System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an input of a destination and a schedule from a user; means for executing congestion prediction on the basis of the input destination and schedule by using a prediction model; means for generating an optimal going-out plan in consideration of a congestion prediction result; and means for presenting the generated going-out plan to the user, wherein the congestion prediction model is constructed by using a generated AI.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] In modern society, congestion and traffic jams at specific locations and times cause wasted time and effort, resulting in economic losses and psychological stress. Congestion, particularly at public transportation and tourist destinations, significantly impairs the comfort of travel and the tourist experience. To solve this problem, enable users to reach their destinations comfortably and efficiently, and provide a user experience with minimal waiting time, a system is needed that can predict congestion and provide optimal travel plans in advance. [Means for solving the problem]

[0005] This invention proposes a means for collecting people flow data, weather data, and demand forecast data from data sources, and a means for constructing a congestion prediction model using generative AI based on that data. Furthermore, it provides a means for accepting input of a user's destination and schedule, and a means for performing congestion prediction using a predictive model based on that input information. This allows the system to generate an optimal outing plan taking into account the congestion prediction results and present that plan to the user. It also includes a means for providing coupon information and special offer information, providing further convenience to users. In this way, it provides a system that prevents the waste of time and effort due to congestion and traffic jams, and ensures a comfortable user experience.

[0006] A "data source" is an information source for collecting people flow data, weather data, demand forecast data, etc., which are necessary for congestion prediction and demand prediction.

[0007] "Generative AI" is an artificial intelligence technology used to analyze collected data and build congestion prediction models.

[0008] A "congestion prediction model" is a mathematical and statistical model that predicts congestion at specific locations and time periods based on past data.

[0009] An "outing plan" is an optimal visiting schedule and related information generated based on the destination and schedule entered by the user, taking into account predicted congestion conditions.

[0010] "Coupon information" is information about discounts and special offers available at or near the location the user plans to visit.

[0011] "Special offer information" is information about additional services and conveniences that can be obtained at or near the location the user plans to visit.

[0012] "Crowding tolerance" is an index that indicates how much congestion a user can tolerate, and is an important parameter when generating an optimal outing plan.

[0013] "People flow data" refers to data on the flow of people observed in a specific area or facility over a certain period of time.

[0014] "Weather data" refers to information about the weather within a prediction period, and is data used as part of a congestion prediction model.

[0015] "Demand forecast data" is data for predicting the number of visitors or users during a specific period or event.

[0016] "User interface" refers to the screen or device through which a user inputs destinations and schedules into the system. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] The present invention relates to a system that predicts congestion and provides optimal outing plans, in which a server, a terminal, and a user operate in cooperation with each other. Specific embodiments of the system will be described below.

[0039] Server Processing

[0040] Data collection

[0041] The server collects multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[0042] Data processing and predictive model building

[0043] The server cleans the collected data, removing noise and missing values. It then extracts useful features and uses generative AI to build a congestion prediction model. This model can predict congestion in specific areas or facilities with high accuracy.

[0044] Processing user requests

[0045] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[0046] Generating an optimal plan

[0047] The server generates an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[0048] Sending a response

[0049] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[0050] Terminal handling

[0051] User Interface Display

[0052] The device provides an interface for users to input their destinations and schedules, and must be designed to be intuitive so that users can easily operate it.

[0053] Sending input data

[0054] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0055] Receiving and Viewing Plans

[0056] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0057] User Action

[0058] Enter your destination and schedule

[0059] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0060] Confirmation of proposed plan

[0061] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0062] Local use

[0063] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0064] Specific examples

[0065] As an example, consider the case where a user wants to visit the zoo next weekend. The user uses the device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, where the user can confirm it, make plans, and visit the zoo. Once at the zoo, the user can enjoy a comfortable stay and take a break at the cafe using the coupon.

[0066] The above is a specific embodiment of the present invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[0067] The processing flow will be explained below.

[0068] Step 1: Data collection

[0069] Server Processing

[0070] The server collects the necessary data from multiple data sources: people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. This data is then stored in a database on the server.

[0071] Step 2: Cleaning the data

[0072] Server Processing

[0073] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[0074] Step 3: Feature extraction

[0075] Server Processing

[0076] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[0077] Step 4: Building a congestion prediction model

[0078] Server Processing

[0079] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[0080] Step 5: Displaying the User Interface

[0081] Terminal handling

[0082] The terminal provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[0083] Step 6: Enter your destination and schedule

[0084] User Action

[0085] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[0086] Step 7: Submitting input data

[0087] Terminal handling

[0088] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0089] Step 8: Parsing the Request

[0090] Server Processing

[0091] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[0092] Step 9: Run congestion forecast

[0093] Server Processing

[0094] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[0095] Step 10: Generate optimal plan

[0096] Server Processing

[0097] The server generates an optimal outing plan for the user based on the congestion prediction results, which includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[0098] Step 11: Sending the Response

[0099] Server Processing

[0100] The server transmits the generated outing plan to the user's terminal.

[0101] Step 12: Receive and view your plan

[0102] Terminal handling

[0103] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0104] Step 13: Review the proposed plan

[0105] User Action

[0106] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0107] Step 14: Travel to your destination

[0108] User Action

[0109] The user follows the proposed plan and adjusts the timing to head to the destination.

[0110] Step 15: Local use

[0111] User Action

[0112] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[0113] The above are the specific processing steps of this invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[0114] Example 1

[0115] 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."

[0116] In recent years, increasing congestion at tourist destinations and commercial facilities has made it difficult for visitors to plan appropriate visit times and itineraries to ensure a comfortable stay. Accurate congestion predictions based on real-time changing environmental conditions and people flow data are also required, but current systems are unable to adequately address this. Furthermore, there are insufficient means to provide users with optimal visitor plans to avoid crowds, and specific suggestions for improving user satisfaction are lacking.

[0117] 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.

[0118] In this invention, the server includes: means for collecting people flow data, weather data, and demand forecast data from data sources; means for processing the collected data with a data cleaning tool to remove noise and missing values; and means for extracting effective features from the processed data and constructing a congestion prediction model using a generative AI model. This enables accurate congestion prediction in real time. The server also includes means for accepting input of a destination and schedule from a user via a terminal; means for using a prediction model to perform congestion prediction based on the input destination and schedule; means for generating an optimal outing plan based on the congestion prediction results, including recommended visit time, predicted stay time, congestion information, and coupon information; and means for transmitting and presenting the generated outing plan to the user's terminal. This allows users to plan their visit optimally and enjoy a comfortable visit experience. Furthermore, by further including means for providing coupon information and special offer information to the user, user satisfaction can be further improved. Furthermore, by including means for adjusting congestion tolerance based on the destination and schedule input by the user, it is possible to provide more personalized and optimal outing plans.

[0119] A "data source" is an information source that provides information such as people flow data, weather data, and demand forecast data.

[0120] "People flow data" refers to information about people's movements and stays in specific areas or facilities.

[0121] "Weather data" refers to data that includes meteorological information such as temperature, precipitation, and wind speed.

[0122] "Demand forecast data" is data used to predict the number of visitors and consumption behavior in a specific area or facility.

[0123] A "data cleaning tool" is software or algorithms used to remove noise and missing values ​​from collected data.

[0124] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and makes predictions and generates results. Examples include GPT-4.

[0125] A "congestion prediction model" is a model for predicting congestion conditions at specific locations and times based on people flow data and environmental data.

[0126] A "terminal" is a device that allows a user to input information or receive information from the system. Examples include smartphones and personal computers.

[0127] A "destination" refers to a place or facility that a user wishes to visit.

[0128] "Schedule" refers to the date and time when the user intends to visit.

[0129] "Recommended Visit Time" refers to the optimal time of day for a visit suggested by the system to avoid overcrowding.

[0130] "Predicted stay time" refers to the time the system predicts the user will stay at a destination.

[0131] "Coupon information" refers to information that allows users to receive discounts or benefits at specific locations or services.

[0132] "Special offer information" refers to special offer information other than discounts that users can receive.

[0133] "Congestion tolerance" refers to a standard indicating how much congestion a user can tolerate.

[0134] This invention relates to a system that predicts congestion and provides optimal outing plans, in which the elements of a server, a terminal, and a user work in cooperation with each other.

[0135] Server Processing

[0136] The server functions by collecting data from the internet and specific data providers. Specifically, it uses APIs to continuously obtain people flow data, weather data, and demand forecast data. A database is used to manage the data. This makes it possible to grasp congestion conditions and weather fluctuations in real time. Examples of APIs that can be used include Google API and Weather API.

[0137] The server uses a data cleaning tool (e.g., Pandas) to remove noise and missing values ​​from the collected data. Next, it uses a machine learning library (e.g., scikit-learn) to extract useful features. Based on this data, it uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. This predictive model can predict the congestion situation in specific areas or facilities with high accuracy.

[0138] The server receives destination and schedule information entered by the user through the device. The received information is converted into a prompt to be input into the generative AI model. For example, if a user enters "zoo" and "next Sunday at 10:00 AM," the prompt will be in the format "Please predict the crowding situation at the zoo at 10:00 AM next Sunday."

[0139] Based on this, the server uses a prediction model to predict congestion and generate an optimal outing plan including recommended visit times, predicted stay times, congestion information, and coupon information. This plan is sent to the user's device as an API response.

[0140] Terminal handling

[0141] The terminal provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. The input data is validated using a consistency check tool (e.g., regular expressions). The validated data is then sent to the server as an API request.

[0142] Once the optimal plan sent from the server is received by the terminal, it is displayed in a user-friendly format, including visit times, travel times, congestion information, coupon details, and more.

[0143] User Action

[0144] Users input their destination and desired date and time of visit through the device interface. Next, they check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. They then head to their destination according to the plan and enjoy a comfortable visit experience by using coupons and special offers offered on site.

[0145] Specific examples

[0146] For example, if a user plans to visit the zoo next weekend, they use their device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server. The server uses a crowd prediction model (GPT-4) based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, where the user confirms it, makes plans, and visits the zoo. Once there, they make themselves comfortable and use the coupon to take a break at the cafe.

[0147] This allows users to plan their trips efficiently, avoiding crowds and traffic jams, and reducing financial losses and psychological burdens.

[0148] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0149] Server Processing

[0150] Step 1: Data collection

[0151] The server collects people flow data, weather data, and demand forecast data from each data source. Specifically, it obtains these data from the Internet using APIs. For example, it collects people flow data from Google API and weather data from Weather API. The input is raw data obtained from the data source, and the output is the initial data stored in the database.

[0152] Step 2: Data cleaning

[0153] The server performs data cleaning on the collected data. Specifically, it uses a data cleaning tool (e.g., Pandas) to remove noise and missing values. The input is the initial data stored in the database, and the output is the cleaned data.

[0154] Step 3: Feature extraction

[0155] The server extracts useful features from the cleaned data. It uses a machine learning library (e.g., scikit-learn) to select features and prepares the data required for prediction. The input is the cleaned data, and the output is a dataset with extracted features.

[0156] Step 4: Building a predictive model

[0157] The server uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. It trains the model based on the extracted features and saves the trained model. The input is the dataset from which the features have been extracted, and the output is the trained prediction model.

[0158] Step 5: Processing User Requests

[0159] The server receives the destination and schedule information sent from the user's device and converts the received information into a prompt format for input to the generative AI model. The input is the request data from the user, and the output is data in the prompt format.

[0160] Step 6: Run congestion forecast

[0161] The server inputs prompts into the prediction model to predict congestion. The generative AI model obtains the prediction results and derives recommended visit times and congestion information. The input is prompt-format data, and the output is the congestion prediction results.

[0162] Step 7: Generate an optimal plan

[0163] The server generates an optimal outing plan based on the prediction results. This plan includes recommended visit times, predicted stay times, congestion information, and coupon information. The input is the congestion prediction results, and the output is the optimal plan.

[0164] Step 8: Submit your plan

[0165] The server sends the generated optimal plan to the user's device as an API response. The input is the optimal plan, and the output is the plan sent to the user's device.

[0166] Terminal handling

[0167] Step 1: Displaying the User Interface

[0168] The device displays an interface for users to input their destination and schedule. Specifically, it provides an intuitive UI (user interface) that includes an input form. The input is the destination and schedule information entered by the user, and the output is the input form displayed on the screen.

[0169] Step 2: Submitting input data

[0170] The terminal checks the consistency of the destination and schedule information entered by the user before sending it to the server. A consistency check tool (e.g., regular expressions) is used. The input is the destination and schedule information entered by the user, and the output is the data sent to the server.

[0171] Step 3: Receive and view your plan

[0172] The terminal receives the optimal plan sent from the server and displays it to the user. Specifically, it displays an interface that includes visit time, required time, congestion information, and coupon information. The input is the optimal plan sent from the server, and the output is the plan displayed to the user.

[0173] User Action

[0174] Step 1: Enter your destination and schedule

[0175] The user inputs the destination and date / time they wish to visit through the terminal interface. The input is the destination and the date / time they wish to visit, and the output is the data entered into the terminal.

[0176] Step 2: Confirm the proposed plan

[0177] The user checks the optimal plan displayed on the terminal and makes a plan based on the recommended visit time and coupon information. The input is the optimal plan displayed on the terminal, and the output is the plan confirmed by the user.

[0178] Step 3: Local use

[0179] The user heads to the destination according to the plan, uses the provided coupons and special offers, and enjoys a pleasant visiting experience. The input is the optimal plan, and the output is the actual visiting experience.

[0180] (Application example 1)

[0181] 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."

[0182] In recent years, congestion in urban areas and tourist destinations has become a problem, creating a need for ways to ensure visitors can spend their time comfortably. Physical stores and tourist facilities also need to provide information to encourage visits while avoiding customer concentration. Conventional technologies are often ineffective for users, as they are unable to adequately predict congestion or suggest optimal visit times. Furthermore, coupons and special offer information are often provided individually, making centralized management difficult. A new system is needed to solve these issues.

[0183] 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.

[0184] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for using a generation AI to build a congestion prediction model based on the collected data, means for accepting input of a destination and schedule from a user, means for using the prediction model to perform congestion prediction based on the input destination and schedule, means for generating an optimal outing plan taking into account the congestion prediction results, means for presenting the generated outing plan to the user, and means for notifying the user of visiting times and special offer information. This allows the user to visit destinations efficiently while avoiding crowds, and at the same time allows the user to use centrally managed coupons and special offer information.

[0185] A "data source" is a source of data from which the system obtains information. Specifically, this includes data such as people flow data, weather data, and demand forecast data.

[0186] "People flow data" is information recorded on the movements and stays of people in specific areas or facilities. This information can be used to predict congestion situations.

[0187] "Weather Data" means information about weather fluctuations, including temperature, precipitation, wind speed, etc.

[0188] "Demand forecast data" is statistical information used to predict future demand. This includes past sales data and event information.

[0189] "Generative AI" refers to algorithms that use artificial intelligence techniques to achieve specific goals. In this case, it is used to build congestion prediction models.

[0190] A "congestion prediction model" is a model that predicts future congestion conditions in specific areas or facilities based on people flow data, weather data, and demand forecast data.

[0191] A "destination" is a place or facility that the user wishes to visit.

[0192] "Schedule" is information about the date and time when the user plans to visit.

[0193] An "outing plan" is a plan created by a user based on the congestion prediction results, taking into consideration the optimal visiting time and special offer information.

[0194] "Visiting time" refers to the optimal time for a user to visit a destination.

[0195] "Special offer information" is information such as discounts and coupons available at the destination and its surrounding areas.

[0196] "Presenting" refers to the act of displaying the generated outing plan and benefit information to the user.

[0197] "Notification" is the act of conveying important information such as visiting times and special offers to users in real time.

[0198] The present invention relates to a system that predicts congestion and provides optimal outing plans, and is a system in which the elements of a server, a terminal, and a user work in cooperation with each other.

[0199] Server Processing

[0200] Data collection

[0201] The server has the means to collect multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[0202] Data processing and predictive model building

[0203] The server cleans the collected data, removing noise and missing values. Based on the collected data, a congestion prediction model is built using generative AI. This model can predict congestion situations in specific areas or facilities with high accuracy. Specifically, this includes data preprocessing using Python and processes related to the training and prediction of the generative AI model.

[0204] Processing user requests

[0205] The server receives destination and schedule information entered by the user through their device. The server analyzes this information and inputs it into a predictive model to predict congestion at the time of the planned visit. This involves retrieving data using various APIs and processing the database.

[0206] Generate and present optimal plans

[0207] The server has a means to generate an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupon and special offer information. The generated outing plan is sent to the application to be presented to the user. Python, Flask / Django, etc. are used to generate the specific plan.

[0208] Terminal handling

[0209] User Interface Display

[0210] The device has a means to provide an interface for users to input their destinations and schedules. An intuitive design is required to make it easy for users to operate. A smartphone application is an example of this.

[0211] Sending input data

[0212] The device sends the destination and schedule data entered by the user to the server, which checks the data for consistency and prompts the user to make corrections if necessary. The transmission involves an internet connection and an API call.

[0213] Receiving and Viewing Plans

[0214] The device receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons, and special offers. The actual display is done on the smartphone screen.

[0215] User Action

[0216] Enter your destination and schedule

[0217] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0218] Confirmation of proposed plan

[0219] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0220] Local use

[0221] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0222] Specific examples

[0223] As an example, let's consider the case where a user plans to visit a shopping mall next weekend. The user uses a device to input "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended time to visit and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is sent to the device, and the user confirms it, makes plans, and visits the shopping mall. Once there, the user can enjoy a comfortable stay and take a break at the cafe using the coupon.

[0224] Prompt Sentence Examples

[0225] Below is an example of a prompt when a user plans to visit a shopping mall:

[0226] "Generate an outing plan that includes the optimal visit time and coupon information based on the user's input data in the following format. For example, the physical store the user wants to visit is a "shopping mall," and the planned date is "November 5, 2023, 10:00 AM."

[0227] The above is a specific embodiment of the present invention. This system allows users to avoid crowds and make efficient outing plans, thereby reducing economic losses and psychological burdens.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] The server continuously collects people flow data, weather data, and demand forecast data from data sources. Specifically, the server accesses the Internet or specific data provider services and sends API requests to obtain the latest data. This data is stored in a database on the server. The input is information from the data source, and the output is the collected data.

[0231] Step 2:

[0232] The server cleans the collected data and removes noise and missing values. Specifically, it preprocesses the data using Python libraries (e.g., pandas, numpy). The clean dataset obtained in this way is used to extract useful features. The input is the collected data, and the output is the cleaned data.

[0233] Step 3:

[0234] The server uses generative AI to build a congestion prediction model based on the cleaned data. Specifically, it trains the model using a machine learning library (e.g., TensorFlow, Scikit-learn). The trained model is stored in a database and used for prediction processing. The input is the cleaned data, and the output is the congestion prediction model.

