system

Abstract

Provide a system. A means for acquiring past people flow data; A means for analyzing the acquired people flow data and identifying congestion patterns; means for generating an optimal guide route based on the identified congestion pattern; means for transmitting the generated guidance route to a user's terminal; means for providing real-time information based on the transmitted guidance route; A means of monitoring actual congestion in real time and readjusting the guidance route as necessary. a means for transmitting the readjusted guidance route to the terminals of the guide and the user; A system including:

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] During large-scale events, many people move at the same time, which can easily lead to congestion in certain areas or routes. This congestion poses safety risks to participants, causes stress due to increased travel time, and creates a sense of unfairness. Furthermore, because congestion changes in real time, there is the issue that pre-set fixed guidance routes and layouts alone cannot adequately respond. [Means for solving the problem]

[0005] The present invention provides a means for acquiring and analyzing past people flow data to identify congestion patterns. It also includes a means for generating an optimal guided route based on the identified congestion pattern and a means for transmitting that guided route to the user's device. It also includes a means for providing information in real time, a means for monitoring actual congestion conditions and readjusting the guided route as necessary, and a means for transmitting the readjusted guided route to the devices of guides and users. This provides a system for alleviating congestion during events and improving the safety and travel efficiency of participants.

[0006] "People flow data" refers to information about the movements of event participants, such as their location, movement route, movement speed, and length of stay.

[0007] "Analysis" refers to the process of analyzing collected data using statistical methods and machine learning algorithms to extract specific patterns and trends.

[0008] "Congestion patterns" refer to characteristics that indicate the degree of concentration of people in a particular area or route during a particular time period, as well as fluctuations in inflow and outflow.

[0009] "Guided route" refers to the recommended route for event participants to move smoothly.

[0010] "User Device" refers to a smartphone, tablet, or other mobile information device owned by an Event Participant.

[0011] "Real-time" refers to processing and responding to ongoing events and situations immediately.

[0012] "Monitoring" refers to the continuous observation of specific indicators or data and tracking their trends.

[0013] "Guide" refers to a person whose role is to guide the movement of participants on-site and convey instructions.

[0014] "Readjustment" refers to modifying or changing already planned routes, placements, and other methods in response to changes in the situation. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system that alleviates congestion during events and improves the efficiency of participant movement. This system enables safe and efficient movement of users by having a server collect and analyze past people flow data and generate optimal guide routes. Details of the system and a specific example implementation are provided below.

[0037] System Configuration

[0038] Data collection and analysis

[0039] The server retrieves people flow data (e.g., location information, movement paths, duration of stay, etc.) collected from past events from a database. The collected data is analyzed using analytical tools (e.g., Python's Pandas or Scikit-learn). The server generates indicators such as congestion level, number of people entering and leaving, and average travel time for each time period and each area, and extracts the information necessary for predicting the next event.

[0040] Examples:

[0041] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0042] Generating optimal guidance methods

[0043] The server generates optimal routes based on the analysis to minimize congestion, using AI algorithms (e.g., genetic algorithms and machine learning models), and creates a plan to distribute traffic among routes to balance waiting and travel times across all participants and reduce perceived unfairness.

[0044] Examples:

[0045] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0046] Sending instructions to user terminal

[0047] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[0048] Examples:

[0049] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0050] Guide staff deployment and real-time adjustment

[0051] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[0052] Examples:

[0053] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0054] Program processing

[0055] In this system, the program performs processing in the following procedure.

[0056] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[0057] Analysis of congestion patterns: The server uses analytical tools to identify the level of congestion for each time period and area, and extracts congestion patterns based on that.

[0058] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[0059] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[0060] Real-time adjustment: The server monitors newly collected data and adjusts the guidance routes and the deployment of guidance staff as needed, allowing it to respond to changing congestion conditions in real time.

[0061] As a result, the present invention alleviates congestion during events and improves safety for participants.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The server retrieves people flow data collected from past events from the database, including participant location information, movement paths, stay times, congestion levels, etc. The retrieved data is read using analysis tools (e.g., Python's Pandas or Scikit-learn).

[0065] Step 2:

[0066] The server analyzes the acquired data. Specifically, it calculates the degree of congestion, the number of people entering and leaving, and the average travel time for each time period and each area. Based on the analysis results, it identifies the congestion patterns that will occur in specific areas and routes during the event.

[0067] Step 3:

[0068] Based on the analysis results, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, and plans to distribute participants across multiple routes to balance waiting and travel times for all participants.

[0069] Step 4:

[0070] The server then sends the generated route to each user's device. The route includes real-time travel instructions, congestion information, estimated waiting time, and other information, allowing each user's device to receive individual instructions.

[0071] Step 5:

[0072] The device analyzes the guidance instructions received from the server and notifies the user in real time, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[0073] Step 6:

[0074] The server also sends instructions to on-site guides, including where to position them during specific times and how to change routes depending on congestion levels, enabling appropriate guidance at the site.

[0075] Step 7:

[0076] Users follow the notification from their device and travel along the designated route. Real-time instructions allow users to avoid congestion and reach their destination efficiently.

[0077] Step 8:

[0078] The server monitors newly collected data in real time (for example, user location information and movement speed), which allows the current congestion situation to be continuously grasped.

[0079] Step 9:

[0080] The server analyzes the collected real-time data and adjusts the guidance route and the deployment of guides as necessary. The adjusted guidance route is then sent back to the user's device and the guide.

[0081] Step 10:

[0082] The terminal then notifies the user of the updated instructions, allowing the user to receive route instructions that reflect the latest congestion conditions.

[0083] Through these steps, the system will enable smooth people flow management and congestion relief during events.

[0084] Example 1

[0085] 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."

[0086] During events, large numbers of participants gather in specific areas or routes at the same time, causing congestion that reduces safety, comfort, and travel efficiency. It is important to eliminate this congestion and establish guidance methods that allow participants to move around efficiently and safely. However, conventional methods have difficulty grasping congestion situations in real time and providing appropriate guidance routes based on that information, making them ineffective. Therefore, a system that can solve these issues, efficiently alleviate congestion, and improve safety and comfort is needed.

[0087] 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.

[0088] In this invention, the server includes means for acquiring past people flow data, means for identifying congestion patterns using an analysis tool for analyzing the acquired people flow data, means for generating an optimal guide route using an AI algorithm based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for notifying the user's terminal based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary based on newly collected data, and means for transmitting the readjusted guide route to the terminals of guides and users. This enables real-time understanding of congestion conditions and subsequent rapid and accurate guidance.

[0089] "Past people flow data" refers to information such as the location, movement route, and length of stay of individual users collected at past events.

[0090] "Analysis Tools" refers to software tools used to analyze data, including commonly used data analysis libraries and algorithms.

[0091] A "congestion pattern" indicates the tendency for people to concentrate and move around in a particular time period or area, and is determined based on indicators such as the degree of congestion, the number of people entering and leaving, and average travel time.

[0092] "AI algorithm" refers to a computational method for deriving optimal solutions using artificial intelligence technology, and specifically includes genetic algorithms and machine learning models.

[0093] A "guided route" is a route that a user should follow when moving from one point to another, and is designed to ensure optimal movement.

[0094] "User Device" means an electronic device held by a User that receives and displays instructions and notifications, including a smartphone or tablet.

[0095] "Real-time monitoring" refers to the immediate observation, analysis, and processing of ongoing situations, including the location and speed of users.

[0096] A "guide" refers to a person in charge of guiding participants at the event site, and is responsible for changing their location and route based on instructions from the server.

[0097] This invention relates to a system that alleviates congestion at events and improves the efficiency of participant movement. This system generates optimal guided routes based on past people flow data and readjusts the routes according to real-time congestion conditions, ensuring safe and efficient movement.

[0098] The server connects to a database to retrieve historical people flow data, including location information, movement paths, and dwell times collected during past events. Data is retrieved using standard database queries.

[0099] The server then analyzes the data using Python analysis tools (such as Pandas or Scikit-learn). Specifically, it calculates the congestion level, number of people entering and leaving, and average travel time for each area and time period. To identify congestion patterns, it uses a clustering algorithm (such as K-means) to extract time periods and areas where large-scale congestion occurs.

[0100] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal routes. The algorithms perform calculations to minimize congestion and travel time. The generated routes are designed to balance total travel time and evenly distribute waiting time among all participants.

[0101] The server then sends the generated route guidance to the user's device (smartphone or tablet). The device receives the instructions and notifies the user in real time. The message displayed on the user's device includes specific instructions such as "Turn right at the next intersection. Waiting time: approximately 15 minutes."

[0102] The server also receives real-time location information and movement speed from each device and readjusts the guidance route based on the newly collected data. This process involves collecting real-time data using WebSockets and generating new routes as needed and sending them back to the device.

[0103] The server also sends instructions to traffic controllers to assist them in guiding traffic at specific times and locations. For example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends this to the devices of the traffic controllers and users.

[0104] Specific examples

[0105] Analysis based on data from 8:00 p.m. to 9:00 p.m. at last year's fireworks display predicted that certain routes would be extremely congested, so the server planned to use routes B and C.

[0106] Prompt Sentence Examples

[0107] "Based on data from last year's fireworks display, identify routes that are most congested between 8:00 and 9:00 p.m."

[0108] "Suggest multiple routes that are most efficient at a given time to reduce congestion."

[0109] "Adjust the optimal route based on the user's location information in real time."

[0110] As described above, the present invention alleviates congestion during events and improves safety for participants.

[0111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0112] System program processing flow

[0113] Step 1: Data collection

[0114] The server retrieves people flow data from a database of past events, which stores location information, movement paths, and duration of stays collected from past events.

[0115] Specific behavior:

[0116] The server connects to the database using an SQL query to retrieve data for a specific date: SELECT FROM EventData WHERE Date = '2022-07-30'.

[0117] input:

[0118] People flow data stored in a database.

[0119] output:

[0120] A people flow dataset to be passed to analysis tools.

