31 18:00:00"

[2329] main(user_id, visit_plan)

[2330] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2331] Step 1:

[2332] Collection of Personal Data

[2333] Users install the application and connect their SNS account. This allows the server to collect user posts, photos, and check-in information via the SNS API. Specifically, the server obtains user data from the SNS API and stores it in a database.

[2334] Step 2:

[2335] Location information collection

[2336] Users allow applications to use their location information. The device continuously collects GPS data and sends it to a server, which records the places visited and the time spent there, and stores it in a database.

[2337] Step 3:

[2338] Inputting feedback data

[2339] Users input their impressions and ratings of the places they visited and the food they ordered into the application. The device sends the input impression data to the server and stores it in a database.

[2340] Step 4:

[2341] Data integration and analysis

[2342] The server integrates the collected social media data, location information, and opinion data to generate a user profile. Using a generative AI model, this data is analyzed to identify the user's preferences. The integrated data is used as input, and the generative AI model analyzes it, outputting user preference data.

[2343] Step 5:

[2344] Generating a recommendation list

[2345] Based on the analysis results, the server generates a recommendation list of delivery restaurants and menus that best suit the user's preferences. Using the preference data as input, the generative AI model generates a recommendation list, which is then output.

[2346] Step 6:

[2347] Recommendation list notification

[2348] The server transmits the generated recommendation list to the user's terminal, and the terminal displays the received recommendation list to the user within the application.

[2349] Step 7:

[2350] Schedule a visit

[2351] The user enters a visit schedule for a specific location and time in the application, and the device sends the visit schedule to the server and stores it in a database.

[2352] Step 8:

[2353] Obtaining and suggesting information about nearby spots

[2354] The server analyzes and suggests interesting spots near the location the user plans to visit. The analysis results are sent to the user's device, which displays the suggestions to the user. The user then checks the suggested spots and selects the ones they want to visit.

[2355] Step 9:

[2356] Automatic Schedule Generation

[2357] The server automatically generates a schedule based on the visit schedule and the nearby spot information selected by the user. The optimal delivery time and visit schedule are generated and sent to the user's terminal.

[2358] Step 10:

[2359] Schedule notification and management

[2360] The device notifies the user of the generated schedule and allows the user to add it to applications such as a calendar, allowing the user to use the delivery service according to an optimal schedule.

[2361] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2362] The present invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. The present invention also incorporates an emotion engine that recognizes the user's emotions, allowing the system to flexibly adjust the recommendation list based on the user's emotional state. Specific embodiments for implementing the present invention are described in detail below.

[2363] Data collection and analysis

[2364] Social media data collection

[2365] User: The user installs the application and connects their social media account, which grants them access to the data that is collected.

[2366] Device: Obtains authentication information for the linked SNS and sends it to the server.

[2367] Server: Uses SNS API to collect user posts, photos, and check-in information and store them in a database.

[2368] Collecting behavioral history

[2369] User: Grants location permission to the application.

[2370] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[2371] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[2372] Collecting feedback data

[2373] Users: Write their thoughts about the places they visited within the app.

[2374] Terminal: Sends the inputted impression data to the server.

[2375] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[2376] Analysis by emotion engine

[2377] Server: Analyzes social media data and sentiment data and runs an emotion engine to identify the user's emotional state.

[2378] Server: Stores the emotional states identified by the emotion engine in a database.

[2379] Recommendation generation and tuning

[2380] User data integration and analysis

[2381] Server: Integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[2382] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[2383] Generating a recommendation list

[2384] Server: Uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of restaurants and spots that are best suited for the user and their friends.

[2385] Server: Sends the generated recommendation list to the user's device and notifies them.

[2386] Recommendation notifications

[2387] On the device: The received recommendation list is notified to the user and displayed within the app.

[2388] User: Select a place of interest from the recommended list.

[2389] Automatic schedule generation

[2390] Schedule a visit

[2391] User: Enter plans to visit specific locations in the app and schedule the visit.

[2392] Terminal: Sends the scheduled visit information to the server.

[2393] Suggestions for nearby spots

[2394] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[2395] Server: Sends the proposal to the user's device and notifies them.