[0235] Step 4:

[0236] The user inputs the destination and the planned date and time of the visit using a terminal (such as a smartphone). The terminal provides an intuitive user interface and sends the input data to the server. The input is the destination and schedule entered by the user, and the output is the data sent to the server.

[0237] Step 5:

[0238] The server inputs the destination and schedule information received from the user into a prediction model to predict the congestion situation at the time of the planned visit. The server analyzes the prediction results and generates an optimal outing plan including recommended visit times and congestion information. The input is the user's destination and schedule, and the output is the generated outing plan.

[0239] Step 6:

[0240] The server sends the generated outing plan to the device. This includes the planned visit time, estimated stay time, congestion information, coupon and special offer information. The server converts the data into an appropriate format and sends it to the device using an API. The input is the generated outing plan, and the output is the transmitted data.

[0241] Step 7:

[0242] The terminal receives the outing plan sent from the server and displays it to the user. The user checks the plan and makes a plan based on the optimal visiting time and coupon information. The input is the outing plan sent from the server, and the output is the information displayed to the user.

[0243] Step 8:

[0244] The user follows the plan to reach the destination and uses the coupons and special offers provided. The user enjoys a pleasant visiting experience at the destination. The input is the user's action plan, and the output is the visiting experience.

[0245] 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.

[0246] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide a customized plan tailored to the user's emotional state. Specific embodiments of this system are described below.

[0247] Server Processing

[0248] Data collection

[0249] The server collects multiple types of data from data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data on users' emotional states. This data is stored in a database on the server.

[0250] Cleaning the data

[0251] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[0252] Feature extraction

[0253] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[0254] Building a congestion prediction model

[0255] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[0256] Processing user requests

[0257] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[0258] Use of emotion engine

[0259] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history, which can include stress, relaxation, excitement, etc.

[0260] Generating an optimal plan

[0261] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. By taking the results of the emotion engine into consideration, it is possible to propose a plan that avoids crowds to a user who is easily stressed, or a plan that includes event information to a user who wants to get excited.

[0262] Sending a response

[0263] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[0264] Terminal handling

[0265] User Interface Display

[0266] The terminal provides an interface for users to input their destination and schedule, and an intuitive design is required to make it easy for users to operate.

[0267] Sending input data

[0268] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0269] Receiving and Viewing Plans

[0270] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0271] User Action

[0272] Enter your destination and schedule

[0273] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0274] Confirmation of proposed plan

[0275] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0276] Local use

[0277] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0278] Specific examples

[0279] As an example, consider a user planning to visit the zoo next weekend. The user uses their device to input "zoo" and "next Sunday at 10 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state, suggesting 9:30 AM as the recommended visit time if the user is prone to stress, and generates an optimal plan that includes a 10% discount coupon for a cafe near the zoo. This plan is then sent to the device, where the user can confirm it, make plans, and visit the zoo. Once there, they can relax comfortably and take a break at the cafe using the coupon.

[0280] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[0281] The processing flow will be explained below.

[0282] Step 1: Data collection

[0283] Server Processing

[0284] The server collects the necessary data from multiple data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data to analyze the user's emotional state. This data is stored in a database on the server.

[0285] Step 2: Cleaning the data

[0286] Server Processing

[0287] The server removes noise and missing values ​​from the collected data, detects and removes outliers, and performs other preprocessing such as filling in missing data to improve the quality of the data.

[0288] Step 3: Feature extraction

[0289] Server Processing

[0290] The server extracts features from the cleaned data that are effective for predicting congestion, such as the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[0291] Step 4: Building a congestion prediction model

[0292] Server Processing

[0293] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[0294] Step 5: Displaying the User Interface

[0295] Terminal handling

[0296] The device provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[0297] Step 6: Enter your destination and schedule

[0298] User Action

[0299] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[0300] Step 7: Submitting input data

[0301] Terminal handling

[0302] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0303] Step 8: Parsing the Request

[0304] Server Processing

[0305] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[0306] Step 9: Use the Emotion Engine

[0307] Server Processing

[0308] The server uses an emotion engine to analyze the user's emotional state, determining their current emotional state (e.g., stressed, relaxed, excited) based on the data they input, their past usage history, and their real-time reaction data.

[0309] Step 10: Run congestion forecast

[0310] Server Processing

[0311] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[0312] Step 11: Generate optimal plan

[0313] Server Processing

[0314] The server generates optimal outing plans for users based on the congestion prediction results and the analysis results of the emotion engine. For example, it generates a plan that avoids crowds for users who are easily stressed, and a plan that includes event information for users who want to get excited.

[0315] Step 12: Add coupons and special offers

[0316] Server Processing

[0317] The server adds coupon information and special offer information to the generated plan. Coupons include discount information that can be used at affiliated stores and services.

[0318] Step 13: Sending the Response

[0319] Server Processing

[0320] The server transmits the generated outing plan to the user's terminal.

[0321] Step 14: Receive and view your plan

[0322] Terminal handling

[0323] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0324] Step 15: Review the proposed plan

[0325] User Action

[0326] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0327] Step 16: Travel to your destination

[0328] User Action

[0329] The user follows the proposed plan and adjusts the timing to head to the destination.

[0330] Step 17: Local use

[0331] User Action

[0332] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[0333] The above are the specific processing steps of this invention. This system allows users to make efficient outing plans that avoid crowds and traffic jams, and furthermore, it is possible to reduce economic losses and psychological burdens by customizing plans based on emotional states.

[0334] Example 2

[0335] 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."

[0336] Conventional congestion prediction and outing plan provision systems provide uniform plans without considering the user's emotional state, making it difficult to alleviate the stress and dissatisfaction felt by users. In addition, many systems collect only a limited number of data types, resulting in low congestion prediction accuracy and making it impossible to respond to the diverse needs of users.

[0337] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting movement data, weather data, and demand forecast data from data sources, means for constructing a congestion prediction model using a generative AI model based on the collected data, means for accepting input of a destination and schedule from a user, means for using an emotion engine to analyze the user's emotional state, means for generating an optimal outing plan taking into account the congestion prediction result and the analysis result of the emotion engine, and means for presenting the generated outing plan to the user. This provides an outing plan customized according to the user's emotional state, enabling a more comfortable and satisfying visiting experience.

[0338] "Data Source" means the information source used to provide travel data, weather data, and demand forecast data.

[0339] "Movement data" is information about the movement of people and things obtained from sensors, cameras, and people flow data measurement devices.

[0340] "Weather data" is information about the weather obtained from a weather forecast service.

[0341] "Demand forecast data" refers to forecast information on demand collected through search engines and social media APIs.

[0342] A "generative AI model" is a model that is generated using artificial intelligence technology and performs predictions and analyses for specific purposes.

[0343] A "congestion prediction model" is a model that uses past data to predict congestion levels at specific locations and time periods.

[0344] An "emotion engine" is a system or algorithm for analyzing a user's emotional state from their input data and past usage history.

[0345] The "optimal outing plan" is a visit plan that is optimal for the user, generated by taking into account the congestion prediction results and the analysis results of the emotion engine.

[0346] "Coupon information" is information that provides discounts on specific services or products.

[0347] "Special offer information" is information other than coupon information about additional services or product offers.

[0348] "Congestion tolerance" is an index that indicates how much congestion a user can tolerate or tolerate at a destination.

[0349] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide customized plans that correspond to the user's emotional state.

[0350] Server Processing

[0351] Data collection

[0352] The server collects movement data, weather data, and demand forecast data from data sources. Specifically, it collects movement data from sensors, cameras, and people flow data measurement devices, obtains weather data using weather forecast service APIs, and collects demand forecast data from search engines and social media APIs. The collected data is stored in the server's database.

[0353] Cleaning the data

[0354] The server detects and removes noise and outliers from the collected data, such as abnormally high values ​​and invalid timestamps. It also improves data quality by imputing missing values ​​using past data or imputation techniques.

[0355] Feature extraction

[0356] The server extracts features from the cleaned data that are effective for predicting congestion. Specifically, it learns user behavior patterns and congestion characteristics by combining factors such as day of the week, time of day, weather, and event information.

[0357] Building a congestion prediction model

[0358] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict future congestion situations with high accuracy.

[0359] Processing user requests

[0360] The server receives destination and schedule information entered by the user from the terminal, and inputs this information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time.

[0361] Use of emotion engine

[0362] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. For example, it determines whether the user is feeling stressed based on their recent social media posts and history.

[0363] Generating an optimal plan

[0364] The server generates an optimal outing plan for the user based on the congestion prediction results and the emotion engine's analysis results. The plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers. For example, for a user who is prone to stress, a plan is proposed that includes visit times that avoid crowds and relaxing spots.

[0365] Sending a response

[0366] The server transmits the generated outing plan to the terminal and presents it to the user.

[0367] Terminal handling

[0368] User Interface Display

[0369] The terminal provides an interface for users to input their destination and schedule, and the interface is designed to be intuitive and easy to operate.

[0370] Sending input data

[0371] The device sends the destination and schedule data entered by the user to the server, which checks the format and consistency of the data and prompts the user to make corrections if necessary.

[0372] Receiving and Viewing Plans

[0373] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes recommended visit times, travel time, congestion information, and details of coupons and special offers.

[0374] User Action

[0375] Enter your destination and schedule

[0376] The user uses the device's interface to input the desired destination and date and time, such as "the zoo" or "next Sunday at 10:00 AM."

[0377] Confirmation of proposed plan

[0378] The user can check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. For example, they can check a plan to visit the zoo at 9:30 in the morning and use a discount coupon at the cafe.

[0379] Local use

[0380] Users can go to their destination as planned and enjoy a pleasant visit experience by using the coupons and offers provided, for example, visiting the zoo at a less crowded time and relaxing at a cafe using coupons.

[0381] Specific examples

[0382] Example input

[0383] For example, if a user wants to visit the zoo next weekend, the user types:

[0384] "The Zoo" "Next Sunday at 10 AM"

[0385] Processing flow

[0386] 1. The terminal sends the user's input data to the server.

[0387] 2. The server uses the congestion prediction model to predict the congestion situation at 10:00 AM on the following Sunday.

[0388] 3. The server uses an emotion engine to analyze the user's emotional state.

[0389] 4. If the user is prone to stress, the server generates an optimal plan with a recommended visit time of 9:30 AM and a 10% discount coupon for a cafe near the zoo.

[0390] 5. The plan is sent to the device and presented to the user.

[0391] Actual use

[0392] Users can check the proposed plan on their device, visit the zoo, avoid crowds, spend the day comfortably, and take a break at the cafe using coupons.

[0393] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Step 1: Data collection

[0396] The server collects movement data, weather data, and demand forecast data. Specifically, it obtains movement data from sensors, cameras, and people flow data measurement devices, obtains weather data from weather forecast services using APIs, and collects demand forecast data from search engines and social media APIs. It receives various data from data sources as input and stores it in the server's database as output.

[0397] Step 2: Cleaning the data

[0398] The server detects and removes noise and outliers from the collected data. Specifically, it removes abnormally high values ​​and invalid timestamps from the data. Missing values ​​are imputed using past data or imputation techniques. It receives the collected data as input and generates cleaned data as output.

[0399] Step 3: Feature extraction

[0400] The server extracts features from the cleaned data that are effective for crowd prediction. Specifically, it combines factors such as the day of the week, time of day, weather, and event information. It receives the cleaned data as input and generates feature data as output to be input into the crowd prediction model.

[0401] Step 4: Building a congestion prediction model

[0402] The server uses a generative AI model to build a congestion prediction model based on the extracted features. Specifically, it learns from past data and generates a model that can predict future congestion situations. It receives feature data as input and generates a completed congestion prediction model as output.

[0403] Step 5: Receiving a user request

[0404] The server receives the destination and schedule information entered by the user from the terminal. The information entered by the user into the terminal (e.g., "Zoo" and "Next Sunday at 10:00 AM") is received as input data, and this information is input into the congestion prediction model as output.

[0405] Step 6: Run congestion forecast

[0406] The server inputs the received destination and schedule information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time. The server receives the user's destination and schedule information as input and generates a congestion prediction result as output.

[0407] Step 7: Emotion Engine Analysis

[0408] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. It receives the user's historical data and current data as input and generates the emotion analysis results as output.

[0409] Step 8: Generate an optimal plan

[0410] The server generates an optimal outing plan for the user based on the congestion prediction results and the analysis results of the emotion engine. Specifically, it creates a plan that includes recommended visit times, predicted stay times, congestion information, coupons and special offers. It receives the congestion prediction results and emotion analysis results as input and generates the optimal outing plan as output.

[0411] Step 9: Submit your plan

[0412] The server receives the generated outing plan as input and sends the plan to the terminal as output.

[0413] Step 10: User confirms plan

[0414] The terminal receives the optimal plan sent from the server and displays it to the user. The user checks the suggested visit time and coupon information and makes a plan. The terminal receives plan data from the server as input and displays it to the user as output.

[0415] Step 11: Execute the plan

[0416] The user visits the destination based on the proposed optimal plan. For example, the user visits the zoo at 9:30 in the morning and uses a discount coupon at the cafe. By following the plan as input, the user enjoys a pleasant visiting experience, and by output, the user gets a satisfying experience.

[0417] These are the specific processing steps of this program. At each step, specific data processing and calculations are performed based on the input data, and output is obtained according to the purpose. This allows users to enjoy customized outing plans that avoid crowds and stress.

[0418] (Application example 2)

[0419] 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."

[0420] In modern urban areas and commercial facilities, crowds frequently occur, causing stress and inconvenience to visitors. Furthermore, visitors' emotional state significantly affects the comfort and satisfaction of their visit. However, conventional crowd prediction systems do not take visitors' emotional state into account, making it difficult to provide optimal outing plans. As a result, situations in which visitors feel stressed are often unavoidable. Therefore, the present invention aims to provide a system that combines crowd prediction and visitors' emotional state to provide optimal visit plans for each individual.

[0421] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0422] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for building a congestion prediction model using a generation AI based on the collected data, means for accepting input of a destination and schedule from a user, means for performing congestion prediction based on the input destination and schedule using the prediction model, means for generating an optimal outing plan taking into account the congestion prediction results and the results of user emotion analysis, means for presenting the generated outing plan to the user, means for providing coupon information and special offer information to the user, means for adjusting the congestion tolerance level according to the destination and schedule input by the user, means for analyzing the user's real-time emotional state, and means for capturing the user's emotional state using a camera in smart glasses or a smartphone. This enables the generation of an optimal outing plan based on the congestion prediction results and the results of user emotion analysis.

[0423] A "data source" is a source of data obtained from various sensors and information sources on the Internet.

[0424] "People flow data" is data that shows the movement and stay patterns of people in specific areas or facilities.

[0425] "Weather data" refers to data related to weather, such as temperature, precipitation, and wind speed, obtained from weather information services.

[0426] "Demand forecast data" is data that shows predicted numbers of visitors at a certain location or time period using search engine or social media APIs, etc.

[0427] "Generative AI" is artificial intelligence that uses machine learning and deep learning techniques to analyze data and generate predictive models and plans.

[0428] A "congestion prediction model" is an algorithm or statistical model that uses past data to predict congestion at specific locations and times of day.

[0429] "User emotion analysis" is the process of analyzing a user's emotional state, such as stress, relaxation, or excitement, based on their facial expressions and behavioral data.

[0430] An "outing plan" is a visiting plan that includes the optimal visiting time, required time, route, benefit information, etc. for the user's visiting destinations.

[0431] "Coupon information" is information about discount coupons and service coupons that can be used at specific stores or facilities.

[0432] "Benefit information" is information that provides additional benefits to users, and includes coupons, gifts, and the like.

[0433] "Smart glasses" are wearable devices that have built-in cameras and displays and can acquire and display information in real time.

[0434] A "smartphone" is a mobile device that has mobile phone functions and can connect to the Internet and use applications.

[0435] The "emotional state" indicates the emotion the user is currently feeling, such as stress, relaxation, excitement, etc.

[0436] "Capture" means using a camera or sensor to capture a user's facial expressions and actions as images or video.

[0437] MODE FOR CARRYING OUT THE INVENTION

[0438] This invention relates to a system that predicts congestion and provides an optimal outing plan based on the user's emotional state. This system includes means for collecting various data from data sources, building a congestion prediction model, accepting input of destinations and schedules from users, analyzing their emotions, and generating and presenting an optimal plan.

[0439] Server Processing

[0440] Data collection

[0441] The server collects people flow data, weather data, and demand forecast data from various sensors and online data sources. Specifically, this includes people flow data obtained from sensors and cameras, weather data obtained from weather forecast service APIs, and demand forecast data obtained via search engine and social media APIs. It also collects data on users' emotional states.

[0442] Data cleaning and preprocessing

[0443] The server performs cleaning processes on the collected data to remove noise and missing values. This process includes detecting and removing outliers and filling in missing data. Appropriate preprocessing is performed to improve the quality of the data. This process uses Python's pandas library, etc.

[0444] Feature extraction

[0445] The server extracts features from the cleaned data that are effective for predicting congestion. For example, information such as the day of the week, time of day, weather, and event information is extracted and used for subsequent training of the predictive model. Generative AI (machine learning and deep learning techniques) is used at this stage.

[0446] Building a congestion prediction model

[0447] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and time periods. Libraries such as TensorFlow and scikit-learn are used.

[0448] Use of emotion engine

[0449] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history. Emotional states include stress, relaxation, excitement, etc. Emotion analysis utilizes face recognition and facial expression analysis technologies using OpenCV and TensorFlow.

[0450] Generating an optimal plan

[0451] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information, etc. By taking into account the results of the emotion engine, it is possible to propose plans that avoid crowds to users who are easily stressed, and plans that include event information to users who want to get excited.

[0452] Terminal handling

[0453] User Interface Display

[0454] The device provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. A smartphone app or smart glasses interface is used.

[0455] Sending input data

[0456] The device sends the destination and schedule data entered by the user to the server. At this time, the data is checked for consistency and the user is prompted to make corrections if necessary. Data transmission uses the HTTP protocol and RESTful API.

[0457] Receiving and Viewing Plans

[0458] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0459] User Action

[0460] Enter your destination and schedule

[0461] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0462] Confirmation of proposed plan

[0463] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0464] Local use

[0465] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0466] Specific examples

[0467] For example, consider a user planning to visit a shopping mall next weekend. Using their smartphone, the user inputs "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to a server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state. If the user is prone to stress, the system suggests 9:30 AM as the recommended time to visit, and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is then sent to the device, where the user can review it and plan their visit.

[0468] This invention allows users to be free from crowds and stress and enjoy plans customized to their emotional state. An example of a specific prompt is, "Please create a program that generates the optimal outing plan based on the user's destinations, visiting times, and detected emotional data."

[0469] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0470] Step 1: Collect data

[0471] The server collects people flow data, weather data, and demand forecast data from data sources. Inputs include various sensors and cameras, weather forecast service APIs, search engines, and social media APIs. These data are stored in a database on the server. To use this data for analysis, a data collection process is executed, and the collected data is obtained as output.