[0121] Step 2: Data analysis

[0122] The server analyzes the acquired data using Python libraries such as Pandas and Scikit-learn, calculating the congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0123] Specific behavior:

[0124] The server creates a data frame using Pandas and executes "df.groupby(['Area', 'Time']).size()" to calculate the congestion level for each area and time period.

[0125] input:

[0126] Acquired people flow data.

[0127] output:

[0128] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0129] Step 3: Extracting congestion patterns

[0130] The server extracts congestion patterns from the analysis results. Specifically, it identifies specific congestion patterns using a clustering algorithm (e.g., K-means).

[0131] Specific behavior:

[0132] The server uses Scikit-learn to perform clustering using code like "kmeans = KMeans(n_clusters=3).fit(df[['Congestion', 'FlowIn', 'FlowOut']])" to classify congestion patterns.

[0133] input:

[0134] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0135] output:

[0136] Congestion patterns by time of day and area.

[0137] Step 4: Generate optimal guidance path

[0138] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal guidance routes.

[0139] Specific behavior:

[0140] The server uses a genetic algorithm to search for the optimal solution with code like "result = genetic_algorithm.optimize(objective_function, population_size=100, generations=50)".

[0141] input:

[0142] Crowding pattern.

[0143] output:

[0144] Optimal guidance route.

[0145] Step 5: Send instructions

[0146] The server sends the generated guided route to the user's terminal, which analyzes it and notifies the user.

[0147] Specific behavior:

[0148] The server uses the REST API to send the guidance route to the endpoint "POST / send-instructions", and the user's device displays this information.

[0149] input:

[0150] Optimal guidance route.

[0151] output:

[0152] Instructions displayed on the user's device.

[0153] Step 6: Real-time monitoring and readjustment

[0154] The server receives real-time location information and movement speed from the user's device and readjusts the guidance route based on the newly collected data.

[0155] Specific behavior:

[0156] The server collects real-time data via WebSocket and generates new routes as needed and sends them again to the device.

[0157] input:

[0158] Location information and movement speed collected in real time.

[0159] output:

[0160] Realigned guidance path.

[0161] The above is the flow of program processing in this system.

[0162] (Application example 1)

[0163] 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."

[0164] Congestion in large facilities, commercial facilities, and other locations can be a factor that impairs the convenience and safety of users. There is a need to efficiently alleviate congestion caused by the flow of people in each area and time period and provide routes that allow users to move smoothly. However, a system that constantly monitors dynamically changing congestion conditions in real time and proposes optimal guidance routes has not yet been fully developed. It is also important to effectively utilize past congestion data to predict future congestion and develop countermeasures in advance. Therefore, the present invention aims to solve these problems by proposing a system that utilizes past people flow data to provide optimal guidance routes that adapt to dynamically changing congestion conditions in real time.

[0165] 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.

[0166] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data and identifying congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of guides and users, and means for proposing a route that optimizes the flow of users within a commercial facility based on past data. This makes it possible to effectively alleviate congestion within large facilities and commercial facilities and provide an environment in which users can move safely and comfortably.

[0167] "Past people flow data" refers to data including people's movement routes, location information, and duration of stay over a certain period of time in the past.

[0168] "Crowd patterns" are data that indicate the degree of crowding and congestion trends in a particular time period and area.

[0169] An "optimal route" is a recommended route to a specific destination that is generated to minimize congestion and evenly distribute waiting and travel times among users.

[0170] A "user device" is a portable electronic device carried by a user, such as a smartphone or tablet.

[0171] "Means for providing information in real time" refers to a system for instantly transmitting current congestion status and optimal route information to users' terminals.

[0172] "Actual congestion situation" refers to information that indicates the current state of people gathering and their travel routes at events or in everyday life.

[0173] "Guides" are personnel who are deployed on-site to provide instructions to users and support their movement.

[0174] A "commercial facility" is a building or surrounding area where many customers gather and make purchases, such as a shopping mall or department store.

[0175] "Flow lines" refer to the routes and directions that users take when moving within a facility.

[0176] The present invention is a system for optimizing user flow lines and alleviating congestion within large facilities and commercial facilities. This system collects and analyzes past people flow data, generates optimal guidance routes, sends instructions to user terminals, and makes adjustments in real time. Specific embodiments are described below.

[0177] 1. Data Collection and Analysis

[0178] The server retrieves past people flow data from a database. This data includes location information, movement paths, and duration of stay. The server analyzes this data using analytical tools (e.g., Python's Pandas or Scikit-learn) to identify the level of congestion for each time period and each area. This allows the server to extract the information necessary for predictions for the next event and for normal times.

[0179] As a specific example, the server analyzes data from a shopping mall during last year's Christmas season to discover areas that become crowded at specific times.

[0180] 2. Generating optimal guidance routes

[0181] Based on the analysis results, the server generates the optimal route to minimize congestion using AI algorithms (e.g., genetic algorithms and machine learning models). It also creates a plan to distribute passengers across routes to balance waiting time and travel time across all users and reduce unfairness.

[0182] As a specific example, the server generates routes that bypass areas where congestion is expected during specific times of the day, and plans to spread out users during those times.

[0183] 3. Send instructions to the user device

[0184] The server sends the generated route to the user's device, which analyzes the received instructions and notifies the user in real time.

[0185] As a specific example, the user's device may display the message, "Considering the current congestion situation, please turn right at the next intersection. Waiting time: approximately 15 minutes."

[0186] 4. Placement of guides and real-time adjustment

[0187] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[0188] As a specific example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends it to the user's terminal.

[0189] Prompt Sentence Examples

[0190] Design an application that analyzes the most efficient route within a specified shopping mall and notifies the user in real time. Crowd data will be based on past data and analyzed using KMeans clustering. Include specific data and the method of user notification.

[0191] As described above, in the embodiment of the present invention, it is possible to perform everything from past data analysis to real-time congestion management, centered on the server, which effectively alleviates congestion in large facilities and commercial facilities, and provides an environment in which users can move around safely and comfortably.

[0192] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0193] Step 1:

[0194] Data collection

[0195] The server retrieves historical people flow data from a database. This data includes location information, travel paths, and dwell times. The input is the historical data in the database, and the output is a dataset for analysis. Specifically, the server uses SQL queries to extract the required data from the database.

[0196] Step 2:

[0197] Data analysis

[0198] The server analyzes the acquired data using analysis tools (Python's Pandas and Scikit-learn) to identify the degree of congestion for each time period and each area. The input is the dataset acquired in step 1, and the output is the congestion pattern based on the analysis results. Specifically, the server performs clustering and statistical analysis to visualize the congestion pattern.

[0199] Step 3:

[0200] Generating optimal guidance routes

[0201] Based on the analysis results, the server generates the optimal guided route to minimize congestion. To do this, it uses an AI algorithm (genetic algorithm or machine learning model). The input is the congestion pattern identified in step 2, and the output is optimized route information. Specifically, the server runs the shortest route algorithm to generate optimal route data.

[0202] Step 4:

[0203] Sending guidance routes

[0204] The server sends the generated guidance route to the user's device. The input is the route information generated in step 3, and the output is route instructions to the user's device. Specifically, the server sends route data to the user's smartphone via API.

[0205] Step 5:

[0206] Real-time information provision

[0207] The device analyzes the instructions received from the server and notifies the user in real time. The input is the route instructions sent from the server, and the output is a notification message to the user. Specifically, the device uses the push notification function to notify the user of the next action.

[0208] Step 6:

[0209] Monitoring actual congestion status

[0210] The server receives real-time location information and movement speed from the user's device and monitors the current congestion situation based on that information. The input is real-time data sent from the user's device, and the output is the latest congestion situation. Specifically, the server analyzes the received data and displays it on a dashboard.

[0211] Step 7:

[0212] Re-adjustment of guidance route

[0213] The server readjusts the guidance route as needed based on the data collected in real time. The input is the real-time data obtained in step 6, and the output is the readjusted route information. Specifically, the server runs the route optimization algorithm again to generate a new route.

[0214] Step 8:

[0215] Sending revised guidance routes

[0216] The server sends the re-adjusted route to the guide and the user's device. The input is the route information regenerated in step 7, and the output is new instructions for the on-site guide and the user. Specifically, the server sends the updated information via the notification system.

[0217] 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.

[0218] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. In this system, a server collects and analyzes past people flow data to generate optimal guided routes, and an emotion engine is used to recognize the user's emotional state and adjust the guided route based on that, thereby increasing user satisfaction. Details of the system and a specific example implementation are provided below.

[0219] System Configuration

[0220] Data collection and analysis

[0221] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. The retrieved data is read using an analysis tool (such as Python's Pandas or Scikit-learn). The server analyzes the data to calculate congestion levels, number of people entering and leaving, average travel time, and other data for each time period and area, and identifies congestion patterns during the event.

[0222] Examples:

[0223] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0224] Generating optimal guidance methods

[0225] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[0226] Examples:

[0227] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0228] Sending instructions to user terminal

[0229] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[0230] Examples:

[0231] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0232] Guide staff deployment and real-time adjustment

[0233] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[0234] Examples:

[0235] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0236] User Emotion Recognition

[0237] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[0238] Examples:

[0239] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[0240] Emotion-based route adjustment

[0241] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, it can guide frustrated users to a route with a shorter waiting time to reduce stress.

[0242] Examples:

[0243] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[0244] Program processing

[0245] In this system, the program performs processing in the following procedure.

[0246] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[0247] Analysis of congestion patterns: The server identifies the degree of congestion for each time period and each area, and extracts congestion patterns based on that.

[0248] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[0249] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[0250] Real-time adjustment: The server monitors newly collected data and adjusts the guidance route and the deployment of guidance personnel as needed.

[0251] Emotion recognition: The server uses an emotion engine to recognize the user's emotional state and readjusts the guidance path based on the results.

[0252] As a result, the present invention realizes smooth people flow management and congestion relief during events, as well as improved travel efficiency and safety while taking into consideration the feelings of users.

[0253] The processing flow will be explained below.

[0254] Step 1:

[0255] The server retrieves people flow data collected from past events from the database, including participants' locations, routes, durations, and congestion levels.