[2396] On the device: Display the suggested spot and ask the user for confirmation.

[2397] User: Review the suggested spots and select the one they want to go to.

[2398] Automatic Schedule Generation

[2399] Server: Automatically generate a schedule based on planned visits and selected nearby spots.

[2400] Server: Sends the completed schedule to the user's terminal and notifies them.

[2401] On the device: The generated schedule is notified to the user so that they can add it to their calendar, etc.

[2402] Specific examples

[2403] The user installs the application and connects their social media account (e.g., Twitter). Next, they allow the use of location information and enter their thoughts about cafes they have visited in the past. If the emotion engine detects from social media data that the user is feeling stressed, the server will prioritize recommendations of relaxing cafes and quiet restaurants. If the user selects "I'm going strawberry picking on the weekend," the server will suggest nearby spots (e.g., relaxing cafes and hot springs) and generate an optimal schedule. The generated schedule is notified to the user and added to their calendar.

[2404] In this way, by specifically implementing the present invention, it is possible to provide flexible recommendations according to the user's emotional state and propose planned schedules.

[2405] The processing flow will be explained below.

[2406] Step 1:

[2407] User: Installs and launches the application. Links social media accounts (e.g., Twitter, Instagram) to the application.

[2408] Step 2:

[2409] Device: Obtains authentication information for the linked SNS account and sends it to the server.

[2410] Step 3:

[2411] Server: Uses SNS APIs to collect data such as user posts, photos, and check-in information and store it in a database.

[2412] Step 4:

[2413] User: Allows the application to use location information.

[2414] Step 5:

[2415] Device: Collects real-time GPS data to record the places you visit and the time you stay.

[2416] Step 6:

[2417] Server: Receives the collected location data and analyzes the frequency of visits and the duration of stay at specific locations.

[2418] Step 7:

[2419] Users: Write their thoughts about the places they visited within the app.

[2420] Step 8:

[2421] Terminal: Sends the inputted impression data to the server.

[2422] Step 9:

[2423] Server: Receives the feedback data, analyzes the content using a natural language processing algorithm, and evaluates it as positive or negative.

[2424] Step 10:

[2425] Server: Integrates social media data, behavioral history, and opinion data to create individual user profiles.

[2426] Step 11:

[2427] Server: Integrates the profiles of multiple users, extracts common interests, and performs analysis.

[2428] Step 12:

[2429] Server: Uses a generative AI model to analyze each user's preferences and generate a list of restaurants and spots that are best suited for the user and their friends.

[2430] Step 13:

[2431] Server: Sends the generated recommendation list to the user's device.

[2432] Step 14:

[2433] On the device: The received recommendation list is notified to the user and displayed within the app.

[2434] Analysis and adjustment by emotion engine

[2435] Step 15:

[2436] Server: Uses an emotion engine to analyze social media data and sentiment data to identify the user's emotional state.

[2437] Step 16:

[2438] Server: Stores the emotional states identified by the emotion engine in a database.

[2439] Step 17:

[2440] Server: Adjust and regenerate the recommendation list depending on the emotional state.

[2441] Step 18:

[2442] Server: Sends the tailored recommendation list to the user's device.

[2443] Automatic schedule generation

[2444] Step 19:

[2445] User: Enter plans to visit specific locations in the app and schedule the visit.

[2446] Step 20:

[2447] Terminal: Sends the scheduled visit information to the server.

[2448] Step 21:

[2449] Server: Analyzes points of interest near the planned visit location and selects suggestions.

[2450] Step 22:

[2451] Server: Sends the proposal to the user's device and notifies them.

[2452] Step 23:

[2453] On the device: Display the suggested spot and ask the user for confirmation.

[2454] Step 24:

[2455] User: Review the suggested spots and select the one they want to go to.

[2456] Step 25:

[2457] Server: Automatically generate a schedule based on the planned visit and selected nearby spots.

[2458] Step 26:

[2459] Server: Sends the generated schedule to the user's terminal.

[2460] Step 27:

[2461] On your device: Notify the user of the created schedule and allow them to add it to their calendar.