[0472] Step 2: Clean and preprocess the data

[0473] The server performs cleaning processing to remove noise and missing values ​​from the data collected in step 1. This includes detecting and removing outliers and completing missing data. Specifically, it uses the Python pandas library to shape and improve the quality of the data. The input is the collected data, and the output is cleaned, high-quality data.

[0474] Step 3: Feature extraction

[0475] The server extracts features from the cleaned data that are effective for predicting congestion. These include the day of the week, time of day, weather, and event information. This uses generative AI to select important features. The input is the cleaned data, and the output is the extracted features. These features are then used for model training.

[0476] Step 4: Building a congestion prediction model

[0477] The server builds a congestion prediction model using the features extracted in step 3. In this process, a generative AI model (using TensorFlow, scikit-learn, etc.) is trained to create a model that can predict congestion at specific locations and time periods based on past data. The input is feature data, and the output is a congestion prediction model.

[0478] Step 5: User sentiment analysis

[0479] The server and device capture the user's real-time emotional state using the smart glasses or smartphone camera. The device captures the user's facial expressions and analyzes them using an emotion engine (using OpenCV and TensorFlow). The input to this process is real-time image data, and the output is the user's emotional state. The analysis results are sent to the server.

[0480] Step 6: Accepting input from the user

[0481] The terminal provides an interface for users to input the destinations and visit times they plan to visit. The input is the destination and schedule data entered by the user through the terminal, which is checked for consistency and sent to the server. The output is the input data sent to the server.

[0482] Step 7: Run congestion forecast

[0483] The server uses the congestion prediction model to predict the congestion status at the destination and visiting time based on the input data received in step 6. The input is the target destination and schedule data, and the output is the predicted congestion status.

[0484] Step 8: Generate an optimal plan

[0485] The server generates an optimal outing plan taking into account the results of crowd prediction and sentiment analysis. The plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. The inputs are the crowd prediction results and sentiment analysis results, and the output is an optimal outing plan.

[0486] Step 9: Present your plan

[0487] The terminal presents the optimal plan sent from the server to the user. The input received by the terminal is the generated outing plan, and the output is the plan displayed to the user, allowing the user to check and refer to the plan.

[0488] Step 10: Local use

[0489] The user follows the presented plan to reach the destination and uses the offered coupons and special offers. The input is the optimal plan and coupon information, and the output is the user's actual visit experience. The user can enjoy a comfortable and efficient visit.

[0490] 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.

[0491] 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.

[0492] 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.

[0493] [Second embodiment]

[0494] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0495] 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.

[0496] 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).

[0497] 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.

[0498] 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.

[0499] 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).

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] 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."

[0506] The present invention relates to a system that predicts congestion and provides optimal outing plans, in which a server, a terminal, and a user operate in cooperation with each other. Specific embodiments of the system will be described below.

[0507] Server Processing

[0508] Data collection

[0509] The server collects multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[0510] Data processing and predictive model building

[0511] The server cleans the collected data, removing noise and missing values. It then extracts useful features and uses generative AI to build a congestion prediction model. This model can predict congestion in specific areas or facilities with high accuracy.

[0512] Processing user requests

[0513] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[0514] Generating an optimal plan

[0515] The server generates an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[0516] Sending a response

[0517] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[0518] Terminal handling

[0519] User Interface Display

[0520] The device provides an interface for users to input their destinations and schedules, and must be designed to be intuitive so that users can easily operate it.

[0521] Sending input data

[0522] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0523] Receiving and Viewing Plans

[0524] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0525] User Action

[0526] Enter your destination and schedule

[0527] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0528] Confirmation of proposed plan

[0529] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0530] Local use

[0531] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0532] Specific examples

[0533] As an example, consider the case where a user wants to visit the zoo next weekend. The user uses the device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, where the user can confirm it, make plans, and visit the zoo. Once at the zoo, the user can enjoy a comfortable stay and take a break at the cafe using the coupon.

[0534] The above is a specific embodiment of the present invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[0535] The processing flow will be explained below.

[0536] Step 1: Data collection

[0537] Server Processing

[0538] The server collects the necessary data from multiple data sources: people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. This data is then stored in a database on the server.

[0539] Step 2: Cleaning the data

[0540] Server Processing

[0541] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[0542] Step 3: Feature extraction

[0543] Server Processing

[0544] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[0545] Step 4: Building a congestion prediction model

[0546] Server Processing

[0547] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[0548] Step 5: Displaying the User Interface

[0549] Terminal handling

[0550] The terminal provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[0551] Step 6: Enter your destination and schedule

[0552] User Action

[0553] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[0554] Step 7: Submitting input data

[0555] Terminal handling

[0556] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0557] Step 8: Parsing the Request

[0558] Server Processing

[0559] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[0560] Step 9: Run congestion forecast

[0561] Server Processing

[0562] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[0563] Step 10: Generate optimal plan

[0564] Server Processing

[0565] The server generates an optimal outing plan for the user based on the congestion prediction results, which includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[0566] Step 11: Sending the Response

[0567] Server Processing

[0568] The server transmits the generated outing plan to the user's terminal.

[0569] Step 12: Receive and view your plan

[0570] Terminal handling

[0571] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0572] Step 13: Review the proposed plan

[0573] User Action

[0574] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0575] Step 14: Travel to your destination

[0576] User Action

[0577] The user follows the proposed plan and adjusts the timing to head to the destination.

[0578] Step 15: Local use

[0579] User Action

[0580] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[0581] The above are the specific processing steps of this invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[0582] Example 1

[0583] 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."

[0584] In recent years, increasing congestion at tourist destinations and commercial facilities has made it difficult for visitors to plan appropriate visit times and itineraries to ensure a comfortable stay. Accurate congestion predictions based on real-time changing environmental conditions and people flow data are also required, but current systems are unable to adequately address this. Furthermore, there are insufficient means to provide users with optimal visitor plans to avoid crowds, and specific suggestions for improving user satisfaction are lacking.

[0585] 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.

[0586] In this invention, the server includes: means for collecting people flow data, weather data, and demand forecast data from data sources; means for processing the collected data with a data cleaning tool to remove noise and missing values; and means for extracting effective features from the processed data and constructing a congestion prediction model using a generative AI model. This enables accurate congestion prediction in real time. The server also includes means for accepting input of a destination and schedule from a user via a terminal; means for using a prediction model to perform congestion prediction based on the input destination and schedule; means for generating an optimal outing plan based on the congestion prediction results, including recommended visit time, predicted stay time, congestion information, and coupon information; and means for transmitting and presenting the generated outing plan to the user's terminal. This allows users to plan their visit optimally and enjoy a comfortable visit experience. Furthermore, by further including means for providing coupon information and special offer information to the user, user satisfaction can be further improved. Furthermore, by including means for adjusting congestion tolerance based on the destination and schedule input by the user, it is possible to provide more personalized and optimal outing plans.

[0587] A "data source" is an information source that provides information such as people flow data, weather data, and demand forecast data.

[0588] "People flow data" refers to information about people's movements and stays in specific areas or facilities.

[0589] "Weather data" refers to data that includes meteorological information such as temperature, precipitation, and wind speed.

[0590] "Demand forecast data" is data used to predict the number of visitors and consumption behavior in a specific area or facility.

[0591] A "data cleaning tool" is software or algorithms used to remove noise and missing values ​​from collected data.

[0592] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and makes predictions and generates results. Examples include GPT-4.

[0593] A "congestion prediction model" is a model for predicting congestion conditions at specific locations and times based on people flow data and environmental data.

[0594] A "terminal" is a device that allows a user to input information or receive information from the system. Examples include smartphones and personal computers.

[0595] A "destination" refers to a place or facility that a user wishes to visit.

[0596] "Schedule" refers to the date and time when the user intends to visit.

[0597] "Recommended Visit Time" refers to the optimal time of day for a visit suggested by the system to avoid overcrowding.

[0598] "Predicted stay time" refers to the time the system predicts the user will stay at a destination.

[0599] "Coupon information" refers to information that allows users to receive discounts or benefits at specific locations or services.

[0600] "Special offer information" refers to special offer information other than discounts that users can receive.

[0601] "Congestion tolerance" refers to a standard indicating how much congestion a user can tolerate.

[0602] This invention relates to a system that predicts congestion and provides optimal outing plans, in which the elements of a server, a terminal, and a user work in cooperation with each other.

[0603] Server Processing

[0604] The server functions by collecting data from the internet and specific data providers. Specifically, it uses APIs to continuously obtain people flow data, weather data, and demand forecast data. A database is used to manage the data. This makes it possible to grasp congestion conditions and weather fluctuations in real time. Examples of APIs that can be used include Google API and Weather API.

[0605] The server uses a data cleaning tool (e.g., Pandas) to remove noise and missing values ​​from the collected data. Next, it uses a machine learning library (e.g., scikit-learn) to extract useful features. Based on this data, it uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. This predictive model can predict the congestion situation in specific areas or facilities with high accuracy.

[0606] The server receives destination and schedule information entered by the user through the device. The received information is converted into a prompt to be input into the generative AI model. For example, if a user enters "zoo" and "next Sunday at 10:00 AM," the prompt will be in the format "Please predict the crowding situation at the zoo at 10:00 AM next Sunday."

[0607] Based on this, the server uses a prediction model to predict congestion and generate an optimal outing plan including recommended visit times, predicted stay times, congestion information, and coupon information. This plan is sent to the user's device as an API response.

[0608] Terminal handling

[0609] The terminal provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. The input data is validated using a consistency check tool (e.g., regular expressions). The validated data is then sent to the server as an API request.

[0610] Once the optimal plan sent from the server is received by the terminal, it is displayed in a user-friendly format, including visit times, travel times, congestion information, coupon details, and more.

[0611] User Action

[0612] Users input their destination and desired date and time of visit through the device interface. Next, they check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. They then head to their destination according to the plan and enjoy a comfortable visit experience by using coupons and special offers offered on site.

[0613] Specific examples

[0614] For example, if a user plans to visit the zoo next weekend, they use their device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server. The server uses a crowd prediction model (GPT-4) based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, where the user confirms it, makes plans, and visits the zoo. Once there, they make themselves comfortable and use the coupon to take a break at the cafe.

[0615] This allows users to plan their trips efficiently, avoiding crowds and traffic jams, and reducing financial losses and psychological burdens.

[0616] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0617] Server Processing

[0618] Step 1: Data collection

[0619] The server collects people flow data, weather data, and demand forecast data from each data source. Specifically, it obtains these data from the Internet using APIs. For example, it collects people flow data from Google API and weather data from Weather API. The input is raw data obtained from the data source, and the output is the initial data stored in the database.

[0620] Step 2: Data cleaning

[0621] The server performs data cleaning on the collected data. Specifically, it uses a data cleaning tool (e.g., Pandas) to remove noise and missing values. The input is the initial data stored in the database, and the output is the cleaned data.

[0622] Step 3: Feature extraction

[0623] The server extracts useful features from the cleaned data. It uses a machine learning library (e.g., scikit-learn) to select features and prepares the data required for prediction. The input is the cleaned data, and the output is a dataset with extracted features.

[0624] Step 4: Building a predictive model

[0625] The server uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. It trains the model based on the extracted features and saves the trained model. The input is the dataset from which the features have been extracted, and the output is the trained prediction model.

[0626] Step 5: Processing User Requests

[0627] The server receives the destination and schedule information sent from the user's device and converts the received information into a prompt format for input to the generative AI model. The input is the request data from the user, and the output is data in the prompt format.

[0628] Step 6: Run congestion forecast

[0629] The server inputs prompts into the prediction model to predict congestion. The generative AI model obtains the prediction results and derives recommended visit times and congestion information. The input is prompt-format data, and the output is the congestion prediction results.

[0630] Step 7: Generate an optimal plan

[0631] The server generates an optimal outing plan based on the prediction results. This plan includes recommended visit times, predicted stay times, congestion information, and coupon information. The input is the congestion prediction results, and the output is the optimal plan.

[0632] Step 8: Submit your plan

[0633] The server sends the generated optimal plan to the user's device as an API response. The input is the optimal plan, and the output is the plan sent to the user's device.

[0634] Terminal handling

[0635] Step 1: Displaying the User Interface

[0636] The device displays an interface for users to input their destination and schedule. Specifically, it provides an intuitive UI (user interface) that includes an input form. The input is the destination and schedule information entered by the user, and the output is the input form displayed on the screen.

[0637] Step 2: Submitting input data

[0638] The terminal checks the consistency of the destination and schedule information entered by the user before sending it to the server. A consistency check tool (e.g., regular expressions) is used. The input is the destination and schedule information entered by the user, and the output is the data sent to the server.

[0639] Step 3: Receive and view your plan

[0640] The terminal receives the optimal plan sent from the server and displays it to the user. Specifically, it displays an interface that includes visit time, required time, congestion information, and coupon information. The input is the optimal plan sent from the server, and the output is the plan displayed to the user.

[0641] User Action

[0642] Step 1: Enter your destination and schedule

[0643] The user inputs the destination and date / time they wish to visit through the terminal interface. The input is the destination and the date / time they wish to visit, and the output is the data entered into the terminal.

[0644] Step 2: Confirm the proposed plan

[0645] The user checks the optimal plan displayed on the terminal and makes a plan based on the recommended visit time and coupon information. The input is the optimal plan displayed on the terminal, and the output is the plan confirmed by the user.

[0646] Step 3: Local use

[0647] The user heads to the destination according to the plan, uses the provided coupons and special offers, and enjoys a pleasant visiting experience. The input is the optimal plan, and the output is the actual visiting experience.

[0648] (Application example 1)

[0649] 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."

[0650] In recent years, congestion in urban areas and tourist destinations has become a problem, creating a need for ways to ensure visitors can spend their time comfortably. Physical stores and tourist facilities also need to provide information to encourage visits while avoiding customer concentration. Conventional technologies are often ineffective for users, as they are unable to adequately predict congestion or suggest optimal visit times. Furthermore, coupons and special offer information are often provided individually, making centralized management difficult. A new system is needed to solve these issues.

[0651] 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.

[0652] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for using a generation AI to build a congestion prediction model based on the collected data, means for accepting input of a destination and schedule from a user, means for using the prediction model to perform congestion prediction based on the input destination and schedule, means for generating an optimal outing plan taking into account the congestion prediction results, means for presenting the generated outing plan to the user, and means for notifying the user of visiting times and special offer information. This allows the user to visit destinations efficiently while avoiding crowds, and at the same time allows the user to use centrally managed coupons and special offer information.

[0653] A "data source" is a source of data from which the system obtains information. Specifically, this includes data such as people flow data, weather data, and demand forecast data.

[0654] "People flow data" is information recorded on the movements and stays of people in specific areas or facilities. This information can be used to predict congestion situations.

[0655] "Weather Data" means information about weather fluctuations, including temperature, precipitation, wind speed, etc.

[0656] "Demand forecast data" is statistical information used to predict future demand. This includes past sales data and event information.

[0657] "Generative AI" refers to algorithms that use artificial intelligence techniques to achieve specific goals. In this case, it is used to build congestion prediction models.

[0658] A "congestion prediction model" is a model that predicts future congestion conditions in specific areas or facilities based on people flow data, weather data, and demand forecast data.

[0659] A "destination" is a place or facility that the user wishes to visit.

[0660] "Schedule" is information about the date and time when the user plans to visit.

[0661] An "outing plan" is a plan created by a user based on the congestion prediction results, taking into consideration the optimal visiting time and special offer information.

[0662] "Visiting time" refers to the optimal time for a user to visit a destination.

[0663] "Special offer information" is information such as discounts and coupons available at the destination and its surrounding areas.

[0664] "Presenting" refers to the act of displaying the generated outing plan and benefit information to the user.

[0665] "Notification" is the act of conveying important information such as visiting times and special offers to users in real time.

[0666] The present invention relates to a system that predicts congestion and provides optimal outing plans, and is a system in which the elements of a server, a terminal, and a user work in cooperation with each other.

[0667] Server Processing

[0668] Data collection

[0669] The server has the means to collect multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[0670] Data processing and predictive model building

[0671] The server cleans the collected data, removing noise and missing values. Based on the collected data, a congestion prediction model is built using generative AI. This model can predict congestion situations in specific areas or facilities with high accuracy. Specifically, this includes data preprocessing using Python and processes related to the training and prediction of the generative AI model.

[0672] Processing user requests

[0673] The server receives destination and schedule information entered by the user through their device. The server analyzes this information and inputs it into a predictive model to predict congestion at the time of the planned visit. This involves retrieving data using various APIs and processing the database.

[0674] Generate and present optimal plans

[0675] The server has a means to generate an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupon and special offer information. The generated outing plan is sent to the application to be presented to the user. Python, Flask / Django, etc. are used to generate the specific plan.

[0676] Terminal handling

[0677] User Interface Display

[0678] The device has a means to provide an interface for users to input their destinations and schedules. An intuitive design is required to make it easy for users to operate. A smartphone application is an example of this.

[0679] Sending input data

[0680] The device sends the destination and schedule data entered by the user to the server, which checks the data for consistency and prompts the user to make corrections if necessary. The transmission involves an internet connection and an API call.

[0681] Receiving and Viewing Plans

[0682] The device receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons, and special offers. The actual display is done on the smartphone screen.

[0683] User Action

[0684] Enter your destination and schedule

[0685] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0686] Confirmation of proposed plan

[0687] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0688] Local use

[0689] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0690] Specific examples

[0691] As an example, let's consider the case where a user plans to visit a shopping mall next weekend. The user uses a device to input "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended time to visit and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is sent to the device, and the user confirms it, makes plans, and visits the shopping mall. Once there, the user can enjoy a comfortable stay and take a break at the cafe using the coupon.

[0692] Prompt Sentence Examples

[0693] Below is an example of a prompt when a user plans to visit a shopping mall:

[0694] "Generate an outing plan that includes the optimal visit time and coupon information based on the user's input data in the following format. For example, the physical store the user wants to visit is a "shopping mall," and the planned date is "November 5, 2023, 10:00 AM."

[0695] The above is a specific embodiment of the present invention. This system allows users to avoid crowds and make efficient outing plans, thereby reducing economic losses and psychological burdens.

[0696] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0697] Step 1:

[0698] The server continuously collects people flow data, weather data, and demand forecast data from data sources. Specifically, the server accesses the Internet or specific data provider services and sends API requests to obtain the latest data. This data is stored in a database on the server. The input is information from the data source, and the output is the collected data.

[0699] Step 2:

[0700] The server cleans the collected data and removes noise and missing values. Specifically, it preprocesses the data using Python libraries (e.g., pandas, numpy). The clean dataset obtained in this way is used to extract useful features. The input is the collected data, and the output is the cleaned data.