[0256] Step 2:

[0257] The server analyzes the acquired people flow data using analytical tools (e.g., Python's Pandas or Scikit-learn), and calculates the congestion level, number of people entering and leaving, average travel time, etc. for each time period and area.

[0258] Step 3:

[0259] The server identifies congestion patterns. Specifically, based on the analysis results, it extracts patterns of congestion occurring in specific areas and time periods during events.

[0260] Examples:

[0261] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0262] Step 4:

[0263] Based on the identified congestion patterns, the server uses AI algorithms (e.g., genetic algorithms or machine learning models) to generate optimal guidance routes, taking into account the balance between waiting time and travel time for all participants.

[0264] Examples:

[0265] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0266] Step 5:

[0267] The server then sends the generated optimal route to each user's device, including real-time travel instructions, congestion status, estimated waiting times, and other information.

[0268] Step 6:

[0269] The device analyzes the guidance instructions received from the server and notifies the user, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[0270] Examples:

[0271] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0272] Step 7:

[0273] The server also sends instructions to on-site traffic controllers, including where to position them during specific times and how to change their routes depending on traffic congestion.

[0274] Examples:

[0275] If the congestion becomes greater than expected at 8:40 p.m., the server sends an instruction to the attendant saying, "Please guide participants to use Route B."

[0276] Step 8:

[0277] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[0278] Examples:

[0279] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[0280] Step 9:

[0281] The server adjusts the route and waiting time based on the user's emotional state as recognized by the emotion engine. For example, it guides a frustrated user to a route with a shorter waiting time.

[0282] Examples:

[0283] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[0284] Step 10:

[0285] The server monitors newly collected data (location information and movement speed) in real time, allowing it to constantly understand the current congestion situation and readjust routes as necessary.

[0286] Examples:

[0287] The server will analyze the user's location data at 8:30 p.m., and if there is more congestion than expected, it will send new route instructions to the user's device and the guide.

[0288] Step 11:

[0289] The terminal receives new updated instructions from the server and notifies the user, so that the user is always provided with the latest route information.

[0290] Examples:

[0291] The terminal notifies the user of new instructions, such as "The congestion situation has changed, so please turn left at the next intersection."

[0292] Through these steps, the present invention achieves congestion relief during events, safer user movement, and improved convenience that takes user feelings into consideration.

[0293] Example 2

[0294] 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."

[0295] To alleviate congestion and improve participant movement efficiency at large-scale events, it is not enough to generate optimal guidance routes based on past data alone; it is also necessary to consider real-time congestion conditions and the emotional state of each user. Therefore, dynamic route adjustment based on emotional state is required to improve the user experience and ensure safe guidance.

[0296] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0297] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of the guide and the user, means for recognizing the user's emotional state, and means for adjusting the guide route based on the recognized emotional state. This enables flexible and effective guidance that takes into account real-time congestion conditions and the user's emotional state.

[0298] "People flow data" is data that records the movements of event participants, such as their location, route, length of stay, and level of congestion.

[0299] A "crowding pattern" is a tendency for participants to concentrate or disperse at a particular time or location, identified based on past people flow data.

[0300] A "guided route" is a route optimized to allow participants to move efficiently within the event venue.

[0301] A "user terminal" is a device held by a participant, such as a smartphone or tablet, that has the function of receiving and displaying information.

[0302] "Real-time monitoring" is a monitoring method that allows you to instantly grasp the congestion situation and movements of participants at an ongoing event.

[0303] "Emotional state" refers to the psychological state and emotions analyzed based on the user's facial expressions and biometric data.

[0304] An "emotion engine" is a system that includes software and algorithms for analyzing a user's emotional state.

[0305] A "genetic algorithm" is a computational method based on evolutionary theory and a type of AI algorithm used to find optimal solutions.

[0306] MODE FOR CARRYING OUT THE INVENTION

[0307] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. This system uses a server to collect and analyze past people flow data to generate optimal guide routes, and an emotion engine to recognize the user's emotional state and adjust the guide route based on that, thereby increasing user satisfaction.

[0308] Data collection and analysis

[0309] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. Using analysis tools such as Python's Pandas and Scikit-learn, the server reads the data and calculates congestion levels, number of people entering and leaving, average travel time, and other information for each time period and area, identifying congestion patterns during the event.

[0310] Examples:

[0311] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0312] Generating optimal guidance methods

[0313] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[0314] Examples:

[0315] The server plans to use routes B and C during the period from 8:00 p.m. to 9:00 p.m., as route A is congested.

[0316] Sending instructions to user terminal

[0317] The server sends the generated route to the user's device (e.g., smartphone or tablet), which then analyzes the received instructions and notifies the user in real time.

[0318] Examples:

[0319] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0320] Guide staff deployment and real-time adjustment

[0321] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[0322] Examples:

[0323] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0324] User Emotion Recognition

[0325] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or feelings of unfairness felt by the user.

[0326] Examples:

[0327] The server collects facial expression data via the user's smartphone camera, analyzes it using an emotion engine, and detects whether the user is dissatisfied.

[0328] Emotion-based route adjustment

[0329] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, a frustrated user can be guided to a route with a shorter waiting time to reduce stress.

[0330] Examples:

[0331] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[0332] This system will not only streamline the movement of event attendees and reduce congestion, but also provide personalized guidance that takes into account the user's emotions, improving the overall user experience and enabling safe and efficient transportation.

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1: Data collection

[0335] Input: The server retrieves past event data from the database. People flow data includes participant location information, movement routes, stay time, congestion level, etc.

[0336] Processing: The server uses Python's Pandas to read the acquired data and manage it as a DataFrame. It then deletes unnecessary data and imputes missing values.

[0337] Output: A clean, pre-processed dataset.

[0338] Specific behavior:

[0339] The server queries the database to retrieve the data.

[0340] Read the data as a DataFrame using Pandas.

[0341] Remove unnecessary columns and impute missing values ​​appropriately.

[0342] Step 2: Analyze crowding patterns

[0343] Input: The server takes as input the dataset that has been preprocessed.

[0344] Processing: Use Pandas to aggregate the number of participants for each time period, and use Scikit-learn to apply K-means clustering to cluster congested areas.

[0345] Output: Quantified congestion levels for each time period and area.

[0346] Specific behavior:

[0347] Use Pandas to count the number of participants for specific time periods and areas.

[0348] Apply Scikit-learn's K-means clustering to identify the degree of congestion for each cluster.

[0349] Visualize (graph) the results.

[0350] Step 3: Generate optimal guidance path

[0351] Input: The server inputs the results of the congestion analysis.

[0352] Processing: Genetic algorithms are used to generate optimal guidance routes, balancing waiting and travel times across participants.

[0353] Output: A set of optimized guided paths.

[0354] Specific behavior:

[0355] The server generates initial routes and evaluates the latency and travel time of each route.

[0356] A fitness function is calculated and new paths are generated through crossover and mutation operations.

[0357] This process is repeated until the optimal route is found.

[0358] Step 4: Send instructions

[0359] Input: The server takes the optimized guided route as input.

[0360] Processing: The server generates and sends a message containing the appropriate route to each user's terminal.

[0361] Output: A message about the route delivered to the user's device.

[0362] Specific behavior:

[0363] The server generates a message to be sent to each user's terminal.

[0364] Sends a message to the user's terminal.

[0365] The user's device receives the message and displays a notification on the screen.

[0366] Step 5: Real-time adjustments

[0367] Input: The server takes as input the congestion status data newly collected in real time.

[0368] Processing: The server recalculates the current congestion level based on the collected data and regenerates the guidance route if necessary.

[0369] Output: The latest re-adjusted guidance path.

[0370] Specific behavior:

[0371] The server periodically collects current congestion data.

[0372] Analyze congestion data and generate new guidance routes as needed.

[0373] The regenerated route is sent to the user and the driver.

[0374] Step 6: Emotion Recognition

[0375] Input: The server inputs the user's facial expression data and biometric data.

[0376] Processing: Analyze the user's emotional state using an emotion engine. Determine the level of stress or frustration based on facial expression data and heart rate data.

[0377] Output: Analysis results about the user's emotional state.

[0378] Specific behavior:

[0379] The server acquires facial expression data through the user's smartphone camera.

[0380] Facial expression data and heart rate data are input into an emotion engine to determine emotions.

[0381] The emotion engine returns the analysis results to the server.

[0382] Step 7: Emotion-Based Path Adjustment

[0383] Input: The server takes the output data of the emotion engine as input.

[0384] Processing: Based on the emotional state of the user, we regenerate a more effective guidance route. In particular, for dissatisfied users, we make adjustments to reduce waiting time.

[0385] Output: New adjusted guidance path.

[0386] Specific behavior:

[0387] The server receives and analyzes the output from the emotion engine.

[0388] Regenerate new routes based on the user's emotional state.

[0389] The new route information is sent to the user's terminal.

[0390] (Application example 2)

[0391] 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."

[0392] Congestion in physical stores reduces customer movement efficiency and significantly reduces customer satisfaction. Congestion, especially during peak hours, can increase waiting times and make it difficult to move around. In the worst case, it can lead to customers leaving the store, negatively impacting sales. Furthermore, uniform guidance that does not take into account the emotional state of customers makes it difficult to meet the needs of individual customers. Therefore, there is a need for a method to efficiently manage congestion in stores and encourage optimal movement based on customers' emotional state.

[0393] 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.

[0394] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for collecting facial expression data and biometric data of users and recognizing their emotional state, means for adjusting the guide route based on the recognized emotional state, means for transmitting the generated or adjusted guide route to the user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, and means for transmitting the readjusted guide route to the terminals of guides and users. This effectively alleviates congestion in physical stores, improving customer movement efficiency and satisfaction.

[0395] "Past people flow data" refers to historical information collected at events and physical stores, such as the location information of customers, their movement routes, length of stay, and congestion levels.

[0396] "Congestion patterns" are analysis results that show the characteristics of people flow and density in specific time periods and areas.

[0397] An "invitation route" is a route designed to guide participants and visitors along a specific path to reduce congestion.