[2462] Through this series of steps, users can efficiently receive recommendations for the best places to visit and generate a detailed schedule based on their planned visits. By combining this with an emotion engine, it is also possible to flexibly adjust the schedule according to the user's emotional state.

[2463] Example 2

[2464] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2465] In modern society, recommendation systems that meet the needs of individual users are extremely important, but conventional systems have had difficulty making recommendations that take into account the emotional state of each user. In particular, although recommending places that reduce users' stress and emotional anxiety would be effective, there were a lack of methods to achieve this. Furthermore, generating and proposing flexible and efficient schedules based on planned visits was also difficult.

[2466] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2467] In this invention, the server includes means for collecting personal data of users, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results, means for notifying the user terminal of the recommendation list, means for using an emotion engine to analyze the user's emotional state, and means for flexibly adjusting the recommendation list based on the analysis results. This makes it possible to provide a flexible recommendation list tailored to the user's emotions and automatically generate an efficient schedule based on the user's planned visits.

[2468] "Personal data" refers to information specific to an individual user, such as the user's behavior, interests, and impressions, and includes data from social networking services, behavioral history, and impression data.

[2469] A "generative AI model" refers to an algorithm that uses artificial intelligence technology to analyze user data and generate appropriate information or suggestions based on the results. Specific examples include natural language generation models.

[2470] An "emotion engine" refers to an algorithm that analyzes a user's emotional state from collected data, and this is achieved using emotion analysis tools and APIs.

[2471] A "recommendation list" refers to a list of places, products, etc. recommended to a user, generated based on analyzed data.

[2472] A "visit plan" refers to a plan to visit a particular location in the future that a user inputs into the application.

[2473] "Nearby spot information" refers to information about interesting places and facilities located around the place you plan to visit.

[2474] "Automatic schedule" refers to a schedule of activities that is automatically generated by an algorithm based on the user's planned visits and information about nearby spots.

[2475] "User terminal" refers to a digital device that is directly used by a user, such as a smartphone or tablet.

[2476] "Notification" refers to the act of conveying information from the system to the user, including push notifications and in-app displays.

[2477] "Analysis results" refers to the analytical conclusions and insights obtained after processing collected data using generative AI models and emotion engines.

[2478] "Flexible adjustment" refers to dynamically changing the recommendation list and suggestions depending on the user's emotions and situation.

[2479] This invention is a system that recommends optimal locations by collecting personal data of users and analyzing it with a generative AI model. It also incorporates an emotion engine that recognizes the user's emotional state and has the ability to flexibly adjust the recommendation list based on the user's emotional state.

[2480] Hardware and software used in data collection

[2481] Social media data collection

[2482] A user installs the application and connects their social media account, which allows access to the data that is collected.

[2483] The terminal acquires the user's SNS authentication information and sends it to the server.

[2484] The server uses SNS APIs (e.g., Twitter API) to collect user posts, photos, and check-in information. This data is stored in a database.

[2485] Collecting behavioral history

[2486] The user grants the application permission to use location information.

[2487] The device collects GPS data in real time and records the places you visit and the time you stay there.

[2488] The server analyzes the collected location data and stores the frequency of visits and length of stay in a database.

[2489] Collecting feedback data

[2490] Users enter their thoughts about the places they visited within the app.

[2491] The terminal transmits the input impression data to the server.

[2492] The server receives the data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), and evaluates it as positive or negative. The evaluation results are also stored in a database.

[2493] Analysis by emotion engine

[2494] The server analyzes the social media data and sentiment data, and runs an emotion engine (e.g., IBM Watson) algorithm to identify the user's emotional state. The analysis results are stored in a database.

[2495] Recommendation generation and notification

[2496] Generating a recommendation list

[2497] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[2498] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[2499] The server transmits the generated recommendation list to the user's terminal.

[2500] Recommendation list notification

[2501] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[2502] The user selects a place of interest from the displayed recommendation list.

[2503] Automatic schedule generation

[2504] Schedule a visit

[2505] Through the application, the user inputs plans to visit specific locations and schedules the visit.

[2506] The terminal transmits the set visiting schedule to the server.