[0701] Step 3:

[0702] The server uses generative AI to build a congestion prediction model based on the cleaned data. Specifically, it trains the model using a machine learning library (e.g., TensorFlow, Scikit-learn). The trained model is stored in a database and used for prediction processing. The input is the cleaned data, and the output is the congestion prediction model.

[0703] Step 4:

[0704] The user inputs the destination and the planned date and time of the visit using a terminal (such as a smartphone). The terminal provides an intuitive user interface and sends the input data to the server. The input is the destination and schedule entered by the user, and the output is the data sent to the server.

[0705] Step 5:

[0706] The server inputs the destination and schedule information received from the user into a prediction model to predict the congestion situation at the time of the planned visit. The server analyzes the prediction results and generates an optimal outing plan including recommended visit times and congestion information. The input is the user's destination and schedule, and the output is the generated outing plan.

[0707] Step 6:

[0708] The server sends the generated outing plan to the device. This includes the planned visit time, estimated stay time, congestion information, coupon and special offer information. The server converts the data into an appropriate format and sends it to the device using an API. The input is the generated outing plan, and the output is the transmitted data.

[0709] Step 7:

[0710] The terminal receives the outing plan sent from the server and displays it to the user. The user checks the plan and makes a plan based on the optimal visiting time and coupon information. The input is the outing plan sent from the server, and the output is the information displayed to the user.

[0711] Step 8:

[0712] The user follows the plan to reach the destination and uses the coupons and special offers provided. The user enjoys a pleasant visiting experience at the destination. The input is the user's action plan, and the output is the visiting experience.

[0713] 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.

[0714] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide a customized plan tailored to the user's emotional state. Specific embodiments of this system are described below.

[0715] Server Processing

[0716] Data collection

[0717] The server collects multiple types of data from data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data on users' emotional states. This data is stored in a database on the server.

[0718] Cleaning the data

[0719] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[0720] Feature extraction

[0721] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[0722] Building a congestion prediction model

[0723] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[0724] Processing user requests

[0725] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[0726] Use of emotion engine

[0727] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history, which can include stress, relaxation, excitement, etc.

[0728] Generating an optimal plan

[0729] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. By taking the results of the emotion engine into consideration, it is possible to propose a plan that avoids crowds to a user who is easily stressed, or a plan that includes event information to a user who wants to get excited.

[0730] Sending a response

[0731] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[0732] Terminal handling

[0733] User Interface Display

[0734] The terminal provides an interface for users to input their destination and schedule, and an intuitive design is required to make it easy for users to operate.

[0735] Sending input data

[0736] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0737] Receiving and Viewing Plans

[0738] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0739] User Action

[0740] Enter your destination and schedule

[0741] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0742] Confirmation of proposed plan

[0743] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0744] Local use

[0745] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0746] Specific examples

[0747] As an example, consider a user planning to visit the zoo next weekend. The user uses their device to input "zoo" and "next Sunday at 10 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state, suggesting 9:30 AM as the recommended visit time if the user is prone to stress, and generates an optimal plan that includes a 10% discount coupon for a cafe near the zoo. This plan is then sent to the device, where the user can confirm it, make plans, and visit the zoo. Once there, they can relax comfortably and take a break at the cafe using the coupon.

[0748] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[0749] The processing flow will be explained below.

[0750] Step 1: Data collection

[0751] Server Processing

[0752] The server collects the necessary data from multiple data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data to analyze the user's emotional state. This data is stored in a database on the server.

[0753] Step 2: Cleaning the data

[0754] Server Processing

[0755] The server removes noise and missing values ​​from the collected data, detects and removes outliers, and performs other preprocessing such as filling in missing data to improve the quality of the data.

[0756] Step 3: Feature extraction

[0757] Server Processing

[0758] The server extracts features from the cleaned data that are effective for predicting congestion, such as the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[0759] Step 4: Building a congestion prediction model

[0760] Server Processing

[0761] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[0762] Step 5: Displaying the User Interface

[0763] Terminal handling

[0764] The device provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[0765] Step 6: Enter your destination and schedule

[0766] User Action

[0767] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[0768] Step 7: Submitting input data

[0769] Terminal handling

[0770] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0771] Step 8: Parsing the Request

[0772] Server Processing

[0773] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[0774] Step 9: Use the Emotion Engine

[0775] Server Processing

[0776] The server uses an emotion engine to analyze the user's emotional state, determining their current emotional state (e.g., stressed, relaxed, excited) based on the data they input, their past usage history, and their real-time reaction data.

[0777] Step 10: Run congestion forecast

[0778] Server Processing

[0779] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[0780] Step 11: Generate optimal plan

[0781] Server Processing

[0782] The server generates optimal outing plans for users based on the congestion prediction results and the analysis results of the emotion engine. For example, it generates a plan that avoids crowds for users who are easily stressed, and a plan that includes event information for users who want to get excited.

[0783] Step 12: Add coupons and special offers

[0784] Server Processing

[0785] The server adds coupon information and special offer information to the generated plan. Coupons include discount information that can be used at affiliated stores and services.

[0786] Step 13: Sending the Response

[0787] Server Processing

[0788] The server transmits the generated outing plan to the user's terminal.

[0789] Step 14: Receive and view your plan

[0790] Terminal handling

[0791] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0792] Step 15: Review the proposed plan

[0793] User Action

[0794] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0795] Step 16: Travel to your destination

[0796] User Action

[0797] The user follows the proposed plan and adjusts the timing to head to the destination.

[0798] Step 17: Local use

[0799] User Action

[0800] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[0801] The above are the specific processing steps of this invention. This system allows users to make efficient outing plans that avoid crowds and traffic jams, and furthermore, it is possible to reduce economic losses and psychological burdens by customizing plans based on emotional states.

[0802] Example 2

[0803] 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."

[0804] Conventional congestion prediction and outing plan provision systems provide uniform plans without considering the user's emotional state, making it difficult to alleviate the stress and dissatisfaction felt by users. In addition, many systems collect only a limited number of data types, resulting in low congestion prediction accuracy and making it impossible to respond to the diverse needs of users.

[0805] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting movement data, weather data, and demand forecast data from data sources, means for constructing a congestion prediction model using a generative AI model based on the collected data, means for accepting input of a destination and schedule from a user, means for using an emotion engine to analyze the user's emotional state, means for generating an optimal outing plan taking into account the congestion prediction result and the analysis result of the emotion engine, and means for presenting the generated outing plan to the user. This provides an outing plan customized according to the user's emotional state, enabling a more comfortable and satisfying visiting experience.

[0806] "Data Source" means the information source used to provide travel data, weather data, and demand forecast data.

[0807] "Movement data" is information about the movement of people and things obtained from sensors, cameras, and people flow data measurement devices.

[0808] "Weather data" is information about the weather obtained from a weather forecast service.

[0809] "Demand forecast data" refers to forecast information on demand collected through search engines and social media APIs.

[0810] A "generative AI model" is a model that is generated using artificial intelligence technology and performs predictions and analyses for specific purposes.

[0811] A "congestion prediction model" is a model that uses past data to predict congestion levels at specific locations and time periods.

[0812] An "emotion engine" is a system or algorithm for analyzing a user's emotional state from their input data and past usage history.

[0813] The "optimal outing plan" is a visit plan that is optimal for the user, generated by taking into account the congestion prediction results and the analysis results of the emotion engine.

[0814] "Coupon information" is information that provides discounts on specific services or products.

[0815] "Special offer information" is information other than coupon information about additional services or product offers.

[0816] "Congestion tolerance" is an index that indicates how much congestion a user can tolerate or tolerate at a destination.

[0817] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide customized plans that correspond to the user's emotional state.

[0818] Server Processing

[0819] Data collection

[0820] The server collects movement data, weather data, and demand forecast data from data sources. Specifically, it collects movement data from sensors, cameras, and people flow data measurement devices, obtains weather data using weather forecast service APIs, and collects demand forecast data from search engines and social media APIs. The collected data is stored in the server's database.

[0821] Cleaning the data

[0822] The server detects and removes noise and outliers from the collected data, such as abnormally high values ​​and invalid timestamps. It also improves data quality by imputing missing values ​​using past data or imputation techniques.

[0823] Feature extraction

[0824] The server extracts features from the cleaned data that are effective for predicting congestion. Specifically, it learns user behavior patterns and congestion characteristics by combining factors such as day of the week, time of day, weather, and event information.

[0825] Building a congestion prediction model

[0826] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict future congestion situations with high accuracy.

[0827] Processing user requests

[0828] The server receives destination and schedule information entered by the user from the terminal, and inputs this information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time.

[0829] Use of emotion engine

[0830] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. For example, it determines whether the user is feeling stressed based on their recent social media posts and history.

[0831] Generating an optimal plan

[0832] The server generates an optimal outing plan for the user based on the congestion prediction results and the emotion engine's analysis results. The plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers. For example, for a user who is prone to stress, a plan is proposed that includes visit times that avoid crowds and relaxing spots.

[0833] Sending a response

[0834] The server transmits the generated outing plan to the terminal and presents it to the user.

[0835] Terminal handling

[0836] User Interface Display

[0837] The terminal provides an interface for users to input their destination and schedule, and the interface is designed to be intuitive and easy to operate.

[0838] Sending input data

[0839] The device sends the destination and schedule data entered by the user to the server, which checks the format and consistency of the data and prompts the user to make corrections if necessary.

[0840] Receiving and Viewing Plans

[0841] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes recommended visit times, travel time, congestion information, and details of coupons and special offers.

[0842] User Action

[0843] Enter your destination and schedule

[0844] The user uses the device's interface to input the desired destination and date and time, such as "the zoo" or "next Sunday at 10:00 AM."

[0845] Confirmation of proposed plan

[0846] The user can check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. For example, they can check a plan to visit the zoo at 9:30 in the morning and use a discount coupon at the cafe.

[0847] Local use

[0848] Users can go to their destination as planned and enjoy a pleasant visit experience by using the coupons and offers provided, for example, visiting the zoo at a less crowded time and relaxing at a cafe using coupons.

[0849] Specific examples

[0850] Example input

[0851] For example, if a user wants to visit the zoo next weekend, the user types:

[0852] "The Zoo" "Next Sunday at 10 AM"

[0853] Processing flow

[0854] 1. The terminal sends the user's input data to the server.

[0855] 2. The server uses the congestion prediction model to predict the congestion situation at 10:00 AM on the following Sunday.

[0856] 3. The server uses an emotion engine to analyze the user's emotional state.

[0857] 4. If the user is prone to stress, the server generates an optimal plan with a recommended visit time of 9:30 AM and a 10% discount coupon for a cafe near the zoo.

[0858] 5. The plan is sent to the device and presented to the user.

[0859] Actual use

[0860] Users can check the proposed plan on their device, visit the zoo, avoid crowds, spend the day comfortably, and take a break at the cafe using coupons.

[0861] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[0862] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0863] Step 1: Data collection

[0864] The server collects movement data, weather data, and demand forecast data. Specifically, it obtains movement data from sensors, cameras, and people flow data measurement devices, obtains weather data from weather forecast services using APIs, and collects demand forecast data from search engines and social media APIs. It receives various data from data sources as input and stores it in the server's database as output.

[0865] Step 2: Cleaning the data

[0866] The server detects and removes noise and outliers from the collected data. Specifically, it removes abnormally high values ​​and invalid timestamps from the data. Missing values ​​are imputed using past data or imputation techniques. It receives the collected data as input and generates cleaned data as output.

[0867] Step 3: Feature extraction

[0868] The server extracts features from the cleaned data that are effective for crowd prediction. Specifically, it combines factors such as the day of the week, time of day, weather, and event information. It receives the cleaned data as input and generates feature data as output to be input into the crowd prediction model.

[0869] Step 4: Building a congestion prediction model

[0870] The server uses a generative AI model to build a congestion prediction model based on the extracted features. Specifically, it learns from past data and generates a model that can predict future congestion situations. It receives feature data as input and generates a completed congestion prediction model as output.

[0871] Step 5: Receiving a user request

[0872] The server receives the destination and schedule information entered by the user from the terminal. The information entered by the user into the terminal (e.g., "Zoo" and "Next Sunday at 10:00 AM") is received as input data, and this information is input into the congestion prediction model as output.

[0873] Step 6: Run congestion forecast

[0874] The server inputs the received destination and schedule information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time. The server receives the user's destination and schedule information as input and generates a congestion prediction result as output.

[0875] Step 7: Emotion Engine Analysis

[0876] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. It receives the user's historical data and current data as input and generates the emotion analysis results as output.

[0877] Step 8: Generate an optimal plan

[0878] The server generates an optimal outing plan for the user based on the congestion prediction results and the analysis results of the emotion engine. Specifically, it creates a plan that includes recommended visit times, predicted stay times, congestion information, coupons and special offers. It receives the congestion prediction results and emotion analysis results as input and generates the optimal outing plan as output.

[0879] Step 9: Submit your plan

[0880] The server receives the generated outing plan as input and sends the plan to the terminal as output.

[0881] Step 10: User confirms plan

[0882] The terminal receives the optimal plan sent from the server and displays it to the user. The user checks the suggested visit time and coupon information and makes a plan. The terminal receives plan data from the server as input and displays it to the user as output.

[0883] Step 11: Execute the plan

[0884] The user visits the destination based on the proposed optimal plan. For example, the user visits the zoo at 9:30 in the morning and uses a discount coupon at the cafe. By following the plan as input, the user enjoys a pleasant visiting experience, and by output, the user gets a satisfying experience.

[0885] These are the specific processing steps of this program. At each step, specific data processing and calculations are performed based on the input data, and output is obtained according to the purpose. This allows users to enjoy customized outing plans that avoid crowds and stress.

[0886] (Application example 2)

[0887] 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."

[0888] In modern urban areas and commercial facilities, crowds frequently occur, causing stress and inconvenience to visitors. Furthermore, visitors' emotional state significantly affects the comfort and satisfaction of their visit. However, conventional crowd prediction systems do not take visitors' emotional state into account, making it difficult to provide optimal outing plans. As a result, situations in which visitors feel stressed are often unavoidable. Therefore, the present invention aims to provide a system that combines crowd prediction and visitors' emotional state to provide optimal visit plans for each individual.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0890] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for building a congestion prediction model using a generation AI based on the collected data, means for accepting input of a destination and schedule from a user, means for performing congestion prediction based on the input destination and schedule using the prediction model, means for generating an optimal outing plan taking into account the congestion prediction results and the results of user emotion analysis, means for presenting the generated outing plan to the user, means for providing coupon information and special offer information to the user, means for adjusting the congestion tolerance level according to the destination and schedule input by the user, means for analyzing the user's real-time emotional state, and means for capturing the user's emotional state using a camera in smart glasses or a smartphone. This enables the generation of an optimal outing plan based on the congestion prediction results and the results of user emotion analysis.

[0891] A "data source" is a source of data obtained from various sensors and information sources on the Internet.

[0892] "People flow data" is data that shows the movement and stay patterns of people in specific areas or facilities.

[0893] "Weather data" refers to data related to weather, such as temperature, precipitation, and wind speed, obtained from weather information services.

[0894] "Demand forecast data" is data that shows predicted numbers of visitors at a certain location or time period using search engine or social media APIs, etc.

[0895] "Generative AI" is artificial intelligence that uses machine learning and deep learning techniques to analyze data and generate predictive models and plans.

[0896] A "congestion prediction model" is an algorithm or statistical model that uses past data to predict congestion at specific locations and times of day.

[0897] "User emotion analysis" is the process of analyzing a user's emotional state, such as stress, relaxation, or excitement, based on their facial expressions and behavioral data.

[0898] An "outing plan" is a visiting plan that includes the optimal visiting time, required time, route, benefit information, etc. for the user's visiting destinations.

[0899] "Coupon information" is information about discount coupons and service coupons that can be used at specific stores or facilities.

[0900] "Benefit information" is information that provides additional benefits to users, and includes coupons, gifts, and the like.

[0901] "Smart glasses" are wearable devices that have built-in cameras and displays and can acquire and display information in real time.

[0902] A "smartphone" is a mobile device that has mobile phone functions and can connect to the Internet and use applications.

[0903] The "emotional state" indicates the emotion the user is currently feeling, such as stress, relaxation, excitement, etc.

[0904] "Capture" means using a camera or sensor to capture a user's facial expressions and actions as images or video.

[0905] MODE FOR CARRYING OUT THE INVENTION

[0906] This invention relates to a system that predicts congestion and provides an optimal outing plan based on the user's emotional state. This system includes means for collecting various data from data sources, building a congestion prediction model, accepting input of destinations and schedules from users, analyzing their emotions, and generating and presenting an optimal plan.

[0907] Server Processing

[0908] Data collection

[0909] The server collects people flow data, weather data, and demand forecast data from various sensors and online data sources. Specifically, this includes people flow data obtained from sensors and cameras, weather data obtained from weather forecast service APIs, and demand forecast data obtained via search engine and social media APIs. It also collects data on users' emotional states.

[0910] Data cleaning and preprocessing

[0911] The server performs cleaning processes on the collected data to remove noise and missing values. This process includes detecting and removing outliers and filling in missing data. Appropriate preprocessing is performed to improve the quality of the data. This process uses Python's pandas library, etc.

[0912] Feature extraction

[0913] The server extracts features from the cleaned data that are effective for predicting congestion. For example, information such as the day of the week, time of day, weather, and event information is extracted and used for subsequent training of the prediction model. Generative AI (machine learning and deep learning techniques) is used at this stage.

[0914] Building a congestion prediction model

[0915] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and time periods. Libraries such as TensorFlow and scikit-learn are used.

[0916] Use of emotion engine

[0917] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history. Emotional states include stress, relaxation, excitement, etc. Emotion analysis utilizes face recognition and facial expression analysis technologies using OpenCV and TensorFlow.

[0918] Generating an optimal plan

[0919] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information, etc. By taking into account the results of the emotion engine, it is possible to propose plans that avoid crowds to users who are easily stressed, and plans that include event information to users who want to get excited.

[0920] Terminal handling

[0921] User Interface Display

[0922] The device provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. A smartphone app or smart glasses interface is used.

[0923] Sending input data

[0924] The device sends the destination and schedule data entered by the user to the server. At this time, the data is checked for consistency and the user is prompted to make corrections if necessary. Data transmission uses the HTTP protocol and RESTful API.

[0925] Receiving and Viewing Plans

[0926] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0927] User Action

[0928] Enter your destination and schedule

[0929] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0930] Confirmation of proposed plan

[0931] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0932] Local use

[0933] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[0934] Specific examples

[0935] For example, consider a user planning to visit a shopping mall next weekend. Using their smartphone, the user inputs "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to a server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state. If the user is prone to stress, the system suggests 9:30 AM as the recommended time to visit, and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is then sent to the device, where the user can review it and plan their visit.

[0936] This invention allows users to be free from crowds and stress and enjoy plans customized to their emotional state. An example of a specific prompt is, "Please create a program that generates the optimal outing plan based on the user's destinations, visiting times, and detected emotional data."