[0398] "Facial expression data" refers to information extracted from a user's facial expressions, and is data captured using a camera or image analysis technology.

[0399] "Biometric data" is data obtained by measuring a user's physical condition, such as heart rate or stress level.

[0400] "Emotional state" refers to the psychological state such as stress, dissatisfaction, or relief felt by the user.

[0401] "User terminal" refers to an information and communication device carried by an individual user, such as a smartphone or tablet.

[0402] "Real-time monitoring" means instantly observing and analyzing ongoing situations and taking immediate action if necessary.

[0403] "Readjustment" means reviewing and optimizing the initially set guidance route and layout according to the situation.

[0404] A "guide" is a person whose role is to actually guide people on-site.

[0405] This invention is a system for reducing congestion in brick-and-mortar stores and improving customer movement efficiency and satisfaction. In this system, a server collects and analyzes past people flow data to generate optimal guide routes, and an emotion engine recognizes the user's emotional state and adjusts the guide route based on that, thereby increasing user satisfaction.

[0406] System Configuration

[0407] Data collection and analysis

[0408] The server retrieves people flow data collected from past brick-and-mortar stores from the database. This people flow data includes information on customers' locations, movement routes, length of stay, and congestion levels. The server then analyzes the retrieved data using Python data analysis tools (e.g., Pandas and Scikit-learn). As a result of the analysis, congestion levels, number of people entering and leaving the store, and average travel times for each time period and area are calculated.

[0409] For example, the server analyzes data from 6:00 PM to 7:00 PM at a shopping mall on a Saturday last year and discovers that the food court is very crowded during this time.

[0410] Generating optimal guidance methods

[0411] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, balancing waiting time and travel time and planning multiple routes to reduce unfairness.

[0412] For example, the server may plan to prioritize a route that passes through the book section during the period when the food court is crowded between 6:00 PM and 7:00 PM.

[0413] Sending instructions to user terminal

[0414] The server sends the generated or adjusted route to the user's device (smartphone or tablet), which analyzes the received instructions and notifies the user in real time.

[0415] For example, the user may be notified with a message such as, "The food court is currently crowded. We recommend turning right and passing through the book section. Travel time: approximately 8 minutes."

[0416] Emotion recognition and re-routing

[0417] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or frustration.

[0418] For example, the server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect whether the user is feeling stressed.

[0419] The system adjusts routes and waiting times based on the user's perceived emotional state. For example, if a user feels stressed, the system will guide them to a less crowded route and shorten their waiting time.

[0420] Hardware and software used

[0421] Hardware: Server (data collection, analysis, route generation), smartphone (data collection and instruction display), smartphone camera (emotion recognition)

[0422] Software: Python (data analysis: Pandas, Scikit-learn), Scipy (optimization calculation), FER library (sentiment analysis)

[0423] Specific examples

[0424] An example of use in a brick-and-mortar shopping mall is shown below.

[0425] Prompt statement:

[0426] "Considering how crowded the shopping mall is right now at 6:00 PM, please tell me the easiest route."

[0427] (System response):

[0428] "The food court is currently crowded. We recommend turning right and taking the route via the book section. Travel time: approximately 8 minutes."

[0429] This system allows customers to move efficiently while avoiding crowds, while also improving customer satisfaction by providing the optimal route based on their emotional state.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] The server retrieves past people flow data from the database. This data includes customer location information, movement paths, stay times, congestion levels, etc. The input is the past people flow data, and the output is the retrieved dataset. Specifically, the required information is extracted from the database using SQL queries.

[0433] Step 2:

[0434] The server analyzes the acquired people flow data using Python data analysis tools (such as Pandas). The input is the dataset acquired in step 1, and the output is the analysis results. Specifically, the data is grouped by time period and area, and the degree of congestion, number of people entering and leaving, and average travel time are calculated.

[0435] Step 3:

[0436] The server identifies congestion patterns based on the analysis results. This identification process uses a clustering algorithm (e.g., K-Means) from a machine learning model (such as Scikit-learn). The input is the analysis results, and the output is the congestion patterns for each time period and each area. Specifically, the visitor data is classified into clusters, and highly congested areas are identified.

[0437] Step 4:

[0438] The server generates the optimal guided route based on the results of analyzing congestion patterns. It uses AI algorithms (genetic algorithms and machine learning models) to create multiple routes and balance waiting time and travel time. The input is the congestion pattern, and the output is the guided route. Specifically, it runs a simulation to identify which route is optimal.

[0439] Step 5:

[0440] The server collects the user's facial expression data and biometric data. This data is acquired through the smartphone's camera and sensors. The input is the user's image data and biometric data, and the output is the processed raw data. Specifically, the image data is uploaded to the cloud, and the biometric data is collected via Bluetooth or other means.

[0441] Step 6:

[0442] The server uses an emotion engine to recognize the user's emotional state. This engine uses the FER library to analyze facial expression data and biometric data. The input is the facial expression data and biometric data collected in the previous step, and the output is the analysis result of the emotional state (e.g., stress, dissatisfaction, relief). Specifically, it performs image analysis and signal analysis to identify emotions.

[0443] Step 7:

[0444] The server adjusts the guidance route based on the recognized emotional state. Taking the emotional state into account, it recalculates the route to provide a more comfortable route. The input is the analysis result of the emotional state, and the output is the adjusted guidance route. Specifically, it responds by presenting a less crowded route to a user who is feeling stressed.

[0445] Step 8:

[0446] The server sends the generated or adjusted guided route to the user's device. The input is the adjusted guided route, and the output is a notification message to the device. Specifically, it sends instructions to the device in real time via an API.

[0447] Step 9:

[0448] The terminal provides real-time information based on the received guidance route. The input is the guidance route information from the server, and the output is a message to be displayed to the user. Specifically, the message is displayed to the user using the smartphone's notification function.

[0449] Step 10:

[0450] The server monitors the actual congestion situation in real time and readjusts the guided route as necessary. The input is real-time location information, movement speed, and emotional state data received from the device, and the output is the readjusted guided route. Specifically, it analyzes new data from the device and updates the guided route.

[0451] Step 11:

[0452] The server sends the readjusted guidance route to the guide and the user's device. The input is the readjusted guidance route, and the output is an instruction message to the guide and the device. Specifically, by distributing the recalculated route information again, optimal guidance tailored to the situation on site is realized.

[0453] 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.

[0454] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0455] 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.

[0456] [Second embodiment]

[0457] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0458] 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.

[0459] 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).

[0460] 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.

[0461] 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.

[0462] 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).

[0463] 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. 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] 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."

[0469] This invention relates to a system that alleviates congestion during events and improves the efficiency of participant movement. This system enables safe and efficient movement of users by having a server collect and analyze past people flow data and generate optimal guide routes. Details of the system and a specific example implementation are provided below.

[0470] System Configuration

[0471] Data collection and analysis

[0472] The server retrieves people flow data (e.g., location information, movement paths, duration of stay, etc.) collected from past events from a database. The collected data is analyzed using analytical tools (e.g., Python's Pandas or Scikit-learn). The server generates indicators such as congestion level, number of people entering and leaving, and average travel time for each time period and each area, and extracts the information necessary for predicting the next event.

[0473] Examples:

[0474] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0475] Generating optimal guidance methods

[0476] The server generates optimal routes based on the analysis to minimize congestion, using AI algorithms (e.g., genetic algorithms and machine learning models), and creates a plan to distribute traffic among routes to balance waiting and travel times across all participants and reduce perceived unfairness.

[0477] Examples:

[0478] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0479] Sending instructions to user terminal

[0480] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[0481] Examples:

[0482] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0483] Guide staff deployment and real-time adjustment

[0484] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[0485] Examples:

[0486] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0487] Program processing

[0488] In this system, the program performs processing in the following procedure.

[0489] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[0490] Analysis of congestion patterns: The server uses analytical tools to identify the level of congestion for each time period and area, and extracts congestion patterns based on that.

[0491] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[0492] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[0493] Real-time adjustment: The server monitors newly collected data and adjusts the guidance routes and the deployment of guidance staff as needed, allowing it to respond to changing congestion conditions in real time.

[0494] As a result, the present invention alleviates congestion during events and improves safety for participants.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] The server retrieves people flow data collected from past events from the database, including participant location information, movement paths, stay times, congestion levels, etc. The retrieved data is read using analysis tools (e.g., Python's Pandas or Scikit-learn).

[0498] Step 2:

[0499] The server analyzes the acquired data. Specifically, it calculates the degree of congestion, the number of people entering and leaving, and the average travel time for each time period and each area. Based on the analysis results, it identifies the congestion patterns that will occur in specific areas and routes during the event.

[0500] Step 3:

[0501] Based on the analysis results, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, and plans to distribute participants across multiple routes to balance waiting and travel times for all participants.

[0502] Step 4:

[0503] The server then sends the generated route to each user's device. The route includes real-time travel instructions, congestion information, estimated waiting time, and other information, allowing each user's device to receive individual instructions.

[0504] Step 5:

[0505] The device analyzes the guidance instructions received from the server and notifies the user in real time, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[0506] Step 6:

[0507] The server also sends instructions to on-site guides, including where to position them during specific times and how to change routes depending on congestion levels, enabling appropriate guidance at the site.

[0508] Step 7:

[0509] Users follow the notification from their device and travel along the designated route. Real-time instructions allow users to avoid congestion and reach their destination efficiently.

[0510] Step 8:

[0511] The server monitors newly collected data in real time (for example, user location information and movement speed), which allows the current congestion situation to be continuously grasped.

[0512] Step 9:

[0513] The server analyzes the collected real-time data and adjusts the guidance route and the deployment of guides as necessary. The adjusted guidance route is then sent back to the user's device and the guide.

[0514] Step 10:

[0515] The terminal then notifies the user of the updated instructions, allowing the user to receive route instructions that reflect the latest congestion conditions.

[0516] Through these steps, the system will enable smooth people flow management and congestion relief during events.

[0517] Example 1

[0518] 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."