[2507] Suggestions for nearby spots

[2508] The server analyzes points of interest near the planned visit location and selects suggestions.

[2509] The server sends the proposal content to the user terminal and notifies the user via push notification.

[2510] The terminal displays the suggested spots and asks the user for confirmation.

[2511] The user checks the suggested spots and selects the place they want to go.

[2512] Automatic Schedule Generation

[2513] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[2514] The server stores the generated schedule in a database and transmits it to the user terminal.

[2515] Schedule notifications and additions

[2516] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[2517] The user adds the schedule to the calendar using the options provided.

[2518] As described above, by implementing the present invention, it is possible to provide a flexible recommendation list according to the emotional state of the user and to automatically generate an efficient schedule based on the planned visits.

[2519] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2520] Step 1:

[2521] Application installation and integration settings

[2522] Users install the application on their smartphones, and then when they launch it for the first time, they link it to their social media accounts.

[2523] The terminal acquires the SNS authentication information entered by the user, generates an authentication token, and sends it to the server.

[2524] The server establishes communication with the SNS API based on the received authentication token and prepares to collect data.

[2525] Input: User's social media credentials

[2526] Output: Communication session with SNS API

[2527] Specific behavior: Attempts to connect to the SNS API and validates the token

[2528] Step 2:

[2529] Social media data collection

[2530] The server uses an SNS API (e.g., an API provided by an SNS service) to collect user posts, photos, and check-in information.

[2531] Input: SNS authentication token

[2532] Output: Posts, photos, and check-ins

[2533] Specific behavior: Requests to API endpoints and analysis of responses

[2534] Step 3:

[2535] Collecting behavioral history

[2536] The user gives permission for the application to use location information.

[2537] The device collects and records location information obtained from the GPS sensor in real time.

[2538] The terminal transmits the collected location information data to the server.

[2539] The server analyzes the received location data and stores the frequency of visits and length of stay in a database.

[2540] Input: Location data

[2541] Output: Visit frequency and duration data

[2542] Specific operation: GPS data analysis and statistical processing

[2543] Step 4:

[2544] Collecting feedback data

[2545] Users enter text within the app to share their thoughts about the places they visit.

[2546] The terminal transmits the input impression data to the server.

[2547] The server receives the opinion data, analyzes the content using a natural language processing library (e.g., NLTK or SpaCy), rates it positively or negatively, and stores the results in a database.

[2548] Input: Impression data

[2549] Output: Positive / negative rating

[2550] Specific behavior: Text data analysis and emotion evaluation

[2551] Step 5:

[2552] Emotional state analysis using emotion engine

[2553] The server analyzes the SNS data and sentiment data, and executes the algorithm of the emotion engine (e.g., API of the emotion analysis service) to identify the user's emotional state. The analysis results are stored in a database.

[2554] Input: SNS data, opinion data

[2555] Output: User's emotional state

[2556] Specific operation: Running a sentiment analysis algorithm and saving the results

[2557] Step 6:

[2558] Generating a recommendation list

[2559] The server integrates the collected social media data, behavioral history, and opinion data, and analyzes the user's sentiment and emotional state using a generative AI model (e.g., GPT-4).

[2560] The server generates a list of optimal restaurants and spots based on each user's profile. At this time, the server inputs a prompt to the AI ​​model: "The user's behavioral history and impression data indicate that they are feeling stressed. Please suggest a relaxing cafe or quiet restaurant."

[2561] The server transmits the generated recommendation list to the user's terminal.

[2562] Input: Social media data, behavioral history, impression data, prompt text

[2563] Output: Recommendation list

[2564] What it does: Combines data and runs AI models to generate a list

[2565] Step 7:

[2566] Recommendation list notification

[2567] The device notifies the user of the received recommendation list via push notification or other means and displays it within the app.

[2568] The user selects a place of interest from the displayed recommendation list.

[2569] Input: Recommendation list

[2570] Output: User's choice

[2571] Specific behavior: Displaying notifications and recording user choices

[2572] Step 8:

[2573] Schedule a visit

[2574] The user enters plans to visit specific locations in the application and schedules the visit.