[0937] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0938] Step 1: Collect data

[0939] The server collects people flow data, weather data, and demand forecast data from data sources. Inputs include various sensors and cameras, weather forecast service APIs, search engines, and social media APIs. These data are stored in a database on the server. To use this data for analysis, a data collection process is executed, and the collected data is obtained as output.

[0940] Step 2: Clean and preprocess the data

[0941] The server performs cleaning processing to remove noise and missing values ​​from the data collected in step 1. This includes detecting and removing outliers and completing missing data. Specifically, it uses the Python pandas library to shape and improve the quality of the data. The input is the collected data, and the output is cleaned, high-quality data.

[0942] Step 3: Feature extraction

[0943] The server extracts features from the cleaned data that are effective for predicting congestion. These include the day of the week, time of day, weather, and event information. This uses generative AI to select important features. The input is the cleaned data, and the output is the extracted features. These features are then used for model training.

[0944] Step 4: Building a congestion prediction model

[0945] The server builds a congestion prediction model using the features extracted in step 3. In this process, a generative AI model (using TensorFlow, scikit-learn, etc.) is trained to create a model that can predict congestion at specific locations and time periods based on past data. The input is feature data, and the output is a congestion prediction model.

[0946] Step 5: User sentiment analysis

[0947] The server and device capture the user's real-time emotional state using the smart glasses or smartphone camera. The device captures the user's facial expressions and analyzes them using an emotion engine (using OpenCV and TensorFlow). The input to this process is real-time image data, and the output is the user's emotional state. The analysis results are sent to the server.

[0948] Step 6: Accepting input from the user

[0949] The terminal provides an interface for users to input the destinations and visit times they plan to visit. The input is the destination and schedule data entered by the user through the terminal, which is checked for consistency and sent to the server. The output is the input data sent to the server.

[0950] Step 7: Run congestion forecast

[0951] The server uses the congestion prediction model to predict the congestion status at the destination and visiting time based on the input data received in step 6. The input is the target destination and schedule data, and the output is the predicted congestion status.

[0952] Step 8: Generate an optimal plan

[0953] The server generates an optimal outing plan taking into account the results of crowd prediction and sentiment analysis. The plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. The inputs are the crowd prediction results and sentiment analysis results, and the output is an optimal outing plan.

[0954] Step 9: Present your plan

[0955] The terminal presents the optimal plan sent from the server to the user. The input received by the terminal is the generated outing plan, and the output is the plan displayed to the user, allowing the user to check and refer to the plan.

[0956] Step 10: Local use

[0957] The user follows the presented plan to reach the destination and uses the offered coupons and special offers. The input is the optimal plan and coupon information, and the output is the user's actual visit experience. The user can enjoy a comfortable and efficient visit.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] [Third embodiment]

[0962] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0963] 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.

[0964] 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).

[0965] 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.

[0966] 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.

[0967] 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).

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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.

[0973] 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."

[0974] The present invention relates to a system that predicts congestion and provides optimal outing plans, in which a server, a terminal, and a user operate in cooperation with each other. Specific embodiments of the system will be described below.

[0975] Server Processing

[0976] Data collection

[0977] The server collects multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[0978] Data processing and predictive model building

[0979] The server cleans the collected data, removing noise and missing values. It then extracts useful features and uses generative AI to build a congestion prediction model. This model can predict congestion in specific areas or facilities with high accuracy.

[0980] Processing user requests

[0981] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[0982] Generating an optimal plan

[0983] The server generates an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[0984] Sending a response

[0985] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[0986] Terminal handling

[0987] User Interface Display

[0988] The device provides an interface for users to input their destinations and schedules, and must be designed to be intuitive so that users can easily operate it.

[0989] Sending input data

[0990] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[0991] Receiving and Viewing Plans

[0992] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[0993] User Action

[0994] Enter your destination and schedule

[0995] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[0996] Confirmation of proposed plan

[0997] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[0998] Local use

[0999] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1000] Specific examples

[1001] As an example, let's consider a case where a user wants to visit the zoo next weekend. The user uses the device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, and the user confirms it, makes plans, and visits the zoo. Once at the zoo, the user can relax comfortably and take a break at the cafe using the coupon.

[1002] The above is a specific embodiment of the present invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[1003] The processing flow will be explained below.

[1004] Step 1: Data collection

[1005] Server Processing

[1006] The server collects the necessary data from multiple data sources: people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. This data is then stored in a database on the server.

[1007] Step 2: Cleaning the data

[1008] Server Processing

[1009] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[1010] Step 3: Feature extraction

[1011] Server Processing

[1012] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[1013] Step 4: Building a congestion prediction model

[1014] Server Processing

[1015] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[1016] Step 5: Displaying the User Interface

[1017] Terminal handling

[1018] The terminal provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[1019] Step 6: Enter your destination and schedule

[1020] User Action

[1021] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[1022] Step 7: Submitting input data

[1023] Terminal handling

[1024] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1025] Step 8: Parsing the Request

[1026] Server Processing

[1027] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[1028] Step 9: Run congestion forecast

[1029] Server Processing

[1030] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[1031] Step 10: Generate optimal plan

[1032] Server Processing

[1033] The server generates an optimal outing plan for the user based on the congestion prediction results, which includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[1034] Step 11: Sending the Response

[1035] Server Processing

[1036] The server transmits the generated outing plan to the user's terminal.

[1037] Step 12: Receive and view your plan

[1038] Terminal handling

[1039] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1040] Step 13: Review the proposed plan

[1041] User Action

[1042] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1043] Step 14: Travel to your destination

[1044] User Action

[1045] The user follows the proposed plan and adjusts the timing to head to the destination.

[1046] Step 15: Local use

[1047] User Action

[1048] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[1049] The above are the specific processing steps of this invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[1050] Example 1

[1051] 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."

[1052] In recent years, increasing congestion at tourist destinations and commercial facilities has made it difficult for visitors to plan appropriate visit times and itineraries to ensure a comfortable stay. Accurate congestion predictions based on real-time changing environmental conditions and people flow data are also required, but current systems are unable to adequately address this. Furthermore, there are insufficient means to provide users with optimal visitor plans to avoid crowds, and specific suggestions for improving user satisfaction are lacking.

[1053] 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.

[1054] In this invention, the server includes: means for collecting people flow data, weather data, and demand forecast data from data sources; means for processing the collected data with a data cleaning tool to remove noise and missing values; and means for extracting effective features from the processed data and constructing a congestion prediction model using a generative AI model. This enables accurate congestion prediction in real time. The server also includes means for accepting input of a destination and schedule from a user via a terminal; means for using a prediction model to perform congestion prediction based on the input destination and schedule; means for generating an optimal outing plan based on the congestion prediction results, including recommended visit time, predicted stay time, congestion information, and coupon information; and means for transmitting and presenting the generated outing plan to the user's terminal. This allows users to plan their visit optimally and enjoy a comfortable visit experience. Furthermore, by further including means for providing coupon information and special offer information to the user, user satisfaction can be further improved. Furthermore, by including means for adjusting congestion tolerance based on the destination and schedule input by the user, it is possible to provide more personalized and optimal outing plans.

[1055] A "data source" is an information source that provides information such as people flow data, weather data, and demand forecast data.

[1056] "People flow data" refers to information about people's movements and stays in specific areas or facilities.

[1057] "Weather data" refers to data that includes meteorological information such as temperature, precipitation, and wind speed.

[1058] "Demand forecast data" is data used to predict the number of visitors and consumption behavior in a specific area or facility.

[1059] A "data cleaning tool" is software or algorithms used to remove noise and missing values ​​from collected data.

[1060] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and makes predictions and generates results. Examples include GPT-4.

[1061] A "congestion prediction model" is a model for predicting congestion conditions at specific locations and times based on people flow data and environmental data.

[1062] A "terminal" is a device that allows a user to input information or receive information from the system. Examples include smartphones and personal computers.

[1063] A "destination" refers to a place or facility that a user wishes to visit.

[1064] "Schedule" refers to the date and time when the user intends to visit.

[1065] "Recommended Visit Time" refers to the optimal time of day for a visit suggested by the system to avoid overcrowding.

[1066] "Predicted stay time" refers to the time the system predicts the user will stay at a destination.

[1067] "Coupon information" refers to information that allows users to receive discounts or benefits at specific locations or services.

[1068] "Special offer information" refers to special offer information other than discounts that users can receive.

[1069] "Congestion tolerance" refers to a standard indicating how much congestion a user can tolerate.

[1070] This invention relates to a system that predicts congestion and provides optimal outing plans, in which the elements of a server, a terminal, and a user work in cooperation with each other.

[1071] Server Processing

[1072] The server functions by collecting data from the internet and specific data providers. Specifically, it uses APIs to continuously obtain people flow data, weather data, and demand forecast data. A database is used to manage the data. This makes it possible to grasp congestion conditions and weather fluctuations in real time. Examples of APIs that can be used include Google API and Weather API.

[1073] The server uses a data cleaning tool (e.g., Pandas) to remove noise and missing values ​​from the collected data. Next, it uses a machine learning library (e.g., scikit-learn) to extract useful features. Based on this data, it uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. This predictive model can predict the congestion situation in specific areas or facilities with high accuracy.

[1074] The server receives destination and schedule information entered by the user through the device. The received information is converted into a prompt to be input into the generative AI model. For example, if a user enters "zoo" and "next Sunday at 10:00 AM," the prompt will be in the format "Please predict the crowding situation at the zoo at 10:00 AM next Sunday."

[1075] Based on this, the server uses a prediction model to predict congestion and generate an optimal outing plan including recommended visit times, predicted stay times, congestion information, and coupon information. This plan is sent to the user's device as an API response.

[1076] Terminal handling

[1077] The terminal provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. The input data is validated using a consistency check tool (e.g., regular expressions). The validated data is then sent to the server as an API request.

[1078] Once the optimal plan sent from the server is received by the terminal, it is displayed in a user-friendly format, including visit times, travel times, congestion information, coupon details, and more.

[1079] User Action

[1080] Users input their destination and desired date and time of visit through the device interface. Next, they check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. They then head to their destination according to the plan and enjoy a comfortable visit experience by using coupons and special offers offered on site.

[1081] Specific examples

[1082] For example, if a user plans to visit the zoo next weekend, they use their device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server. The server uses a crowd prediction model (GPT-4) based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, where the user confirms it, makes plans, and visits the zoo. Once there, they make themselves comfortable and use the coupon to take a break at the cafe.

[1083] This allows users to plan their trips efficiently, avoiding crowds and traffic jams, and reducing financial losses and psychological burdens.

[1084] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1085] Server Processing

[1086] Step 1: Data collection

[1087] The server collects people flow data, weather data, and demand forecast data from each data source. Specifically, it obtains these data from the Internet using APIs. For example, it collects people flow data from Google API and weather data from Weather API. The input is raw data obtained from the data source, and the output is the initial data stored in the database.

[1088] Step 2: Data cleaning

[1089] The server performs data cleaning on the collected data. Specifically, it uses a data cleaning tool (e.g., Pandas) to remove noise and missing values. The input is the initial data stored in the database, and the output is the cleaned data.

[1090] Step 3: Feature extraction

[1091] The server extracts useful features from the cleaned data. It uses a machine learning library (e.g., scikit-learn) to select features and prepares the data required for prediction. The input is the cleaned data, and the output is a dataset with extracted features.

[1092] Step 4: Building a predictive model

[1093] The server uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. It trains the model based on the extracted features and saves the trained model. The input is the dataset from which the features have been extracted, and the output is the trained prediction model.

[1094] Step 5: Processing User Requests

[1095] The server receives the destination and schedule information sent from the user's device and converts the received information into a prompt format for input to the generative AI model. The input is the request data from the user, and the output is data in the prompt format.

[1096] Step 6: Run congestion forecast

[1097] The server inputs prompts into the prediction model to predict congestion. The generative AI model obtains the prediction results and derives recommended visit times and congestion information. The input is prompt-format data, and the output is the congestion prediction results.

[1098] Step 7: Generate an optimal plan

[1099] The server generates an optimal outing plan based on the prediction results. This plan includes recommended visit times, predicted stay times, congestion information, and coupon information. The input is the congestion prediction results, and the output is the optimal plan.

[1100] Step 8: Submit your plan

[1101] The server sends the generated optimal plan to the user's device as an API response. The input is the optimal plan, and the output is the plan sent to the user's device.

[1102] Terminal handling

[1103] Step 1: Displaying the User Interface

[1104] The device displays an interface for users to input their destination and schedule. Specifically, it provides an intuitive UI (user interface) that includes an input form. The input is the destination and schedule information entered by the user, and the output is the input form displayed on the screen.

[1105] Step 2: Submitting input data

[1106] The terminal checks the consistency of the destination and schedule information entered by the user before sending it to the server. A consistency check tool (e.g., regular expressions) is used. The input is the destination and schedule information entered by the user, and the output is the data sent to the server.

[1107] Step 3: Receive and view your plan

[1108] The terminal receives the optimal plan sent from the server and displays it to the user. Specifically, it displays an interface that includes visit time, required time, congestion information, and coupon information. The input is the optimal plan sent from the server, and the output is the plan displayed to the user.

[1109] User Action

[1110] Step 1: Enter your destination and schedule

[1111] The user inputs the destination and date / time they wish to visit through the terminal interface. The input is the destination and the date / time they wish to visit, and the output is the data entered into the terminal.

[1112] Step 2: Confirm the proposed plan

[1113] The user checks the optimal plan displayed on the terminal and makes a plan based on the recommended visit time and coupon information. The input is the optimal plan displayed on the terminal, and the output is the plan confirmed by the user.

[1114] Step 3: Local use

[1115] The user heads to the destination according to the plan, uses the provided coupons and special offers, and enjoys a pleasant visiting experience. The input is the optimal plan, and the output is the actual visiting experience.

[1116] (Application example 1)

[1117] 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."

[1118] In recent years, congestion in urban areas and tourist destinations has become a problem, creating a need for ways to ensure visitors can spend their time comfortably. Physical stores and tourist facilities also need to provide information to encourage visits while avoiding customer concentration. Conventional technologies are often ineffective for users, as they are unable to adequately predict congestion or suggest optimal visit times. Furthermore, coupons and special offer information are often provided individually, making centralized management difficult. A new system is needed to solve these issues.

[1119] 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.

[1120] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for using a generation AI to build a congestion prediction model based on the collected data, means for accepting input of a destination and schedule from a user, means for using the prediction model to perform congestion prediction based on the input destination and schedule, means for generating an optimal outing plan taking into account the congestion prediction results, means for presenting the generated outing plan to the user, and means for notifying the user of visiting times and special offer information. This allows the user to visit destinations efficiently while avoiding crowds, and at the same time allows the user to use centrally managed coupons and special offer information.

[1121] A "data source" is a source of data from which the system obtains information. Specifically, this includes data such as people flow data, weather data, and demand forecast data.

[1122] "People flow data" is information recorded on the movements and stays of people in specific areas or facilities. This information can be used to predict congestion situations.

[1123] "Weather Data" means information about weather fluctuations, including temperature, precipitation, wind speed, etc.

[1124] "Demand forecast data" is statistical information used to predict future demand. This includes past sales data and event information.

[1125] "Generative AI" refers to algorithms that use artificial intelligence techniques to achieve specific goals. In this case, it is used to build congestion prediction models.

[1126] A "congestion prediction model" is a model that predicts future congestion conditions in specific areas or facilities based on people flow data, weather data, and demand forecast data.

[1127] A "destination" is a place or facility that the user wishes to visit.

[1128] "Schedule" is information about the date and time when the user plans to visit.

[1129] An "outing plan" is a plan created by a user based on the congestion prediction results, taking into consideration the optimal visiting time and special offer information.

[1130] "Visiting time" refers to the optimal time for a user to visit a destination.

[1131] "Special offer information" is information such as discounts and coupons available at the destination and its surrounding areas.

[1132] "Presenting" refers to the act of displaying the generated outing plan and benefit information to the user.

[1133] "Notification" is the act of conveying important information such as visiting times and special offers to users in real time.

[1134] The present invention relates to a system that predicts congestion and provides optimal outing plans, and is a system in which the elements of a server, a terminal, and a user work in cooperation with each other.

[1135] Server Processing

[1136] Data collection

[1137] The server has the means to collect multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[1138] Data processing and predictive model building

[1139] The server cleans the collected data, removing noise and missing values. Based on the collected data, a congestion prediction model is built using generative AI. This model can predict congestion situations in specific areas or facilities with high accuracy. Specifically, this includes data preprocessing using Python and processes related to the training and prediction of the generative AI model.

[1140] Processing user requests

[1141] The server receives destination and schedule information entered by the user through their device. The server analyzes this information and inputs it into a predictive model to predict congestion at the time of the planned visit. This involves retrieving data using various APIs and processing the database.

[1142] Generate and present optimal plans

[1143] The server has a means to generate an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupon and special offer information. The generated outing plan is sent to the application to be presented to the user. Python, Flask / Django, etc. are used to generate the specific plan.

[1144] Terminal handling

[1145] User Interface Display

[1146] The device has a means to provide an interface for users to input their destinations and schedules. An intuitive design is required to make it easy for users to operate. A smartphone application is an example of this.

[1147] Sending input data

[1148] The device sends the destination and schedule data entered by the user to the server, which checks the data for consistency and prompts the user to make corrections if necessary. The transmission involves an internet connection and an API call.

[1149] Receiving and Viewing Plans

[1150] The device receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons, and special offers. The actual display is done on the smartphone screen.

[1151] User Action

[1152] Enter your destination and schedule

[1153] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[1154] Confirmation of proposed plan

[1155] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1156] Local use

[1157] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1158] Specific examples

[1159] As an example, let's consider the case where a user plans to visit a shopping mall next weekend. The user uses a device to input "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended time to visit and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is sent to the device, and the user confirms it, makes plans, and visits the shopping mall. Once there, the user can enjoy a comfortable stay and take a break at the cafe using the coupon.

[1160] Prompt Sentence Examples

[1161] Below is an example of a prompt when a user plans to visit a shopping mall:

[1162] "Generate an outing plan that includes the optimal visit time and coupon information based on the user's input data in the following format. For example, the physical store the user wants to visit is a "shopping mall," and the planned date is "November 5, 2023, 10:00 AM."

[1163] The above is a specific embodiment of the present invention. This system allows users to avoid crowds and make efficient outing plans, thereby reducing economic losses and psychological burdens.

[1164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1165] Step 1:

[1166] The server continuously collects people flow data, weather data, and demand forecast data from data sources. Specifically, the server accesses the Internet or specific data provider services and sends API requests to obtain the latest data. This data is stored in a database on the server. The input is information from the data source, and the output is the collected data.

[1167] Step 2:

[1168] The server cleans the collected data and removes noise and missing values. Specifically, it preprocesses the data using Python libraries (e.g., pandas, numpy). The clean dataset obtained in this way is used to extract useful features. The input is the collected data, and the output is the cleaned data.