[0519] During events, large numbers of participants gather in specific areas or routes at the same time, causing congestion that reduces safety, comfort, and travel efficiency. It is important to eliminate this congestion and establish guidance methods that allow participants to move around efficiently and safely. However, conventional methods have difficulty grasping congestion situations in real time and providing appropriate guidance routes based on that information, making them ineffective. Therefore, a system that can solve these issues, efficiently alleviate congestion, and improve safety and comfort is needed.

[0520] 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.

[0521] In this invention, the server includes means for acquiring past people flow data, means for identifying congestion patterns using an analysis tool for analyzing the acquired people flow data, means for generating an optimal guide route using an AI algorithm based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for notifying the user's terminal based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary based on newly collected data, and means for transmitting the readjusted guide route to the terminals of guides and users. This enables real-time understanding of congestion conditions and subsequent rapid and accurate guidance.

[0522] "Past people flow data" refers to information such as the location, movement route, and length of stay of individual users collected at past events.

[0523] "Analysis Tools" refers to software tools used to analyze data, including commonly used data analysis libraries and algorithms.

[0524] A "congestion pattern" indicates the tendency for people to concentrate and move around in a particular time period or area, and is determined based on indicators such as the degree of congestion, the number of people entering and leaving, and average travel time.

[0525] "AI algorithm" refers to a computational method for deriving optimal solutions using artificial intelligence technology, and specifically includes genetic algorithms and machine learning models.

[0526] A "guided route" is a route that a user should follow when moving from one point to another, and is designed to ensure optimal movement.

[0527] "User Device" means an electronic device held by a User that receives and displays instructions and notifications, including a smartphone or tablet.

[0528] "Real-time monitoring" refers to the immediate observation, analysis, and processing of ongoing situations, including the location and speed of users.

[0529] A "guide" refers to a person in charge of guiding participants at the event site, and is responsible for changing their location and route based on instructions from the server.

[0530] This invention relates to a system that alleviates congestion at events and improves the efficiency of participant movement. This system generates optimal guided routes based on past people flow data and readjusts the routes according to real-time congestion conditions, ensuring safe and efficient movement.

[0531] The server connects to a database to retrieve historical people flow data, including location information, movement paths, and dwell times collected during past events. Data is retrieved using standard database queries.

[0532] The server then analyzes the data using Python analysis tools (such as Pandas or Scikit-learn). Specifically, it calculates the congestion level, number of people entering and leaving, and average travel time for each area and time period. To identify congestion patterns, it uses a clustering algorithm (such as K-means) to extract time periods and areas where large-scale congestion occurs.

[0533] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal routes. The algorithms perform calculations to minimize congestion and travel time. The generated routes are designed to balance total travel time and evenly distribute waiting time among all participants.

[0534] The server then sends the generated route guidance to the user's device (smartphone or tablet). The device receives the instructions and notifies the user in real time. The message displayed on the user's device includes specific instructions such as "Turn right at the next intersection. Waiting time: approximately 15 minutes."

[0535] The server also receives real-time location information and movement speed from each device and readjusts the guidance route based on the newly collected data. This process involves collecting real-time data using WebSockets and generating new routes as needed and sending them back to the device.

[0536] The server also sends instructions to traffic controllers to assist them in guiding traffic at specific times and locations. For example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends this to the devices of the traffic controllers and users.

[0537] Specific examples

[0538] Analysis based on data from 8:00 p.m. to 9:00 p.m. at last year's fireworks display predicted that certain routes would be extremely congested, so the server planned to use routes B and C.

[0539] Prompt Sentence Examples

[0540] "Based on data from last year's fireworks display, identify routes that are most congested between 8:00 and 9:00 p.m."

[0541] "Suggest multiple routes that are most efficient at a given time to reduce congestion."

[0542] "Adjust the optimal route based on the user's location information in real time."

[0543] As described above, the present invention alleviates congestion during events and improves safety for participants.

[0544] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0545] System program processing flow

[0546] Step 1: Data collection

[0547] The server retrieves people flow data from a database of past events, which stores location information, movement paths, and duration of stays collected from past events.

[0548] Specific behavior:

[0549] The server connects to the database using an SQL query to retrieve data for a specific date: SELECT FROM EventData WHERE Date = '2022-07-30'.

[0550] input:

[0551] People flow data stored in a database.

[0552] output:

[0553] A people flow dataset to be passed to analysis tools.

[0554] Step 2: Data analysis

[0555] The server analyzes the acquired data using Python libraries such as Pandas and Scikit-learn, calculating the congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0556] Specific behavior:

[0557] The server creates a data frame using Pandas and executes "df.groupby(['Area', 'Time']).size()" to calculate the congestion level for each area and time period.

[0558] input:

[0559] Acquired people flow data.

[0560] output:

[0561] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0562] Step 3: Extracting congestion patterns

[0563] The server extracts congestion patterns from the analysis results. Specifically, it identifies specific congestion patterns using a clustering algorithm (e.g., K-means).

[0564] Specific behavior:

[0565] The server uses Scikit-learn to perform clustering using code like "kmeans = KMeans(n_clusters=3).fit(df[['Congestion', 'FlowIn', 'FlowOut']])" to classify congestion patterns.

[0566] input:

[0567] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0568] output:

[0569] Congestion patterns by time of day and area.

[0570] Step 4: Generate optimal guidance path

[0571] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal guidance routes.

[0572] Specific behavior:

[0573] The server uses a genetic algorithm to search for the optimal solution with code like "result = genetic_algorithm.optimize(objective_function, population_size=100, generations=50)".

[0574] input:

[0575] Crowding pattern.

[0576] output:

[0577] Optimal guidance route.

[0578] Step 5: Send instructions

[0579] The server sends the generated guided route to the user's terminal, which analyzes it and notifies the user.

[0580] Specific behavior:

[0581] The server uses the REST API to send the guidance route to the endpoint "POST / send-instructions", and the user's device displays this information.

[0582] input:

[0583] Optimal guidance route.

[0584] output:

[0585] Instructions displayed on the user's device.

[0586] Step 6: Real-time monitoring and readjustment

[0587] The server receives real-time location information and movement speed from the user's device and readjusts the guidance route based on the newly collected data.

[0588] Specific behavior:

[0589] The server collects real-time data via WebSocket and generates new routes as needed and sends them again to the device.

[0590] input:

[0591] Location information and movement speed collected in real time.

[0592] output:

[0593] Realigned guidance path.

[0594] The above is the flow of program processing in this system.

[0595] (Application example 1)

[0596] 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."

[0597] Congestion in large facilities, commercial facilities, and other locations can be a factor that impairs the convenience and safety of users. There is a need to efficiently alleviate congestion caused by the flow of people in each area and time period and provide routes that allow users to move smoothly. However, a system that constantly monitors dynamically changing congestion conditions in real time and proposes optimal guidance routes has not yet been fully developed. It is also important to effectively utilize past congestion data to predict future congestion and develop countermeasures in advance. Therefore, the present invention aims to solve these problems by proposing a system that utilizes past people flow data to provide optimal guidance routes that adapt to dynamically changing congestion conditions in real time.

[0598] 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.

[0599] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data and identifying congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of guides and users, and means for proposing a route that optimizes the flow of users within a commercial facility based on past data. This makes it possible to effectively alleviate congestion within large facilities and commercial facilities and provide an environment in which users can move safely and comfortably.

[0600] "Past people flow data" refers to data including people's movement routes, location information, and duration of stay over a certain period of time in the past.

[0601] "Crowd patterns" are data that indicate the degree of crowding and congestion trends in a particular time period and area.

[0602] An "optimal route" is a recommended route to a specific destination that is generated to minimize congestion and evenly distribute waiting and travel times among users.

[0603] A "user device" is a portable electronic device carried by a user, such as a smartphone or tablet.

[0604] "Means for providing information in real time" refers to a system for instantly transmitting current congestion status and optimal route information to users' terminals.

[0605] "Actual congestion situation" refers to information that indicates the current state of people gathering and their travel routes at events or in everyday life.

[0606] "Guides" are personnel who are deployed on-site to provide instructions to users and support their movement.

[0607] A "commercial facility" is a building or surrounding area where many customers gather and make purchases, such as a shopping mall or department store.

[0608] "Flow lines" refer to the routes and directions that users take when moving within a facility.

[0609] The present invention is a system for optimizing user flow lines and alleviating congestion within large facilities and commercial facilities. This system collects and analyzes past people flow data, generates optimal guidance routes, sends instructions to user terminals, and makes adjustments in real time. Specific embodiments are described below.

[0610] 1. Data Collection and Analysis

[0611] The server retrieves past people flow data from a database. This data includes location information, movement paths, and duration of stay. The server analyzes this data using analytical tools (e.g., Python's Pandas or Scikit-learn) to identify the level of congestion for each time period and each area. This allows the server to extract the information necessary for predictions for the next event and for normal times.

[0612] As a specific example, the server analyzes data from a shopping mall during last year's Christmas season to discover areas that become crowded at specific times.

[0613] 2. Generating optimal guidance routes

[0614] Based on the analysis results, the server generates the optimal route to minimize congestion using AI algorithms (e.g., genetic algorithms and machine learning models). It also creates a plan to distribute passengers across routes to balance waiting time and travel time across all users and reduce unfairness.

[0615] As a specific example, the server generates routes that bypass areas where congestion is expected during specific times of the day, and plans to spread out users during those times.

[0616] 3. Send instructions to the user device

[0617] The server sends the generated route to the user's device, which analyzes the received instructions and notifies the user in real time.

[0618] As a specific example, the user's device may display the message, "Considering the current congestion situation, please turn right at the next intersection. Waiting time: approximately 15 minutes."

[0619] 4. Placement of guides and real-time adjustment

[0620] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[0621] As a specific example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends it to the user's terminal.

[0622] Prompt Sentence Examples

[0623] Design an application that analyzes the most efficient route within a specified shopping mall and notifies the user in real time. Crowd data will be based on past data and analyzed using KMeans clustering. Include specific data and the method of user notification.

[0624] As described above, in the embodiment of the present invention, it is possible to perform everything from past data analysis to real-time congestion management, centered on the server, which effectively alleviates congestion in large facilities and commercial facilities, and provides an environment in which users can move around safely and comfortably.