[2575] The terminal transmits the set visiting schedule to the server.

[2576] Input: Visit Schedule

[2577] Output: Visit schedule data

[2578] Specific behavior: Save and send a visit appointment

[2579] Step 9:

[2580] Suggestions for nearby spots

[2581] The server analyzes points of interest near the planned visit location and selects suggestions.

[2582] The server sends the proposal content to the user terminal and notifies the user via push notification.

[2583] The terminal displays the suggested spots and asks the user for confirmation.

[2584] The user checks the suggested spots and selects the place they want to go.

[2585] Input: Visit schedule data, nearby spot information

[2586] Output: Proposal, user's choice

[2587] Specific behavior: Spot analysis and suggestion notification

[2588] Step 10:

[2589] Automatic Schedule Generation

[2590] The server automatically generates an optimal schedule based on the planned visit and the selected nearby spots.

[2591] The server stores the generated schedule in a database and transmits it to the user terminal.

[2592] Input: Planned visit, selected nearby spots

[2593] Output: Auto-generated schedule

[2594] Specific behavior: Automatically generate and save schedules

[2595] Step 11:

[2596] Schedule notifications and additions

[2597] The device notifies the user of the generated schedule and provides the option to add it to the smartphone calendar.

[2598] The user adds the generated schedule to their calendar using the options provided.

[2599] Input: Auto-generated schedule

[2600] Output: Add to calendar

[2601] Specific operation: Schedule notification and calendar update options provided

[2602] (Application example 2)

[2603] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2604] Conventional recommendation systems make recommendations based on a user's behavioral history and personal data, but because they cannot take the user's emotional state into account, it is difficult to provide highly satisfying recommendations that address the user's current psychological needs. Furthermore, existing systems automatically generate schedules based solely on the user's plans, failing to reflect the user's emotional state, resulting in incomplete plans. There is a need to solve these issues and realize optimal recommendations and automatic schedule generation that reflect the user's psychological state.

[2605] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting personal data, means for analyzing the collected personal data using a generative AI model, means for generating a recommendation list based on the analysis results and the user's emotional state, means for inputting the user's visit plans, means for acquiring information on spots near the planned visits, means for generating an automatic schedule based on the planned visits and the information on nearby spots, means for notifying the user terminal of the recommendation list and the automatic schedule, and means for adjusting the schedule based on the user's emotional state. This enables flexible and satisfying recommendations that take the user's emotional state into consideration and automatic generation of a schedule that suits the user's psychological state.

[2606] "Personal data" refers to information about individual users, including data from social networking services, behavioral history, and impression data.

[2607] A "generative AI model" refers to an algorithm or mechanism that uses artificial intelligence to analyze data and generate new information or recommendations.

[2608] The "emotional state" indicates the psychological state of the user, and includes an evaluation of emotions such as positive or negative.

[2609] A "recommendation list" refers to a list of recommended places, products, etc. for a user, which is generated based on collected and analyzed personal data and emotional state.

[2610] "User terminal" refers to a device used by a user, such as a computer, smartphone, tablet, or biometric input device.

[2611] "Visiting Plans" indicates plans such as places the user wants to visit or events the user wants to attend in the future.

[2612] "Neighborhood spot information" refers to information about spots located in the vicinity of a place that the user plans to visit.

[2613] "Automatic schedule" refers to a user's action plan that is automatically generated based on planned visits and information on nearby spots.

[2614] The "notification means" refers to a method or device for transmitting specific information to a user terminal and informing the user of that information.

[2615] "Adjustment measures" refer to methods and mechanisms for changing or modifying plans such as schedules and lists based on specific conditions.

[2616] This invention is a system that provides an optimal recommendation list and schedule by collecting personal data of a user and analyzing the data with a generative AI model. The system includes the following means.

[2617] Data collection and analysis

[2618] Social media data collection

[2619] Users install the application and connect their social media accounts, which grants them access to the data that is collected.

[2620] The device obtains the SNS authentication information and sends it to the server.

[2621] The server uses the SNS API to collect user posts, photos, and check-in information and store them in a database.

[2622] Collecting behavioral history

[2623] The user gives permission for the application to use location information.