[1169] Step 3:

[1170] The server uses generative AI to build a congestion prediction model based on the cleaned data. Specifically, it trains the model using a machine learning library (e.g., TensorFlow, Scikit-learn). The trained model is stored in a database and used for prediction processing. The input is the cleaned data, and the output is the congestion prediction model.

[1171] Step 4:

[1172] The user inputs the destination and the planned date and time of the visit using a terminal (such as a smartphone). The terminal provides an intuitive user interface and sends the input data to the server. The input is the destination and schedule entered by the user, and the output is the data sent to the server.

[1173] Step 5:

[1174] The server inputs the destination and schedule information received from the user into a prediction model to predict the congestion situation at the time of the planned visit. The server analyzes the prediction results and generates an optimal outing plan including recommended visit times and congestion information. The input is the user's destination and schedule, and the output is the generated outing plan.

[1175] Step 6:

[1176] The server sends the generated outing plan to the device. This includes the planned visit time, estimated stay time, congestion information, coupon and special offer information. The server converts the data into an appropriate format and sends it to the device using an API. The input is the generated outing plan, and the output is the transmitted data.

[1177] Step 7:

[1178] The terminal receives the outing plan sent from the server and displays it to the user. The user checks the plan and makes a plan based on the optimal visiting time and coupon information. The input is the outing plan sent from the server, and the output is the information displayed to the user.

[1179] Step 8:

[1180] The user follows the plan to reach the destination and uses the coupons and special offers provided. The user enjoys a pleasant visiting experience at the destination. The input is the user's action plan, and the output is the visiting experience.

[1181] 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.

[1182] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide a customized plan tailored to the user's emotional state. Specific embodiments of this system are described below.

[1183] Server Processing

[1184] Data collection

[1185] The server collects multiple types of data from data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data on users' emotional states. This data is stored in a database on the server.

[1186] Cleaning the data

[1187] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[1188] Feature extraction

[1189] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[1190] Building a congestion prediction model

[1191] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[1192] Processing user requests

[1193] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[1194] Use of emotion engine

[1195] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history, which can include stress, relaxation, excitement, etc.

[1196] Generating an optimal plan

[1197] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. By taking the results of the emotion engine into consideration, it is possible to propose a plan that avoids crowds to a user who is easily stressed, or a plan that includes event information to a user who wants to get excited.

[1198] Sending a response

[1199] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[1200] Terminal handling

[1201] User Interface Display

[1202] The terminal provides an interface for users to input their destination and schedule, and an intuitive design is required to make it easy for users to operate.

[1203] Sending input data

[1204] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1205] Receiving and Viewing Plans

[1206] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1207] User Action

[1208] Enter your destination and schedule

[1209] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[1210] Confirmation of proposed plan

[1211] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1212] Local use

[1213] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1214] Specific examples

[1215] As an example, consider a user planning to visit the zoo next weekend. The user uses their device to input "zoo" and "next Sunday at 10 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state, suggesting 9:30 AM as the recommended visit time if the user is prone to stress, and generates an optimal plan that includes a 10% discount coupon for a cafe near the zoo. This plan is then sent to the device, where the user can confirm it, make plans, and visit the zoo. Once there, they can relax comfortably and take a break at the cafe using the coupon.

[1216] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[1217] The processing flow will be explained below.

[1218] Step 1: Data collection

[1219] Server Processing

[1220] The server collects the necessary data from multiple data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data to analyze the user's emotional state. This data is stored in a database on the server.

[1221] Step 2: Cleaning the data

[1222] Server Processing

[1223] The server removes noise and missing values ​​from the collected data, detects and removes outliers, and performs other preprocessing such as filling in missing data to improve the quality of the data.

[1224] Step 3: Feature extraction

[1225] Server Processing

[1226] The server extracts features from the cleaned data that are effective for predicting congestion, such as the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[1227] Step 4: Building a congestion prediction model

[1228] Server Processing

[1229] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[1230] Step 5: Displaying the User Interface

[1231] Terminal handling

[1232] The device provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[1233] Step 6: Enter your destination and schedule

[1234] User Action

[1235] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[1236] Step 7: Submitting input data

[1237] Terminal handling

[1238] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1239] Step 8: Parsing the Request

[1240] Server Processing

[1241] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[1242] Step 9: Use the Emotion Engine

[1243] Server Processing

[1244] The server uses an emotion engine to analyze the user's emotional state, determining their current emotional state (e.g., stressed, relaxed, excited) based on the data they input, their past usage history, and their real-time reaction data.

[1245] Step 10: Run congestion forecast

[1246] Server Processing

[1247] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[1248] Step 11: Generate optimal plan

[1249] Server Processing

[1250] The server generates optimal outing plans for users based on the congestion prediction results and the analysis results of the emotion engine. For example, it generates a plan that avoids crowds for users who are easily stressed, and a plan that includes event information for users who want to get excited.

[1251] Step 12: Add coupons and special offers

[1252] Server Processing

[1253] The server adds coupon information and special offer information to the generated plan. Coupons include discount information that can be used at affiliated stores and services.

[1254] Step 13: Sending the Response

[1255] Server Processing

[1256] The server transmits the generated outing plan to the user's terminal.

[1257] Step 14: Receive and view your plan

[1258] Terminal handling

[1259] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1260] Step 15: Review the proposed plan

[1261] User Action

[1262] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1263] Step 16: Travel to your destination

[1264] User Action

[1265] The user follows the proposed plan and adjusts the timing to head to the destination.

[1266] Step 17: Local use

[1267] User Action

[1268] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[1269] The above are the specific processing steps of this invention. This system allows users to make efficient outing plans that avoid crowds and traffic jams, and furthermore, it is possible to reduce economic losses and psychological burdens by customizing plans based on emotional states.

[1270] Example 2

[1271] 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."

[1272] Conventional congestion prediction and outing plan provision systems provide uniform plans without considering the user's emotional state, making it difficult to alleviate the stress and dissatisfaction felt by users. In addition, many systems collect only a limited number of data types, resulting in low congestion prediction accuracy and making it impossible to respond to the diverse needs of users.

[1273] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting movement data, weather data, and demand forecast data from data sources, means for constructing a congestion prediction model using a generative AI model based on the collected data, means for accepting input of a destination and schedule from a user, means for using an emotion engine to analyze the user's emotional state, means for generating an optimal outing plan taking into account the congestion prediction result and the analysis result of the emotion engine, and means for presenting the generated outing plan to the user. This provides an outing plan customized according to the user's emotional state, enabling a more comfortable and satisfying visiting experience.

[1274] "Data Source" means the information source used to provide travel data, weather data, and demand forecast data.

[1275] "Movement data" is information about the movement of people and things obtained from sensors, cameras, and people flow data measurement devices.

[1276] "Weather data" is information about the weather obtained from a weather forecast service.

[1277] "Demand forecast data" refers to forecast information on demand collected through search engines and social media APIs.

[1278] A "generative AI model" is a model that is generated using artificial intelligence technology and performs predictions and analyses for specific purposes.

[1279] A "congestion prediction model" is a model that uses past data to predict congestion levels at specific locations and time periods.

[1280] An "emotion engine" is a system or algorithm for analyzing a user's emotional state from their input data and past usage history.

[1281] The "optimal outing plan" is a visit plan that is optimal for the user, generated by taking into account the congestion prediction results and the analysis results of the emotion engine.

[1282] "Coupon information" is information that provides discounts on specific services or products.

[1283] "Special offer information" is information other than coupon information about additional services or product offers.

[1284] "Congestion tolerance" is an index that indicates how much congestion a user can tolerate or tolerate at a destination.

[1285] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide customized plans that correspond to the user's emotional state.

[1286] Server Processing

[1287] Data collection

[1288] The server collects movement data, weather data, and demand forecast data from data sources. Specifically, it collects movement data from sensors, cameras, and people flow data measurement devices, obtains weather data using weather forecast service APIs, and collects demand forecast data from search engines and social media APIs. The collected data is stored in the server's database.

[1289] Cleaning the data

[1290] The server detects and removes noise and outliers from the collected data, such as abnormally high values ​​and invalid timestamps. It also improves data quality by imputing missing values ​​using past data or imputation techniques.

[1291] Feature extraction

[1292] The server extracts features from the cleaned data that are effective for predicting congestion. Specifically, it learns user behavior patterns and congestion characteristics by combining factors such as day of the week, time of day, weather, and event information.

[1293] Building a congestion prediction model

[1294] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict future congestion situations with high accuracy.

[1295] Processing user requests

[1296] The server receives destination and schedule information entered by the user from the terminal, and inputs this information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time.

[1297] Use of emotion engine

[1298] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. For example, it determines whether the user is feeling stressed based on their recent social media posts and history.

[1299] Generating an optimal plan

[1300] The server generates an optimal outing plan for the user based on the congestion prediction results and the emotion engine's analysis results. The plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers. For example, for a user who is prone to stress, a plan is proposed that includes visit times that avoid crowds and relaxing spots.

[1301] Sending a response

[1302] The server transmits the generated outing plan to the terminal and presents it to the user.

[1303] Terminal handling

[1304] User Interface Display

[1305] The terminal provides an interface for users to input their destination and schedule, and the interface is designed to be intuitive and easy to operate.

[1306] Sending input data

[1307] The device sends the destination and schedule data entered by the user to the server, which checks the format and consistency of the data and prompts the user to make corrections if necessary.

[1308] Receiving and Viewing Plans

[1309] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes recommended visit times, travel time, congestion information, and details of coupons and special offers.

[1310] User Action

[1311] Enter your destination and schedule

[1312] The user uses the device's interface to input the desired destination and date and time, such as "the zoo" or "next Sunday at 10:00 AM."

[1313] Confirmation of proposed plan

[1314] The user can check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. For example, they can check a plan to visit the zoo at 9:30 in the morning and use a discount coupon at the cafe.

[1315] Local use

[1316] Users can go to their destination as planned and enjoy a pleasant visit experience by using the coupons and offers provided, for example, visiting the zoo at a less crowded time and relaxing at a cafe using coupons.

[1317] Specific examples

[1318] Example input

[1319] For example, if a user wants to visit the zoo next weekend, the user types:

[1320] "The Zoo" "Next Sunday at 10 AM"

[1321] Processing flow

[1322] 1. The terminal sends the user's input data to the server.

[1323] 2. The server uses the congestion prediction model to predict the congestion situation at 10:00 AM on the following Sunday.

[1324] 3. The server uses an emotion engine to analyze the user's emotional state.

[1325] 4. If the user is prone to stress, the server generates an optimal plan with a recommended visit time of 9:30 AM and a 10% discount coupon for a cafe near the zoo.

[1326] 5. The plan is sent to the device and presented to the user.

[1327] Actual use

[1328] Users can check the proposed plan on their device, visit the zoo, avoid crowds, spend the day comfortably, and take a break at the cafe using coupons.

[1329] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[1330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1331] Step 1: Data collection

[1332] The server collects movement data, weather data, and demand forecast data. Specifically, it obtains movement data from sensors, cameras, and people flow data measurement devices, obtains weather data from weather forecast services using APIs, and collects demand forecast data from search engines and social media APIs. It receives various data from data sources as input and stores it in the server's database as output.

[1333] Step 2: Cleaning the data

[1334] The server detects and removes noise and outliers from the collected data. Specifically, it removes abnormally high values ​​and invalid timestamps from the data. Missing values ​​are imputed using past data or imputation techniques. It receives the collected data as input and generates cleaned data as output.

[1335] Step 3: Feature extraction

[1336] The server extracts features from the cleaned data that are effective for crowd prediction. Specifically, it combines factors such as the day of the week, time of day, weather, and event information. It receives the cleaned data as input and generates feature data as output to be input into the crowd prediction model.

[1337] Step 4: Building a congestion prediction model

[1338] The server uses a generative AI model to build a congestion prediction model based on the extracted features. Specifically, it learns from past data and generates a model that can predict future congestion situations. It receives feature data as input and generates a completed congestion prediction model as output.

[1339] Step 5: Receiving a user request

[1340] The server receives the destination and schedule information entered by the user from the terminal. The information entered by the user into the terminal (e.g., "Zoo" and "Next Sunday at 10:00 AM") is received as input data, and this information is input into the congestion prediction model as output.

[1341] Step 6: Run congestion forecast

[1342] The server inputs the received destination and schedule information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time. The server receives the user's destination and schedule information as input and generates a congestion prediction result as output.

[1343] Step 7: Emotion Engine Analysis

[1344] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. It receives the user's historical data and current data as input and generates the emotion analysis results as output.

[1345] Step 8: Generate an optimal plan

[1346] The server generates an optimal outing plan for the user based on the congestion prediction results and the analysis results of the emotion engine. Specifically, it creates a plan that includes recommended visit times, predicted stay times, congestion information, coupons and special offers. It receives the congestion prediction results and emotion analysis results as input and generates the optimal outing plan as output.

[1347] Step 9: Submit your plan

[1348] The server receives the generated outing plan as input and sends the plan to the terminal as output.

[1349] Step 10: User confirms plan

[1350] The terminal receives the optimal plan sent from the server and displays it to the user. The user checks the suggested visit time and coupon information and makes a plan. The terminal receives plan data from the server as input and displays it to the user as output.

[1351] Step 11: Execute the plan

[1352] The user visits the destination based on the proposed optimal plan. For example, the user visits the zoo at 9:30 in the morning and uses a discount coupon at the cafe. By following the plan as input, the user enjoys a pleasant visiting experience, and by output, the user gets a satisfying experience.

[1353] These are the specific processing steps of this program. At each step, specific data processing and calculations are performed based on the input data, and output is obtained according to the purpose. This allows users to enjoy customized outing plans that avoid crowds and stress.

[1354] (Application example 2)

[1355] 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."

[1356] In modern urban areas and commercial facilities, crowds frequently occur, causing stress and inconvenience to visitors. Furthermore, visitors' emotional state significantly affects the comfort and satisfaction of their visit. However, conventional crowd prediction systems do not take visitors' emotional state into account, making it difficult to provide optimal outing plans. As a result, situations in which visitors feel stressed are often unavoidable. Therefore, the present invention aims to provide a system that combines crowd prediction and visitors' emotional state to provide optimal visit plans for each individual.

[1357] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1358] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for building a congestion prediction model using a generation AI based on the collected data, means for accepting input of a destination and schedule from a user, means for performing congestion prediction based on the input destination and schedule using the prediction model, means for generating an optimal outing plan taking into account the congestion prediction results and the results of user emotion analysis, means for presenting the generated outing plan to the user, means for providing coupon information and special offer information to the user, means for adjusting the congestion tolerance level according to the destination and schedule input by the user, means for analyzing the user's real-time emotional state, and means for capturing the user's emotional state using a camera in smart glasses or a smartphone. This enables the generation of an optimal outing plan based on the congestion prediction results and the results of user emotion analysis.

[1359] A "data source" is a source of data obtained from various sensors and information sources on the Internet.

[1360] "People flow data" is data that shows the movement and stay patterns of people in specific areas or facilities.

[1361] "Weather data" refers to data related to weather, such as temperature, precipitation, and wind speed, obtained from weather information services.

[1362] "Demand forecast data" is data that shows predicted numbers of visitors at a certain location or time period using search engine or social media APIs, etc.

[1363] "Generative AI" is artificial intelligence that uses machine learning and deep learning techniques to analyze data and generate predictive models and plans.

[1364] A "congestion prediction model" is an algorithm or statistical model that uses past data to predict congestion at specific locations and times of day.

[1365] "User emotion analysis" is the process of analyzing a user's emotional state, such as stress, relaxation, or excitement, based on their facial expressions and behavioral data.

[1366] An "outing plan" is a visiting plan that includes the optimal visiting time, required time, route, benefit information, etc. for the user's visiting destinations.

[1367] "Coupon information" is information about discount coupons and service coupons that can be used at specific stores or facilities.

[1368] "Benefit information" is information that provides additional benefits to users, and includes coupons, gifts, and the like.

[1369] "Smart glasses" are wearable devices that have built-in cameras and displays and can acquire and display information in real time.

[1370] A "smartphone" is a mobile device that has mobile phone functions and can connect to the Internet and use applications.

[1371] The "emotional state" indicates the emotion the user is currently feeling, such as stress, relaxation, excitement, etc.

[1372] "Capture" means using a camera or sensor to capture a user's facial expressions and actions as images or video.

[1373] MODE FOR CARRYING OUT THE INVENTION

[1374] This invention relates to a system that predicts congestion and provides an optimal outing plan based on the user's emotional state. This system includes means for collecting various data from data sources, building a congestion prediction model, accepting input of destinations and schedules from users, analyzing their emotions, and generating and presenting an optimal plan.

[1375] Server Processing

[1376] Data collection

[1377] The server collects people flow data, weather data, and demand forecast data from various sensors and online data sources. Specifically, this includes people flow data obtained from sensors and cameras, weather data obtained from weather forecast service APIs, and demand forecast data obtained via search engine and social media APIs. It also collects data on users' emotional states.

[1378] Data cleaning and preprocessing

[1379] The server performs cleaning processes on the collected data to remove noise and missing values. This process includes detecting and removing outliers and filling in missing data. Appropriate preprocessing is performed to improve the quality of the data. This process uses Python's pandas library, etc.

[1380] Feature extraction

[1381] The server extracts features from the cleaned data that are effective for predicting congestion. For example, information such as the day of the week, time of day, weather, and event information is extracted and used for subsequent training of the predictive model. Generative AI (machine learning and deep learning techniques) is used at this stage.

[1382] Building a congestion prediction model

[1383] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and time periods. Libraries such as TensorFlow and scikit-learn are used.

[1384] Use of emotion engine

[1385] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history. Emotional states include stress, relaxation, excitement, etc. Emotion analysis utilizes face recognition and facial expression analysis technologies using OpenCV and TensorFlow.

[1386] Generating an optimal plan

[1387] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information, etc. By taking into account the results of the emotion engine, it is possible to propose plans that avoid crowds to users who are easily stressed, and plans that include event information to users who want to get excited.

[1388] Terminal handling

[1389] User Interface Display

[1390] The device provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. A smartphone app or smart glasses interface is used.

[1391] Sending input data

[1392] The device sends the destination and schedule data entered by the user to the server. At this time, the data is checked for consistency and the user is prompted to make corrections if necessary. Data transmission uses the HTTP protocol and RESTful API.

[1393] Receiving and Viewing Plans

[1394] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1395] User Action

[1396] Enter your destination and schedule

[1397] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[1398] Confirmation of proposed plan

[1399] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1400] Local use

[1401] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1402] Specific examples

[1403] For example, consider a user planning to visit a shopping mall next weekend. Using their smartphone, the user inputs "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to a server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state. If the user is prone to stress, the system suggests 9:30 AM as the recommended time to visit, and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is then sent to the device, where the user can review it and plan their visit.