[0625] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0626] Step 1:

[0627] Data collection

[0628] The server retrieves historical people flow data from a database. This data includes location information, travel paths, and dwell times. The input is the historical data in the database, and the output is a dataset for analysis. Specifically, the server uses SQL queries to extract the required data from the database.

[0629] Step 2:

[0630] Data analysis

[0631] The server analyzes the acquired data using analysis tools (Python's Pandas and Scikit-learn) to identify the degree of congestion for each time period and each area. The input is the dataset acquired in step 1, and the output is the congestion pattern based on the analysis results. Specifically, the server performs clustering and statistical analysis to visualize the congestion pattern.

[0632] Step 3:

[0633] Generating optimal guidance routes

[0634] Based on the analysis results, the server generates the optimal guided route to minimize congestion. To do this, it uses an AI algorithm (genetic algorithm or machine learning model). The input is the congestion pattern identified in step 2, and the output is optimized route information. Specifically, the server runs the shortest route algorithm to generate optimal route data.

[0635] Step 4:

[0636] Sending guidance routes

[0637] The server sends the generated guidance route to the user's device. The input is the route information generated in step 3, and the output is route instructions to the user's device. Specifically, the server sends route data to the user's smartphone via API.

[0638] Step 5:

[0639] Real-time information provision

[0640] The device analyzes the instructions received from the server and notifies the user in real time. The input is the route instructions sent from the server, and the output is a notification message to the user. Specifically, the device uses the push notification function to notify the user of the next action.

[0641] Step 6:

[0642] Monitoring actual congestion status

[0643] The server receives real-time location information and movement speed from the user's device and monitors the current congestion situation based on that information. The input is real-time data sent from the user's device, and the output is the latest congestion situation. Specifically, the server analyzes the received data and displays it on a dashboard.

[0644] Step 7:

[0645] Re-adjustment of guidance route

[0646] The server readjusts the guidance route as needed based on the data collected in real time. The input is the real-time data obtained in step 6, and the output is the readjusted route information. Specifically, the server runs the route optimization algorithm again to generate a new route.

[0647] Step 8:

[0648] Sending revised guidance routes

[0649] The server sends the re-adjusted route to the guide and the user's device. The input is the route information regenerated in step 7, and the output is new instructions for the on-site guide and the user. Specifically, the server sends the updated information via the notification system.

[0650] 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.

[0651] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. In this system, a server collects and analyzes past people flow data to generate optimal guided routes, and an emotion engine is used to recognize the user's emotional state and adjust the guided route based on that, thereby increasing user satisfaction. Details of the system and a specific example implementation are provided below.

[0652] System Configuration

[0653] Data collection and analysis

[0654] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. The retrieved data is read using an analysis tool (such as Python's Pandas or Scikit-learn). The server analyzes the data to calculate congestion levels, number of people entering and leaving, average travel time, and other data for each time period and area, and identifies congestion patterns during the event.

[0655] Examples:

[0656] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0657] Generating optimal guidance methods

[0658] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[0659] Examples:

[0660] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0661] Sending instructions to user terminal

[0662] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[0663] Examples:

[0664] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0665] Guide staff deployment and real-time adjustment

[0666] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[0667] Examples:

[0668] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0669] User Emotion Recognition

[0670] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[0671] Examples:

[0672] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[0673] Emotion-based route adjustment

[0674] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, it can guide frustrated users to a route with a shorter waiting time to reduce stress.

[0675] Examples:

[0676] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[0677] Program processing

[0678] In this system, the program performs processing in the following procedure.

[0679] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[0680] Analysis of congestion patterns: The server identifies the degree of congestion for each time period and each area, and extracts congestion patterns based on that.

[0681] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[0682] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[0683] Real-time adjustment: The server monitors newly collected data and adjusts the guidance route and the deployment of guidance personnel as needed.

[0684] Emotion recognition: The server uses an emotion engine to recognize the user's emotional state and readjusts the guidance path based on the results.

[0685] As a result, the present invention realizes smooth people flow management and congestion relief during events, as well as improved travel efficiency and safety while taking into consideration the feelings of users.

[0686] The processing flow will be explained below.

[0687] Step 1:

[0688] The server retrieves people flow data collected from past events from the database, including participants' locations, routes, durations, and congestion levels.

[0689] Step 2:

[0690] The server analyzes the acquired people flow data using analytical tools (e.g., Python's Pandas or Scikit-learn), and calculates the congestion level, number of people entering and leaving, average travel time, etc. for each time period and area.

[0691] Step 3:

[0692] The server identifies congestion patterns. Specifically, based on the analysis results, it extracts patterns of congestion occurring in specific areas and time periods during events.

[0693] Examples:

[0694] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0695] Step 4:

[0696] Based on the identified congestion patterns, the server uses AI algorithms (e.g., genetic algorithms or machine learning models) to generate optimal guidance routes, taking into account the balance between waiting time and travel time for all participants.

[0697] Examples:

[0698] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0699] Step 5:

[0700] The server then sends the generated optimal route to each user's device, including real-time travel instructions, congestion status, estimated waiting times, and other information.

[0701] Step 6:

[0702] The device analyzes the guidance instructions received from the server and notifies the user, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[0703] Examples:

[0704] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0705] Step 7:

[0706] The server also sends instructions to on-site traffic controllers, including where to position them during specific times and how to change their routes depending on traffic congestion.

[0707] Examples:

[0708] If the congestion becomes greater than expected at 8:40 p.m., the server sends an instruction to the attendant saying, "Please guide participants to use Route B."

[0709] Step 8:

[0710] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[0711] Examples:

[0712] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[0713] Step 9:

[0714] The server adjusts the route and waiting time based on the user's emotional state as recognized by the emotion engine. For example, it guides a frustrated user to a route with a shorter waiting time.

[0715] Examples:

[0716] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[0717] Step 10:

[0718] The server monitors newly collected data (location information and movement speed) in real time, allowing it to constantly understand the current congestion situation and readjust routes as necessary.

[0719] Examples:

[0720] The server will analyze the user's location data at 8:30 p.m., and if there is more congestion than expected, it will send new route instructions to the user's device and the guide.

[0721] Step 11:

[0722] The terminal receives new updated instructions from the server and notifies the user, so that the user is always provided with the latest route information.

[0723] Examples:

[0724] The terminal notifies the user of new instructions, such as "The congestion situation has changed, so please turn left at the next intersection."

[0725] Through these steps, the present invention achieves congestion relief during events, safer user movement, and improved convenience that takes user feelings into consideration.

[0726] Example 2

[0727] 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."

[0728] To alleviate congestion and improve participant movement efficiency at large-scale events, it is not enough to generate optimal guidance routes based on past data alone; it is also necessary to consider real-time congestion conditions and the emotional state of each user. Therefore, dynamic route adjustment based on emotional state is required to improve the user experience and ensure safe guidance.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0730] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of the guide and the user, means for recognizing the user's emotional state, and means for adjusting the guide route based on the recognized emotional state. This enables flexible and effective guidance that takes into account real-time congestion conditions and the user's emotional state.

[0731] "People flow data" is data that records the movements of event participants, such as their location, route, length of stay, and level of congestion.

[0732] A "crowding pattern" is a tendency for participants to concentrate or disperse at a particular time or location, identified based on past people flow data.

[0733] A "guided route" is a route optimized to allow participants to move efficiently within the event venue.

[0734] A "user terminal" is a device held by a participant, such as a smartphone or tablet, that has the function of receiving and displaying information.

[0735] "Real-time monitoring" is a monitoring method that allows you to instantly grasp the congestion situation and movements of participants at an ongoing event.

[0736] "Emotional state" refers to the psychological state and emotions analyzed based on the user's facial expressions and biometric data.

[0737] An "emotion engine" is a system that includes software and algorithms for analyzing a user's emotional state.

[0738] A "genetic algorithm" is a computational method based on evolutionary theory and a type of AI algorithm used to find optimal solutions.

[0739] MODE FOR CARRYING OUT THE INVENTION

[0740] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. This system uses a server to collect and analyze past people flow data to generate optimal guide routes, and an emotion engine to recognize the user's emotional state and adjust the guide route based on that, thereby increasing user satisfaction.

[0741] Data collection and analysis

[0742] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. Using analysis tools such as Python's Pandas and Scikit-learn, the server reads the data and calculates congestion levels, number of people entering and leaving, average travel time, and other information for each time period and area, identifying congestion patterns during the event.

[0743] Examples:

[0744] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0745] Generating optimal guidance methods

[0746] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[0747] Examples:

[0748] The server plans to use routes B and C during the period from 8:00 p.m. to 9:00 p.m., as route A is congested.

[0749] Sending instructions to user terminal

[0750] The server sends the generated route to the user's device (e.g., smartphone or tablet), which then analyzes the received instructions and notifies the user in real time.

[0751] Examples:

[0752] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0753] Guide staff deployment and real-time adjustment

[0754] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[0755] Examples:

[0756] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0757] User Emotion Recognition

[0758] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or feelings of unfairness felt by the user.

[0759] Examples:

[0760] The server collects facial expression data via the user's smartphone camera, analyzes it using an emotion engine, and detects whether the user is dissatisfied.

[0761] Emotion-based route adjustment

[0762] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, a frustrated user can be guided to a route with a shorter waiting time to reduce stress.

[0763] Examples:

[0764] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[0765] This system will not only streamline the movement of event attendees and reduce congestion, but also provide personalized guidance that takes into account the user's emotions, improving the overall user experience and enabling safe and efficient transportation.

[0766] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0767] Step 1: Data collection

[0768] Input: The server retrieves past event data from the database. People flow data includes participant location information, movement routes, stay time, congestion level, etc.

[0769] Processing: The server uses Python's Pandas to read the acquired data and manage it as a DataFrame. It then deletes unnecessary data and imputes missing values.

[0770] Output: A clean, pre-processed dataset.

[0771] Specific behavior:

[0772] The server queries the database to retrieve the data.

[0773] Read the data as a DataFrame using Pandas.