[2624] The device collects GPS data in real time, recording the places you visit and the time you stay there.

[2625] The server receives the collected location data and analyzes the frequency of visits and the length of time spent at specific locations.

[2626] Collecting feedback data

[2627] Users enter their impressions of the places they visit within the app.

[2628] The terminal transmits the input impression data to the server.

[2629] The server receives the sentiment data, analyzes the content using natural language processing algorithms (e.g., NLTK or SpaCy), and assigns a positive or negative rating.

[2630] Analysis by emotion engine

[2631] The server analyzes the SNS data and sentiment data and runs an emotion engine to identify the user's emotional state.

[2632] The server stores the emotional states identified by the emotion engine in a database.

[2633] Recommendation generation and tuning

[2634] User data integration and analysis

[2635] The server integrates social media data, behavioral history, and opinion data to generate a profile for each user.

[2636] The server integrates the profiles of multiple users, extracts common interests, and performs analysis.

[2637] Generating a recommendation list

[2638] The server uses a generative AI model to analyze each user's sentiment and emotional state and generate a list of products and spots that are best suited for the user and their friends.

[2639] The server sends the generated recommendation list to the user's terminal and notifies the user.

[2640] Automatic schedule generation

[2641] Schedule a visit

[2642] The application allows users to input plans to visit specific locations and schedule visits.

[2643] The terminal transmits the set visit schedule to the server.

[2644] Suggestions for nearby spots

[2645] The server analyzes points of interest near the planned visit and selects suggestions.

[2646] The server transmits the proposal contents to the user terminal and notifies it.

[2647] The terminal displays the suggested spots and asks the user for confirmation.

[2648] The user checks the suggested spots and selects the place they want to go.

[2649] Automatic Schedule Generation

[2650] The server automatically generates a schedule based on the planned visit and the selected nearby spots.

[2651] The server transmits the generated schedule to the user terminal and notifies it.

[2652] The terminal notifies the user of the generated schedule so that the user can add it to a calendar, etc.

[2653] Specific examples

[2654] The user installs the application and connects their social media account. Next, they allow the use of their location information and enter their thoughts about shops they have visited in the past. If the emotion engine detects the user's current psychological state from the social media data, for example, if it determines that the user is feeling stressed, the server will prioritize recommendations of items that will help them relax.

[2655] Example prompts for generative AI models

[2656] An example of a prompt is shown below.

[2657] Recommend shopping items based on the user's emotional state.

[2658] User social media data: ["I'm busy and stressed today", "I want to try out a new gadget"]

[2659] Emotional state: Negative

[2660] User profile: {"interests": ["relaxation", "gadgets"]}

[2661] Recommendation list: ["Relaxation furniture", "Aroma candles", "Massage machine"]

[2662] By setting prompt sentences in this way, the generative AI model can provide a recommendation list that is optimal for the user's psychological state.

[2663] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2664] Step 1:

[2665] A user installs the application and links their SNS account. This linking allows the application to obtain authorization to access the user's SNS data. Once the user authorizes the linking, the device sends the SNS authentication information to the server. The input is the SNS authentication information, and the output is a request containing the authentication information.

[2666] Step 2:

[2667] The server uses SNS APIs to collect user posts, photos, and check-in information. The collected data is stored in a database. The input is user data obtained through the SNS API, and the output is personal data stored in the database.

[2668] Step 3:

[2669] The user gives permission for the application to use location information. The device collects GPS data in real time and records the places visited and the duration of stay. This data is periodically sent to the server. The input is real-ti...

Claims

1. means of collecting personal data; A means for analyzing the collected personal data using a generative AI model; and A means for generating a recommendation list based on the analysis results; A means for notifying a user terminal of the recommendation list; A system including:

2. The system according to claim 1 , wherein the personal data includes data from social networking services, behavioral history, and opinion data.

3. A means for inputting a user's visit schedule; A means for acquiring information about nearby spots to be visited; A means for generating an automatic schedule based on the visit schedule and information on nearby spots; means for notifying a user terminal of an automatic schedule; The system of claim 1 further comprising:

Images