[1404] This invention allows users to be free from crowds and stress and enjoy plans customized to their emotional state. An example of a specific prompt is, "Please create a program that generates the optimal outing plan based on the user's destinations, visiting times, and detected emotional data."

[1405] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1406] Step 1: Collect data

[1407] The server collects people flow data, weather data, and demand forecast data from data sources. Inputs include various sensors and cameras, weather forecast service APIs, search engines, and social media APIs. These data are stored in a database on the server. To use this data for analysis, a data collection process is executed, and the collected data is obtained as output.

[1408] Step 2: Clean and preprocess the data

[1409] The server performs cleaning processing to remove noise and missing values ​​from the data collected in step 1. This includes detecting and removing outliers and completing missing data. Specifically, it uses the Python pandas library to shape and improve the quality of the data. The input is the collected data, and the output is cleaned, high-quality data.

[1410] Step 3: Feature extraction

[1411] The server extracts features from the cleaned data that are effective for predicting congestion. These include the day of the week, time of day, weather, and event information. This uses generative AI to select important features. The input is the cleaned data, and the output is the extracted features. These features are then used for model training.

[1412] Step 4: Building a congestion prediction model

[1413] The server builds a congestion prediction model using the features extracted in step 3. In this process, a generative AI model (using TensorFlow, scikit-learn, etc.) is trained to create a model that can predict congestion at specific locations and time periods based on past data. The input is feature data, and the output is a congestion prediction model.

[1414] Step 5: User sentiment analysis

[1415] The server and device capture the user's real-time emotional state using the smart glasses or smartphone camera. The device captures the user's facial expressions and analyzes them using an emotion engine (using OpenCV and TensorFlow). The input to this process is real-time image data, and the output is the user's emotional state. The analysis results are sent to the server.

[1416] Step 6: Accepting input from the user

[1417] The terminal provides an interface for users to input the destinations and visit times they plan to visit. The input is the destination and schedule data entered by the user through the terminal, which is checked for consistency and sent to the server. The output is the input data sent to the server.

[1418] Step 7: Run congestion forecast

[1419] The server uses the congestion prediction model to predict the congestion status at the destination and visiting time based on the input data received in step 6. The input is the target destination and schedule data, and the output is the predicted congestion status.

[1420] Step 8: Generate an optimal plan

[1421] The server generates an optimal outing plan taking into account the results of crowd prediction and sentiment analysis. The plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. The inputs are the crowd prediction results and sentiment analysis results, and the output is an optimal outing plan.

[1422] Step 9: Present your plan

[1423] The terminal presents the optimal plan sent from the server to the user. The input received by the terminal is the generated outing plan, and the output is the plan displayed to the user, allowing the user to check and refer to the plan.

[1424] Step 10: Local use

[1425] The user follows the presented plan to reach the destination and uses the offered coupons and special offers. The input is the optimal plan and coupon information, and the output is the user's actual visit experience. The user can enjoy a comfortable and efficient visit.

[1426] 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.

[1427] 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.

[1428] 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.

[1429] [Fourth embodiment]

[1430] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1431] 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.

[1432] 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).

[1433] 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.

[1434] 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.

[1435] 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).

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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."

[1443] The present invention relates to a system that predicts congestion and provides optimal outing plans, in which a server, a terminal, and a user operate in cooperation with each other. Specific embodiments of the system will be described below.

[1444] Server Processing

[1445] Data collection

[1446] The server collects multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[1447] Data processing and predictive model building

[1448] The server cleans the collected data, removing noise and missing values. It then extracts useful features and uses generative AI to build a congestion prediction model. This model can predict congestion in specific areas or facilities with high accuracy.

[1449] Processing user requests

[1450] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[1451] Generating an optimal plan

[1452] The server generates an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[1453] Sending a response

[1454] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[1455] Terminal handling

[1456] User Interface Display

[1457] The device provides an interface for users to input their destinations and schedules, and must be designed to be intuitive so that users can easily operate it.

[1458] Sending input data

[1459] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1460] Receiving and Viewing Plans

[1461] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1462] User Action

[1463] Enter your destination and schedule

[1464] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[1465] Confirmation of proposed plan

[1466] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1467] Local use

[1468] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1469] Specific examples

[1470] As an example, let's consider a case where a user wants to visit the zoo next weekend. The user uses the device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, and the user confirms it, makes plans, and visits the zoo. Once at the zoo, the user can relax comfortably and take a break at the cafe using the coupon.

[1471] The above is a specific embodiment of the present invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[1472] The processing flow will be explained below.

[1473] Step 1: Data collection

[1474] Server Processing

[1475] The server collects the necessary data from multiple data sources: people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. This data is then stored in a database on the server.

[1476] Step 2: Cleaning the data

[1477] Server Processing

[1478] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[1479] Step 3: Feature extraction

[1480] Server Processing

[1481] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[1482] Step 4: Building a congestion prediction model

[1483] Server Processing

[1484] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[1485] Step 5: Displaying the User Interface

[1486] Terminal handling

[1487] The terminal provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[1488] Step 6: Enter your destination and schedule

[1489] User Action

[1490] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[1491] Step 7: Submitting input data

[1492] Terminal handling

[1493] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1494] Step 8: Parsing the Request

[1495] Server Processing

[1496] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[1497] Step 9: Run congestion forecast

[1498] Server Processing

[1499] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[1500] Step 10: Generate optimal plan

[1501] Server Processing

[1502] The server generates an optimal outing plan for the user based on the congestion prediction results, which includes recommended visit times, predicted stay times, congestion information, coupons, and special offers.

[1503] Step 11: Sending the Response

[1504] Server Processing

[1505] The server transmits the generated outing plan to the user's terminal.

[1506] Step 12: Receive and view your plan

[1507] Terminal handling

[1508] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1509] Step 13: Review the proposed plan

[1510] User Action

[1511] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1512] Step 14: Travel to your destination

[1513] User Action

[1514] The user follows the proposed plan and adjusts the timing to head to the destination.

[1515] Step 15: Local use

[1516] User Action

[1517] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[1518] The above are the specific processing steps of this invention. This system allows users to make efficient travel plans that avoid crowds and traffic jams, thereby reducing economic losses and psychological burdens.

[1519] Example 1

[1520] 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."

[1521] In recent years, increasing congestion at tourist destinations and commercial facilities has made it difficult for visitors to plan appropriate visit times and itineraries to ensure a comfortable stay. Accurate congestion predictions based on real-time changing environmental conditions and people flow data are also required, but current systems are unable to adequately address this. Furthermore, there are insufficient means to provide users with optimal visitor plans to avoid crowds, and specific suggestions for improving user satisfaction are lacking.

[1522] 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.

[1523] In this invention, the server includes: means for collecting people flow data, weather data, and demand forecast data from data sources; means for processing the collected data with a data cleaning tool to remove noise and missing values; and means for extracting effective features from the processed data and constructing a congestion prediction model using a generative AI model. This enables accurate congestion prediction in real time. The server also includes means for accepting input of a destination and schedule from a user via a terminal; means for using a prediction model to perform congestion prediction based on the input destination and schedule; means for generating an optimal outing plan based on the congestion prediction results, including recommended visit time, predicted stay time, congestion information, and coupon information; and means for transmitting and presenting the generated outing plan to the user's terminal. This allows users to plan their visit optimally and enjoy a comfortable visit experience. Furthermore, by further including means for providing coupon information and special offer information to the user, user satisfaction can be further improved. Furthermore, by including means for adjusting congestion tolerance based on the destination and schedule input by the user, it is possible to provide more personalized and optimal outing plans.

[1524] A "data source" is an information source that provides information such as people flow data, weather data, and demand forecast data.

[1525] "People flow data" refers to information about people's movements and stays in specific areas or facilities.

[1526] "Weather data" refers to data that includes meteorological information such as temperature, precipitation, and wind speed.

[1527] "Demand forecast data" is data used to predict the number of visitors and consumption behavior in a specific area or facility.

[1528] A "data cleaning tool" is software or algorithms used to remove noise and missing values ​​from collected data.

[1529] A "generative AI model" is an artificial intelligence model that learns from large amounts of data and makes predictions and generates results. Examples include GPT-4.

[1530] A "congestion prediction model" is a model for predicting congestion conditions at specific locations and times based on people flow data and environmental data.

[1531] A "terminal" is a device that allows a user to input information or receive information from the system. Examples include smartphones and personal computers.

[1532] A "destination" refers to a place or facility that a user wishes to visit.

[1533] "Schedule" refers to the date and time when the user intends to visit.

[1534] "Recommended Visit Time" refers to the optimal time of day for a visit suggested by the system to avoid overcrowding.

[1535] "Predicted stay time" refers to the time the system predicts the user will stay at a destination.

[1536] "Coupon information" refers to information that allows users to receive discounts or benefits at specific locations or services.

[1537] "Special offer information" refers to special offer information other than discounts that users can receive.

[1538] "Congestion tolerance" refers to a standard indicating how much congestion a user can tolerate.

[1539] This invention relates to a system that predicts congestion and provides optimal outing plans, in which the elements of a server, a terminal, and a user work in cooperation with each other.

[1540] Server Processing

[1541] The server functions by collecting data from the internet and specific data providers. Specifically, it uses APIs to continuously obtain people flow data, weather data, and demand forecast data. A database is used to manage the data. This makes it possible to grasp congestion conditions and weather fluctuations in real time. Examples of APIs that can be used include Google API and Weather API.

[1542] The server uses a data cleaning tool (e.g., Pandas) to remove noise and missing values ​​from the collected data. Next, it uses a machine learning library (e.g., scikit-learn) to extract useful features. Based on this data, it uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. This predictive model can predict the congestion situation in specific areas or facilities with high accuracy.

[1543] The server receives destination and schedule information entered by the user through the device. The received information is converted into a prompt to be input into the generative AI model. For example, if a user enters "zoo" and "next Sunday at 10:00 AM," the prompt will be in the format "Please predict the crowding situation at the zoo at 10:00 AM next Sunday."

[1544] Based on this, the server uses a prediction model to predict congestion and generate an optimal outing plan including recommended visit times, predicted stay times, congestion information, and coupon information. This plan is sent to the user's device as an API response.

[1545] Terminal handling

[1546] The terminal provides an interface for users to input their destination and schedule. An intuitive design is required to make it easy for users to operate. The input data is validated using a consistency check tool (e.g., regular expressions). The validated data is then sent to the server as an API request.

[1547] Once the optimal plan sent from the server is received by the terminal, it is displayed in a user-friendly format, including visit times, travel times, congestion information, coupon details, and more.

[1548] User Action

[1549] Users input their destination and desired date and time of visit through the device interface. Next, they check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. They then head to their destination according to the plan and enjoy a comfortable visit experience by using coupons and special offers offered on site.

[1550] Specific examples

[1551] For example, if a user plans to visit the zoo next weekend, they use their device to input "zoo" and "next Sunday at 10:00 AM." The device sends this data to the server. The server uses a crowd prediction model (GPT-4) based on the most recent data to predict how crowded the zoo will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended visit time and generates an optimal plan that also includes a 10% discount coupon for a cafe near the zoo. This plan is sent to the device, where the user confirms it, makes plans, and visits the zoo. Once there, they make themselves comfortable and use the coupon to take a break at the cafe.

[1552] This allows users to plan their trips efficiently, avoiding crowds and traffic jams, and reducing financial losses and psychological burdens.

[1553] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1554] Server Processing

[1555] Step 1: Data collection

[1556] The server collects people flow data, weather data, and demand forecast data from each data source. Specifically, it obtains these data from the Internet using APIs. For example, it collects people flow data from Google API and weather data from Weather API. The input is raw data obtained from the data source, and the output is the initial data stored in the database.

[1557] Step 2: Data cleaning

[1558] The server performs data cleaning on the collected data. Specifically, it uses a data cleaning tool (e.g., Pandas) to remove noise and missing values. The input is the initial data stored in the database, and the output is the cleaned data.

[1559] Step 3: Feature extraction

[1560] The server extracts useful features from the cleaned data. It uses a machine learning library (e.g., scikit-learn) to select features and prepares the data required for prediction. The input is the cleaned data, and the output is a dataset with extracted features.

[1561] Step 4: Building a predictive model

[1562] The server uses a generative AI model (e.g., GPT-4) to build a congestion prediction model. It trains the model based on the extracted features and saves the trained model. The input is the dataset from which the features have been extracted, and the output is the trained prediction model.

[1563] Step 5: Processing User Requests

[1564] The server receives the destination and schedule information sent from the user's device and converts the received information into a prompt format for input to the generative AI model. The input is the request data from the user, and the output is data in the prompt format.

[1565] Step 6: Run congestion forecast

[1566] The server inputs prompts into the prediction model to predict congestion. The generative AI model obtains the prediction results and derives recommended visit times and congestion information. The input is prompt-format data, and the output is the congestion prediction results.

[1567] Step 7: Generate an optimal plan

[1568] The server generates an optimal outing plan based on the prediction results. This plan includes recommended visit times, predicted stay times, congestion information, and coupon information. The input is the congestion prediction results, and the output is the optimal plan.

[1569] Step 8: Submit your plan

[1570] The server sends the generated optimal plan to the user's device as an API response. The input is the optimal plan, and the output is the plan sent to the user's device.

[1571] Terminal handling

[1572] Step 1: Displaying the User Interface

[1573] The device displays an interface for users to input their destination and schedule. Specifically, it provides an intuitive UI (user interface) that includes an input form. The input is the destination and schedule information entered by the user, and the output is the input form displayed on the screen.

[1574] Step 2: Submitting input data

[1575] The terminal checks the consistency of the destination and schedule information entered by the user before sending it to the server. A consistency check tool (e.g., regular expressions) is used. The input is the destination and schedule information entered by the user, and the output is the data sent to the server.

[1576] Step 3: Receive and view your plan

[1577] The terminal receives the optimal plan sent from the server and displays it to the user. Specifically, it displays an interface that includes visit time, required time, congestion information, and coupon information. The input is the optimal plan sent from the server, and the output is the plan displayed to the user.

[1578] User Action

[1579] Step 1: Enter your destination and schedule

[1580] The user inputs the destination and date / time they wish to visit through the terminal interface. The input is the destination and the date / time they wish to visit, and the output is the data entered into the terminal.

[1581] Step 2: Confirm the proposed plan

[1582] The user checks the optimal plan displayed on the terminal and makes a plan based on the recommended visit time and coupon information. The input is the optimal plan displayed on the terminal, and the output is the plan confirmed by the user.

[1583] Step 3: Local use

[1584] The user heads to the destination according to the plan, uses the provided coupons and special offers, and enjoys a pleasant visiting experience. The input is the optimal plan, and the output is the actual visiting experience.

[1585] (Application example 1)

[1586] 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."

[1587] In recent years, congestion in urban areas and tourist destinations has become a problem, creating a need for ways to ensure visitors can spend their time comfortably. Physical stores and tourist facilities also need to provide information to encourage visits while avoiding customer concentration. Conventional technologies are often ineffective for users, as they are unable to adequately predict congestion or suggest optimal visit times. Furthermore, coupons and special offer information are often provided individually, making centralized management difficult. A new system is needed to solve these issues.

[1588] 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.

[1589] In this invention, the server includes means for collecting people flow data, weather data, and demand forecast data from data sources, means for using a generation AI to build a congestion prediction model based on the collected data, means for accepting input of a destination and schedule from a user, means for using the prediction model to perform congestion prediction based on the input destination and schedule, means for generating an optimal outing plan taking into account the congestion prediction results, means for presenting the generated outing plan to the user, and means for notifying the user of visiting times and special offer information. This allows the user to visit destinations efficiently while avoiding crowds, and at the same time allows the user to use centrally managed coupons and special offer information.

[1590] A "data source" is a source of data from which the system obtains information. Specifically, this includes data such as people flow data, weather data, and demand forecast data.

[1591] "People flow data" is information recorded on the movements and stays of people in specific areas or facilities. This information can be used to predict congestion situations.

[1592] "Weather Data" means information about weather fluctuations, including temperature, precipitation, wind speed, etc.

[1593] "Demand forecast data" is statistical information used to predict future demand. This includes past sales data and event information.

[1594] "Generative AI" refers to algorithms that use artificial intelligence techniques to achieve specific goals. In this case, it is used to build congestion prediction models.

[1595] A "congestion prediction model" is a model that predicts future congestion conditions in specific areas or facilities based on people flow data, weather data, and demand forecast data.

[1596] A "destination" is a place or facility that the user wishes to visit.

[1597] "Schedule" is information about the date and time when the user plans to visit.

[1598] An "outing plan" is a plan created by a user based on the congestion prediction results, taking into consideration the optimal visiting time and special offer information.

[1599] "Visiting time" refers to the optimal time for a user to visit a destination.

[1600] "Special offer information" is information such as discounts and coupons available at the destination and its surrounding areas.

[1601] "Presenting" refers to the act of displaying the generated outing plan and benefit information to the user.

[1602] "Notification" is the act of conveying important information such as visiting times and special offers to users in real time.

[1603] The present invention relates to a system that predicts congestion and provides optimal outing plans, and is a system in which the elements of a server, a terminal, and a user work in cooperation with each other.

[1604] Server Processing

[1605] Data collection

[1606] The server has the means to collect multiple types of data from data sources. Specifically, it continuously obtains people flow data, weather data, demand forecast data, etc. from the Internet and specific data provider services. This makes it possible to grasp congestion conditions and weather fluctuations in real time.

[1607] Data processing and predictive model building

[1608] The server cleans the collected data, removing noise and missing values. Based on the collected data, a congestion prediction model is built using generative AI. This model can predict congestion situations in specific areas or facilities with high accuracy. Specifically, this includes data preprocessing using Python and processes related to the training and prediction of the generative AI model.

[1609] Processing user requests

[1610] The server receives destination and schedule information entered by the user through their device. The server analyzes this information and inputs it into a predictive model to predict congestion at the time of the planned visit. This involves retrieving data using various APIs and processing the database.

[1611] Generate and present optimal plans

[1612] The server has a means to generate an optimal outing plan for the user based on the congestion prediction results. This plan includes recommended visit times, predicted stay times, congestion information, coupon and special offer information. The generated outing plan is sent to the application to be presented to the user. Python, Flask / Django, etc. are used to generate the specific plan.

[1613] Terminal handling

[1614] User Interface Display

[1615] The device has a means to provide an interface for users to input their destinations and schedules. An intuitive design is required to make it easy for users to operate. A smartphone application is an example of this.

[1616] Sending input data

[1617] The device sends the destination and schedule data entered by the user to the server, which checks the data for consistency and prompts the user to make corrections if necessary. The transmission involves an internet connection and an API call.

[1618] Receiving and Viewing Plans

[1619] The device receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons, and special offers. The actual display is done on the smartphone screen.