[0774] Remove unnecessary columns and impute missing values ​​appropriately.

[0775] Step 2: Analyze crowding patterns

[0776] Input: The server takes as input the dataset that has been preprocessed.

[0777] Processing: Use Pandas to aggregate the number of participants for each time period, and use Scikit-learn to apply K-means clustering to cluster congested areas.

[0778] Output: Quantified congestion levels for each time period and area.

[0779] Specific behavior:

[0780] Use Pandas to count the number of participants for specific time periods and areas.

[0781] Apply Scikit-learn's K-means clustering to identify the degree of congestion for each cluster.

[0782] Visualize (graph) the results.

[0783] Step 3: Generate optimal guidance path

[0784] Input: The server inputs the results of the congestion analysis.

[0785] Processing: Genetic algorithms are used to generate optimal guidance routes, balancing waiting and travel times across participants.

[0786] Output: A set of optimized guided paths.

[0787] Specific behavior:

[0788] The server generates initial routes and evaluates the latency and travel time of each route.

[0789] A fitness function is calculated and new paths are generated through crossover and mutation operations.

[0790] This process is repeated until the optimal route is found.

[0791] Step 4: Send instructions

[0792] Input: The server takes the optimized guided route as input.

[0793] Processing: The server generates and sends a message containing the appropriate route to each user's terminal.

[0794] Output: A message about the route delivered to the user's device.

[0795] Specific behavior:

[0796] The server generates a message to be sent to each user's terminal.

[0797] Sends a message to the user's terminal.

[0798] The user's device receives the message and displays a notification on the screen.

[0799] Step 5: Real-time adjustments

[0800] Input: The server takes as input the congestion status data newly collected in real time.

[0801] Processing: The server recalculates the current congestion level based on the collected data and regenerates the guidance route if necessary.

[0802] Output: The latest re-adjusted guidance path.

[0803] Specific behavior:

[0804] The server periodically collects current congestion data.

[0805] Analyze congestion data and generate new guidance routes as needed.

[0806] The regenerated route is sent to the user and the driver.

[0807] Step 6: Emotion Recognition

[0808] Input: The server inputs the user's facial expression data and biometric data.

[0809] Processing: Analyze the user's emotional state using an emotion engine. Determine the level of stress or frustration based on facial expression data and heart rate data.

[0810] Output: Analysis results about the user's emotional state.

[0811] Specific behavior:

[0812] The server acquires facial expression data through the user's smartphone camera.

[0813] Facial expression data and heart rate data are input into an emotion engine to determine emotions.

[0814] The emotion engine returns the analysis results to the server.

[0815] Step 7: Emotion-Based Path Adjustment

[0816] Input: The server takes the output data of the emotion engine as input.

[0817] Processing: Based on the emotional state of the user, we regenerate a more effective guidance route. In particular, for dissatisfied users, we make adjustments to reduce waiting time.

[0818] Output: New adjusted guidance path.

[0819] Specific behavior:

[0820] The server receives and analyzes the output from the emotion engine.

[0821] Regenerate new routes based on the user's emotional state.

[0822] The new route information is sent to the user's terminal.

[0823] (Application example 2)

[0824] 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."

[0825] Congestion in physical stores reduces customer movement efficiency and significantly reduces customer satisfaction. Congestion, especially during peak hours, can increase waiting times and make it difficult to move around. In the worst case, it can lead to customers leaving the store, negatively impacting sales. Furthermore, uniform guidance that does not take into account the emotional state of customers makes it difficult to meet the needs of individual customers. Therefore, there is a need for a method to efficiently manage congestion in stores and encourage optimal movement based on customers' emotional state.

[0826] 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.

[0827] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for collecting facial expression data and biometric data of users and recognizing their emotional state, means for adjusting the guide route based on the recognized emotional state, means for transmitting the generated or adjusted guide route to the user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, and means for transmitting the readjusted guide route to the terminals of guides and users. This effectively alleviates congestion in physical stores, improving customer movement efficiency and satisfaction.

[0828] "Past people flow data" refers to historical information collected at events and physical stores, such as the location information of customers, their movement routes, length of stay, and congestion levels.

[0829] "Congestion patterns" are analysis results that show the characteristics of people flow and density in specific time periods and areas.

[0830] An "invitation route" is a route designed to guide participants and visitors along a specific path to reduce congestion.

[0831] "Facial expression data" refers to information extracted from a user's facial expressions, and is data captured using a camera or image analysis technology.

[0832] "Biometric data" is data obtained by measuring a user's physical condition, such as heart rate or stress level.

[0833] "Emotional state" refers to the psychological state such as stress, dissatisfaction, or relief felt by the user.

[0834] "User terminal" refers to an information and communication device carried by an individual user, such as a smartphone or tablet.

[0835] "Real-time monitoring" means instantly observing and analyzing ongoing situations and taking immediate action if necessary.

[0836] "Readjustment" means reviewing and optimizing the initially set guidance route and layout according to the situation.

[0837] A "guide" is a person whose role is to actually guide people on-site.

[0838] This invention is a system for reducing congestion in brick-and-mortar stores and improving customer movement efficiency and satisfaction. In this system, a server collects and analyzes past people flow data to generate optimal guide routes, and an emotion engine recognizes the user's emotional state and adjusts the guide route based on that, thereby increasing user satisfaction.

[0839] System Configuration

[0840] Data collection and analysis

[0841] The server retrieves people flow data collected from past brick-and-mortar stores from the database. This people flow data includes information on customers' locations, movement routes, length of stay, and congestion levels. The server then analyzes the retrieved data using Python data analysis tools (e.g., Pandas and Scikit-learn). As a result of the analysis, congestion levels, number of people entering and leaving the store, and average travel times for each time period and area are calculated.

[0842] For example, the server analyzes data from 6:00 PM to 7:00 PM at a shopping mall on a Saturday last year and discovers that the food court is very crowded during this time.

[0843] Generating optimal guidance methods

[0844] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, balancing waiting time and travel time and planning multiple routes to reduce unfairness.

[0845] For example, the server may plan to prioritize a route that passes through the book section during the period when the food court is crowded between 6:00 PM and 7:00 PM.

[0846] Sending instructions to user terminal

[0847] The server sends the generated or adjusted route to the user's device (smartphone or tablet), which analyzes the received instructions and notifies the user in real time.

[0848] For example, the user may be notified with a message such as, "The food court is currently crowded. We recommend turning right and passing through the book section. Travel time: approximately 8 minutes."

[0849] Emotion recognition and re-routing

[0850] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or frustration.

[0851] For example, the server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect whether the user is feeling stressed.

[0852] The system adjusts routes and waiting times based on the user's perceived emotional state. For example, if a user feels stressed, the system will guide them to a less crowded route and shorten their waiting time.

[0853] Hardware and software used

[0854] Hardware: Server (data collection, analysis, route generation), smartphone (data collection and instruction display), smartphone camera (emotion recognition)

[0855] Software: Python (data analysis: Pandas, Scikit-learn), Scipy (optimization calculation), FER library (sentiment analysis)

[0856] Specific examples

[0857] An example of use in a brick-and-mortar shopping mall is shown below.

[0858] Prompt statement:

[0859] "Considering how crowded the shopping mall is right now at 6:00 PM, please tell me the easiest route."

[0860] (System response):

[0861] "The food court is currently crowded. We recommend turning right and taking the route via the book section. Travel time: approximately 8 minutes."

[0862] This system allows customers to move efficiently while avoiding crowds, while also improving customer satisfaction by providing the optimal route based on their emotional state.

[0863] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0864] Step 1:

[0865] The server retrieves past people flow data from the database. This data includes customer location information, movement paths, stay times, congestion levels, etc. The input is the past people flow data, and the output is the retrieved dataset. Specifically, the required information is extracted from the database using SQL queries.

[0866] Step 2:

[0867] The server analyzes the acquired people flow data using Python data analysis tools (such as Pandas). The input is the dataset acquired in step 1, and the output is the analysis results. Specifically, the data is grouped by time period and area, and the degree of congestion, number of people entering and leaving, and average travel time are calculated.

[0868] Step 3:

[0869] The server identifies congestion patterns based on the analysis results. This identification process uses a clustering algorithm (e.g., K-Means) from a machine learning model (such as Scikit-learn). The input is the analysis results, and the output is the congestion patterns for each time period and each area. Specifically, the visitor data is classified into clusters, and highly congested areas are identified.

[0870] Step 4:

[0871] The server generates the optimal guided route based on the results of analyzing congestion patterns. It uses AI algorithms (genetic algorithms and machine learning models) to create multiple routes and balance waiting time and travel time. The input is the congestion pattern, and the output is the guided route. Specifically, it runs a simulation to identify which route is optimal.

[0872] Step 5:

[0873] The server collects the user's facial expression data and biometric data. This data is acquired through the smartphone's camera and sensors. The input is the user's image data and biometric data, and the output is the processed raw data. Specifically, the image data is uploaded to the cloud, and the biometric data is collected via Bluetooth or other means.

[0874] Step 6:

[0875] The server uses an emotion engine to recognize the user's emotional state. This engine uses the FER library to analyze facial expression data and biometric data. The input is the facial expression data and biometric data collected in the previous step, and the output is the analysis result of the emotional state (e.g., stress, dissatisfaction, relief). Specifically, it performs image analysis and signal analysis to identify emotions.

[0876] Step 7:

[0877] The server adjusts the guidance route based on the recognized emotional state. Taking the emotional state into account, it recalculates the route to provide a more comfortable route. The input is the analysis result of the emotional state, and the output is the adjusted guidance route. Specifically, it responds by presenting a less crowded route to a user who is feeling stressed.

[0878] Step 8:

[0879] The server sends the generated or adjusted guided route to the user's device. The input is the adjusted guided route, and the output is a notification message to the device. Specifically, it sends instructions to the device in real time via an API.

[0880] Step 9:

[0881] The terminal provides real-time information based on the received guidance route. The input is the guidance route information from the server, and the output is a message to be displayed to the user. Specifically, the message is displayed to the user using the smartphone's notification function.