[1620] User Action

[1621] Enter your destination and schedule

[1622] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[1623] Confirmation of proposed plan

[1624] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1625] Local use

[1626] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1627] Specific examples

[1628] As an example, let's consider the case where a user plans to visit a shopping mall next weekend. The user uses a device to input "shopping mall" and "next Sunday at 10:00 AM." The device sends this data to the server, which uses a congestion prediction model based on the most recent data to predict how crowded the mall will be at 10:00 AM next Sunday. The server then suggests "9:30 AM" as the recommended time to visit and generates an optimal plan that also includes a 10% discount coupon for a cafe near the mall. This plan is sent to the device, and the user confirms it, makes plans, and visits the shopping mall. Once there, the user can enjoy a comfortable stay and take a break at the cafe using the coupon.

[1629] Prompt Sentence Examples

[1630] Below is an example of a prompt when a user plans to visit a shopping mall:

[1631] "Generate an outing plan that includes the optimal visit time and coupon information based on the user's input data in the following format. For example, the physical store the user wants to visit is a "shopping mall," and the planned date is "November 5, 2023, 10:00 AM."

[1632] The above is a specific embodiment of the present invention. This system allows users to avoid crowds and make efficient outing plans, thereby reducing economic losses and psychological burdens.

[1633] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1634] Step 1:

[1635] The server continuously collects people flow data, weather data, and demand forecast data from data sources. Specifically, the server accesses the Internet or specific data provider services and sends API requests to obtain the latest data. This data is stored in a database on the server. The input is information from the data source, and the output is the collected data.

[1636] Step 2:

[1637] The server cleans the collected data and removes noise and missing values. Specifically, it preprocesses the data using Python libraries (e.g., pandas, numpy). The clean dataset obtained in this way is used to extract useful features. The input is the collected data, and the output is the cleaned data.

[1638] Step 3:

[1639] The server uses generative AI to build a congestion prediction model based on the cleaned data. Specifically, it trains the model using a machine learning library (e.g., TensorFlow, Scikit-learn). The trained model is stored in a database and used for prediction processing. The input is the cleaned data, and the output is the congestion prediction model.

[1640] Step 4:

[1641] The user inputs the destination and the planned date and time of the visit using a terminal (such as a smartphone). The terminal provides an intuitive user interface and sends the input data to the server. The input is the destination and schedule entered by the user, and the output is the data sent to the server.

[1642] Step 5:

[1643] The server inputs the destination and schedule information received from the user into a prediction model to predict the congestion situation at the time of the planned visit. The server analyzes the prediction results and generates an optimal outing plan including recommended visit times and congestion information. The input is the user's destination and schedule, and the output is the generated outing plan.

[1644] Step 6:

[1645] The server sends the generated outing plan to the device. This includes the planned visit time, estimated stay time, congestion information, coupon and special offer information. The server converts the data into an appropriate format and sends it to the device using an API. The input is the generated outing plan, and the output is the transmitted data.

[1646] Step 7:

[1647] The terminal receives the outing plan sent from the server and displays it to the user. The user checks the plan and makes a plan based on the optimal visiting time and coupon information. The input is the outing plan sent from the server, and the output is the information displayed to the user.

[1648] Step 8:

[1649] The user follows the plan to reach the destination and uses the coupons and special offers provided. The user enjoys a pleasant visiting experience at the destination. The input is the user's action plan, and the output is the visiting experience.

[1650] 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.

[1651] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide a customized plan tailored to the user's emotional state. Specific embodiments of this system are described below.

[1652] Server Processing

[1653] Data collection

[1654] The server collects multiple types of data from data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data on users' emotional states. This data is stored in a database on the server.

[1655] Cleaning the data

[1656] The server removes noise and missing values ​​from the collected data, including detecting and removing outliers, imputing missing data, etc. It also performs appropriate preprocessing to improve the quality of the data.

[1657] Feature extraction

[1658] The server extracts features from the cleaned data that are effective for predicting congestion, such as information on the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[1659] Building a congestion prediction model

[1660] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[1661] Processing user requests

[1662] The server receives destination and schedule information entered by the user through their device, analyzes this information, and inputs it into a prediction model to predict congestion at the time of the planned visit.

[1663] Use of emotion engine

[1664] The server uses an emotion engine to analyze the user's emotional state based on the data entered by the user and their past usage history, which can include stress, relaxation, excitement, etc.

[1665] Generating an optimal plan

[1666] The server generates an optimal outing plan for the user based on the crowd prediction results and the analysis results of the emotion engine. This plan includes recommended visit times, predicted stay times, crowd information, coupon and special offer information. By taking the results of the emotion engine into consideration, it is possible to propose a plan that avoids crowds to a user who is easily stressed, or a plan that includes event information to a user who wants to get excited.

[1667] Sending a response

[1668] The server transmits the generated outing plan to the user's terminal and presents it to the user.

[1669] Terminal handling

[1670] User Interface Display

[1671] The terminal provides an interface for users to input their destination and schedule, and an intuitive design is required to make it easy for users to operate.

[1672] Sending input data

[1673] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1674] Receiving and Viewing Plans

[1675] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1676] User Action

[1677] Enter your destination and schedule

[1678] The user inputs the destination and the date and time they wish to visit through the terminal interface.

[1679] Confirmation of proposed plan

[1680] The user checks the optimal plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1681] Local use

[1682] Users can travel to their destination according to their plan and take advantage of the coupons and special offers provided, allowing them to enjoy a comfortable and efficient visiting experience.

[1683] Specific examples

[1684] As an example, consider a user planning to visit the zoo next weekend. The user uses their device to input "zoo" and "next Sunday at 10 AM." The device sends this data to the server, which uses a crowd prediction model based on the most recent data to predict how crowded the zoo will be at 10 AM next Sunday. The server then uses an emotion engine to analyze the user's emotional state, suggesting 9:30 AM as the recommended visit time if the user is prone to stress, and generates an optimal plan that includes a 10% discount coupon for a cafe near the zoo. This plan is then sent to the device, where the user can confirm it, make plans, and visit the zoo. Once there, they can relax comfortably and take a break at the cafe using the coupon.

[1685] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[1686] The processing flow will be explained below.

[1687] Step 1: Data collection

[1688] Server Processing

[1689] The server collects the necessary data from multiple data sources. Specifically, it obtains people flow data from sensors and cameras, weather data from weather forecast service APIs, and demand forecast data from search engines and social media APIs. It also collects data to analyze the user's emotional state. This data is stored in a database on the server.

[1690] Step 2: Cleaning the data

[1691] Server Processing

[1692] The server removes noise and missing values ​​from the collected data, detects and removes outliers, and performs other preprocessing such as filling in missing data to improve the quality of the data.

[1693] Step 3: Feature extraction

[1694] Server Processing

[1695] The server extracts features from the cleaned data that are effective for predicting congestion, such as the day of the week, time of day, weather, and event information, and uses this information to train a predictive model.

[1696] Step 4: Building a congestion prediction model

[1697] Server Processing

[1698] The server uses generative AI to build a congestion prediction model based on the extracted features. This model learns from past data and can predict congestion levels at specific locations and times of day.

[1699] Step 5: Displaying the User Interface

[1700] Terminal handling

[1701] The device provides an interface that allows users to input their destination and schedule. The screen is designed intuitively to make it easy for users to operate.

[1702] Step 6: Enter your destination and schedule

[1703] User Action

[1704] The user uses the terminal interface to input the location they want to go to and the date and time they want to visit.

[1705] Step 7: Submitting input data

[1706] Terminal handling

[1707] The device sends the destination and schedule data entered by the user to the server, where it checks the data for consistency and prompts the user to make corrections if necessary.

[1708] Step 8: Parsing the Request

[1709] Server Processing

[1710] The server analyzes the data sent by the user and prepares to predict the destination and congestion at the planned time of visit based on this information.

[1711] Step 9: Use the Emotion Engine

[1712] Server Processing

[1713] The server uses an emotion engine to analyze the user's emotional state, determining their current emotional state (e.g., stressed, relaxed, excited) based on the data they input, their past usage history, and their real-time reaction data.

[1714] Step 10: Run congestion forecast

[1715] Server Processing

[1716] The server uses the congestion prediction model to predict the congestion level at the destination on the date and time the user plans to visit, and the prediction result is customized based on individual user information.

[1717] Step 11: Generate optimal plan

[1718] Server Processing

[1719] The server generates optimal outing plans for users based on the congestion prediction results and the analysis results of the emotion engine. For example, it generates a plan that avoids crowds for users who are easily stressed, and a plan that includes event information for users who want to get excited.

[1720] Step 12: Add coupons and special offers

[1721] Server Processing

[1722] The server adds coupon information and special offer information to the generated plan. Coupons include discount information that can be used at affiliated stores and services.

[1723] Step 13: Sending the Response

[1724] Server Processing

[1725] The server transmits the generated outing plan to the user's terminal.

[1726] Step 14: Receive and view your plan

[1727] Terminal handling

[1728] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes details of the visit time, required time, congestion information, coupons and special offers.

[1729] Step 15: Review the proposed plan

[1730] User Action

[1731] The user checks the plan displayed on the terminal and makes a plan based on the suggested visit time and coupon information.

[1732] Step 16: Travel to your destination

[1733] User Action

[1734] The user follows the proposed plan and adjusts the timing to head to the destination.

[1735] Step 17: Local use

[1736] User Action

[1737] After arriving, users can use the provided coupon information to spend a comfortable time at their destination, and also enjoy their trip while avoiding crowds by following the plan.

[1738] The above are the specific processing steps of this invention. This system allows users to make efficient outing plans that avoid crowds and traffic jams, and furthermore, it is possible to reduce economic losses and psychological burdens by customizing plans based on emotional states.

[1739] Example 2

[1740] 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."

[1741] Conventional congestion prediction and outing plan provision systems provide uniform plans without considering the user's emotional state, making it difficult to alleviate the stress and dissatisfaction felt by users. In addition, many systems collect only a limited number of data types, resulting in low congestion prediction accuracy and making it impossible to respond to the diverse needs of users.

[1742] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting movement data, weather data, and demand forecast data from data sources, means for constructing a congestion prediction model using a generative AI model based on the collected data, means for accepting input of a destination and schedule from a user, means for using an emotion engine to analyze the user's emotional state, means for generating an optimal outing plan taking into account the congestion prediction result and the analysis result of the emotion engine, and means for presenting the generated outing plan to the user. This provides an outing plan customized according to the user's emotional state, enabling a more comfortable and satisfying visiting experience.

[1743] "Data Source" means the information source used to provide travel data, weather data, and demand forecast data.

[1744] "Movement data" is information about the movement of people and things obtained from sensors, cameras, and people flow data measurement devices.

[1745] "Weather data" is information about the weather obtained from a weather forecast service.

[1746] "Demand forecast data" refers to forecast information on demand collected through search engines and social media APIs.

[1747] A "generative AI model" is a model that is generated using artificial intelligence technology and performs predictions and analyses for specific purposes.

[1748] A "congestion prediction model" is a model that uses past data to predict congestion levels at specific locations and time periods.

[1749] An "emotion engine" is a system or algorithm for analyzing a user's emotional state from their input data and past usage history.

[1750] The "optimal outing plan" is a visit plan that is optimal for the user, generated by taking into account the congestion prediction results and the analysis results of the emotion engine.

[1751] "Coupon information" is information that provides discounts on specific services or products.

[1752] "Special offer information" is information other than coupon information about additional services or product offers.

[1753] "Congestion tolerance" is an index that indicates how much congestion a user can tolerate or tolerate at a destination.

[1754] This invention combines a system that predicts congestion and provides optimal outing plans with an emotion engine that recognizes the user's emotions. The server, terminal, and user elements work together to provide customized plans that correspond to the user's emotional state.

[1755] Server Processing

[1756] Data collection

[1757] The server collects movement data, weather data, and demand forecast data from data sources. Specifically, it collects movement data from sensors, cameras, and people flow data measurement devices, obtains weather data using weather forecast service APIs, and collects demand forecast data from search engines and social media APIs. The collected data is stored in the server's database.

[1758] Cleaning the data

[1759] The server detects and removes noise and outliers from the collected data, such as abnormally high values ​​and invalid timestamps. It also improves data quality by imputing missing values ​​using past data or imputation techniques.

[1760] Feature extraction

[1761] The server extracts features from the cleaned data that are effective for predicting congestion. Specifically, it learns user behavior patterns and congestion characteristics by combining factors such as day of the week, time of day, weather, and event information.

[1762] Building a congestion prediction model

[1763] The server uses a generative AI model to build a congestion prediction model based on the extracted features. This model learns from past data and can predict future congestion situations with high accuracy.

[1764] Processing user requests

[1765] The server receives destination and schedule information entered by the user from the terminal, and inputs this information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time.

[1766] Use of emotion engine

[1767] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. For example, it determines whether the user is feeling stressed based on their recent social media posts and history.

[1768] Generating an optimal plan

[1769] The server generates an optimal outing plan for the user based on the congestion prediction results and the emotion engine's analysis results. The plan includes recommended visit times, predicted stay times, congestion information, coupons, and special offers. For example, for a user who is prone to stress, a plan is proposed that includes visit times that avoid crowds and relaxing spots.

[1770] Sending a response

[1771] The server transmits the generated outing plan to the terminal and presents it to the user.

[1772] Terminal handling

[1773] User Interface Display

[1774] The terminal provides an interface for users to input their destination and schedule, and the interface is designed to be intuitive and easy to operate.

[1775] Sending input data

[1776] The device sends the destination and schedule data entered by the user to the server, which checks the format and consistency of the data and prompts the user to make corrections if necessary.

[1777] Receiving and Viewing Plans

[1778] The terminal receives the optimized plan sent from the server and displays it to the user. The plan includes recommended visit times, travel time, congestion information, and details of coupons and special offers.

[1779] User Action

[1780] Enter your destination and schedule

[1781] The user uses the device's interface to input the desired destination and date and time, such as "the zoo" or "next Sunday at 10:00 AM."

[1782] Confirmation of proposed plan

[1783] The user can check the optimal plan displayed on the device and make a plan based on the suggested visit time and coupon information. For example, they can check a plan to visit the zoo at 9:30 in the morning and use a discount coupon at the cafe.

[1784] Local use

[1785] Users can go to their destination as planned and enjoy a pleasant visit experience by using the coupons and offers provided, for example, visiting the zoo at a less crowded time and relaxing at a cafe using coupons.

[1786] Specific examples

[1787] Example input

[1788] For example, if a user wants to visit the zoo next weekend, the user types:

[1789] "The Zoo" "Next Sunday at 10 AM"

[1790] Processing flow

[1791] 1. The terminal sends the user's input data to the server.

[1792] 2. The server uses the congestion prediction model to predict the congestion situation at 10:00 AM on the following Sunday.

[1793] 3. The server uses an emotion engine to analyze the user's emotional state.

[1794] 4. If the user is prone to stress, the server generates an optimal plan with a recommended visit time of 9:30 AM and a 10% discount coupon for a cafe near the zoo.

[1795] 5. The plan is sent to the device and presented to the user.

[1796] Actual use

[1797] Users can check the proposed plan on their device, visit the zoo, avoid crowds, spend the day comfortably, and take a break at the cafe using coupons.

[1798] The above is a specific embodiment of the present invention. This system not only allows users to avoid crowds and traffic jams, but also allows them to enjoy a customized plan according to their emotional state, resulting in a more comfortable visiting experience.

[1799] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1800] Step 1: Data collection

[1801] The server collects movement data, weather data, and demand forecast data. Specifically, it obtains movement data from sensors, cameras, and people flow data measurement devices, obtains weather data from weather forecast services using APIs, and collects demand forecast data from search engines and social media APIs. It receives various data from data sources as input and stores it in the server's database as output.

[1802] Step 2: Cleaning the data

[1803] The server detects and removes noise and outliers from the collected data. Specifically, it removes abnormally high values ​​and invalid timestamps from the data. Missing values ​​are imputed using past data or imputation techniques. It receives the collected data as input and generates cleaned data as output.

[1804] Step 3: Feature extraction

[1805] The server extracts features from the cleaned data that are effective for crowd prediction. Specifically, it combines factors such as the day of the week, time of day, weather, and event information. It receives the cleaned data as input and generates feature data as output to be input into the crowd prediction model.

[1806] Step 4: Building a congestion prediction model

[1807] The server uses a generative AI model to build a congestion prediction model based on the extracted features. Specifically, it learns from past data and generates a model that can predict future congestion situations. It receives feature data as input and generates a completed congestion prediction model as output.

[1808] Step 5: Receiving a user request

[1809] The server receives the destination and schedule information entered by the user from the terminal. The information entered by the user into the terminal (e.g., "Zoo" and "Next Sunday at 10:00 AM") is received as input data, and this information is input into the congestion prediction model as output.

[1810] Step 6: Run congestion forecast

[1811] The server inputs the received destination and schedule information into a congestion prediction model to predict the congestion situation at the destination on a specific date and time. The server receives the user's destination and schedule information as input and generates a congestion prediction result as output.

[1812] Step 7: Emotion Engine Analysis

[1813] The server uses an emotion engine to analyze the user's emotional state based on their input data and past usage history. Specifically, it determines their emotional state, such as stress, relaxation, or excitement. It receives the user's historical data and current data as input and generates the emotion analysis results as output.

[1814] Step 8: Generate an optimal plan

[1815] The server generates an optimal outing plan for the user based on the congestion prediction results and the analysis results of the emotion engine. Specifically, it creates a plan that includes recommended visit times, predicted stay times, congestion information, coupons and special offers. It receives the congestion prediction results and emotion analysis results as input and generates the optimal outing plan as output.

[1816] Step 9: Submit your plan

[1817] The server receives the generated outing plan as input and sends the plan to the terminal as output.

[1818] Step 10: User confirms plan

[1819] The terminal receives the optimal plan sent from the server and displays it to the user. The user checks the suggested visit time and coupon information and makes a plan. The terminal receives plan data from the server as input and displays it to the user as output.

[1820] Step 11: Execute the plan

[1821] The user visits the destination based on the proposed optimal plan. For example, the user visits the zoo at 9:30 in the morning and uses a discount coupon at the cafe. By following the plan as input, the user enjoys a pleasant visiting experience, and by output, the user gets a satisfying experience.

[1822] These are the specific processing steps of this program. At each step, specific data processing and calculations are performed based on the input data, and output is obtained according to the purpose. This allows users to enjoy customized outing plans that avoid crowds and stress. ...

Claims

1. means for collecting people flow data, weather data, and demand forecast data from data sources; A method for building a congestion prediction model using generative AI based on the collected data, and means for receiving input of a destination and a schedule from a user; means for performing congestion prediction based on input destinations and schedules using a prediction model; A means for generating an optimal outing plan taking into account the congestion prediction results; The system includes a means for presenting the generated outing plan to a user.

2. The system of claim 1 further comprising means for providing coupon and special offer information to the user.

3. The system of claim 1 , further comprising means for adjusting congestion tolerance in response to a destination and schedule input by a user.

Images