[0882] Step 10:

[0883] The server monitors the actual congestion situation in real time and readjusts the guided route as necessary. The input is real-time location information, movement speed, and emotional state data received from the device, and the output is the readjusted guided route. Specifically, it analyzes new data from the device and updates the guided route.

[0884] Step 11:

[0885] The server sends the readjusted guidance route to the guide and the user's device. The input is the readjusted guidance route, and the output is an instruction message to the guide and the device. Specifically, by distributing the recalculated route information again, optimal guidance tailored to the situation on site is realized.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] [Third embodiment]

[0890] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0891] 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.

[0892] 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).

[0893] 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.

[0894] 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.

[0895] 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).

[0896] 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. 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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."

[0902] This invention relates to a system that alleviates congestion during events and improves the efficiency of participant movement. This system enables safe and efficient movement of users by having a server collect and analyze past people flow data and generate optimal guide routes. Details of the system and a specific example implementation are provided below.

[0903] System Configuration

[0904] Data collection and analysis

[0905] The server retrieves people flow data (e.g., location information, movement paths, duration of stay, etc.) collected from past events from a database. The collected data is analyzed using analytical tools (e.g., Python's Pandas or Scikit-learn). The server generates indicators such as congestion level, number of people entering and leaving, and average travel time for each time period and each area, and extracts the information necessary for predicting the next event.

[0906] Examples:

[0907] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[0908] Generating optimal guidance methods

[0909] The server generates optimal routes based on the analysis to minimize congestion, using AI algorithms (e.g., genetic algorithms and machine learning models), and creates a plan to distribute traffic among routes to balance waiting and travel times across all participants and reduce perceived unfairness.

[0910] Examples:

[0911] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[0912] Sending instructions to user terminal

[0913] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[0914] Examples:

[0915] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[0916] Guide staff deployment and real-time adjustment

[0917] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[0918] Examples:

[0919] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[0920] Program processing

[0921] In this system, the program performs processing in the following procedure.

[0922] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[0923] Analysis of congestion patterns: The server uses analytical tools to identify the level of congestion for each time period and area, and extracts congestion patterns based on that.

[0924] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[0925] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[0926] Real-time adjustment: The server monitors newly collected data and adjusts the guidance routes and the deployment of guidance staff as needed, allowing it to respond to changing congestion conditions in real time.

[0927] As a result, the present invention alleviates congestion during events and improves safety for participants.

[0928] The processing flow will be explained below.

[0929] Step 1:

[0930] The server retrieves people flow data collected from past events from the database, including participant location information, movement paths, stay times, congestion levels, etc. The retrieved data is read using analysis tools (e.g., Python's Pandas or Scikit-learn).

[0931] Step 2:

[0932] The server analyzes the acquired data. Specifically, it calculates the degree of congestion, the number of people entering and leaving, and the average travel time for each time period and each area. Based on the analysis results, it identifies the congestion patterns that will occur in specific areas and routes during the event.

[0933] Step 3:

[0934] Based on the analysis results, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, and plans to distribute participants across multiple routes to balance waiting and travel times for all participants.

[0935] Step 4:

[0936] The server then sends the generated route to each user's device. The route includes real-time travel instructions, congestion information, estimated waiting time, and other information, allowing each user's device to receive individual instructions.

[0937] Step 5:

[0938] The device analyzes the guidance instructions received from the server and notifies the user in real time, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[0939] Step 6:

[0940] The server also sends instructions to on-site guides, including where to position them during specific times and how to change routes depending on congestion levels, enabling appropriate guidance at the site.

[0941] Step 7:

[0942] Users follow the notification from their device and travel along the designated route. Real-time instructions allow users to avoid congestion and reach their destination efficiently.

[0943] Step 8:

[0944] The server monitors newly collected data in real time (for example, user location information and movement speed), which allows the current congestion situation to be continuously grasped.

[0945] Step 9:

[0946] The server analyzes the collected real-time data and adjusts the guidance route and the deployment of guides as necessary. The adjusted guidance route is then sent back to the user's device and the guide.

[0947] Step 10:

[0948] The terminal then notifies the user of the updated instructions, allowing the user to receive route instructions that reflect the latest congestion conditions.

[0949] Through these steps, the system will enable smooth people flow management and congestion relief during events.

[0950] Example 1

[0951] 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."

[0952] During events, large numbers of participants gather in specific areas or routes at the same time, causing congestion that reduces safety, comfort, and travel efficiency. It is important to eliminate this congestion and establish guidance methods that allow participants to move around efficiently and safely. However, conventional methods have difficulty grasping congestion situations in real time and providing appropriate guidance routes based on that information, making them ineffective. Therefore, a system that can solve these issues, efficiently alleviate congestion, and improve safety and comfort is needed.

[0953] 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.

[0954] In this invention, the server includes means for acquiring past people flow data, means for identifying congestion patterns using an analysis tool for analyzing the acquired people flow data, means for generating an optimal guide route using an AI algorithm based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for notifying the user's terminal based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary based on newly collected data, and means for transmitting the readjusted guide route to the terminals of guides and users. This enables real-time understanding of congestion conditions and subsequent rapid and accurate guidance.

[0955] "Past people flow data" refers to information such as the location, movement route, and length of stay of individual users collected at past events.

[0956] "Analysis Tools" refers to software tools used to analyze data, including commonly used data analysis libraries and algorithms.

[0957] A "congestion pattern" indicates the tendency for people to concentrate and move around in a particular time period or area, and is determined based on indicators such as the degree of congestion, the number of people entering and leaving, and average travel time.

[0958] "AI algorithm" refers to a computational method for deriving optimal solutions using artificial intelligence technology, and specifically includes genetic algorithms and machine learning models.

[0959] A "guided route" is a route that a user should follow when moving from one point to another, and is designed to ensure optimal movement.

[0960] "User Device" means an electronic device held by a User that receives and displays instructions and notifications, including a smartphone or tablet.

[0961] "Real-time monitoring" refers to the immediate observation, analysis, and processing of ongoing situations, including the location and speed of users.

[0962] A "guide" refers to a person in charge of guiding participants at the event site, and is responsible for changing their location and route based on instructions from the server.

[0963] This invention relates to a system that alleviates congestion at events and improves the efficiency of participant movement. This system generates optimal guided routes based on past people flow data and readjusts the routes according to real-time congestion conditions, ensuring safe and efficient movement.

[0964] The server connects to a database to retrieve historical people flow data, including location information, movement paths, and dwell times collected during past events. Data is retrieved using standard database queries.

[0965] The server then analyzes the data using Python analysis tools (such as Pandas or Scikit-learn). Specifically, it calculates the congestion level, number of people entering and leaving, and average travel time for each area and time period. To identify congestion patterns, it uses a clustering algorithm (such as K-means) to extract time periods and areas where large-scale congestion occurs.

[0966] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal routes. The algorithms perform calculations to minimize congestion and travel time. The generated routes are designed to balance total travel time and evenly distribute waiting time among all participants.

[0967] The server then sends the generated route guidance to the user's device (smartphone or tablet). The device receives the instructions and notifies the user in real time. The message displayed on the user's device includes specific instructions such as "Turn right at the next intersection. Waiting time: approximately 15 minutes."

[0968] The server also receives real-time location information and movement speed from each device and readjusts the guidance route based on the newly collected data. This process involves collecting real-time data using WebSockets and generating new routes as needed and sending them back to the device.

[0969] The server also sends instructions to traffic controllers to assist them in guiding traffic at specific times and locations. For example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends this to the devices of the traffic controllers and users.

[0970] Specific examples

[0971] Analysis based on data from 8:00 p.m. to 9:00 p.m. at last year's fireworks display predicted that certain routes would be extremely congested, so the server planned to use routes B and C.

[0972] Prompt Sentence Examples

[0973] "Based on data from last year's fireworks display, identify routes that are most congested between 8:00 and 9:00 p.m."

[0974] "Suggest multiple routes that are most efficient at a given time to reduce congestion."

[0975] "Adjust the optimal route based on the user's location information in real time."

[0976] As described above, the present invention alleviates congestion during events and improves safety for participants.

[0977] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0978] System program processing flow

[0979] Step 1: Data collection

[0980] The server retrieves people flow data from a database of past events, which stores location information, movement paths, and duration of stays collected from past events.

[0981] Specific behavior:

[0982] The server connects to the database using an SQL query to retrieve data for a specific date: SELECT FROM EventData WHERE Date = '2022-07-30'.

[0983] input:

[0984] People flow data stored in a database.

[0985] output:

[0986] A people flow dataset to be passed to analysis tools.

[0987] Step 2: Data analysis

[0988] The server analyzes the acquired data using Python libraries such as Pandas and Scikit-learn, calculating the congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0989] Specific behavior:

[0990] The server creates a data frame using Pandas and executes "df.groupby(['Area', 'Time']).size()" to calculate the congestion level for each area and time period.

[0991] input:

[0992] Acquired people flow data.

[0993] output:

[0994] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[0995] Step 3: Extracting congestion patterns

[0996] The server extracts congestion patterns from the analysis results. Specifically, it identifies specific congestion patterns using a clustering algorithm (e.g., K-means).

[0997] Specific behavior:

[0998] The server uses Scikit-learn to perform clustering using code like "kmeans = KMeans(n_clusters=3).fit(df[['Congestion', 'FlowIn', 'FlowOut']])" to classify congestion patterns.

[0999] input:

[1000] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[1001] output:

[1002] Congestion patterns by time of day and area.

[1003] Step 4: Generate optimal guidance path

[1004] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal guidance routes.

[1005] Specific behavior:

[1006] The server uses a genetic algorithm to search for the optimal solution with code like "result = genetic_algorithm.optimize(objective_function, population_size=100, generations=50)".

[1007] input:

[1008] Crowding pattern.

[1009] output:

[1010] Optimal guidance route.

[1011] Step 5: Send instructions

[1012] The server sends the generated guided route to the user's terminal, which analyzes it and notifies the user.

[1013] Specific behavior:

[1014] The server uses the REST API to send the guidance route to the endpoint "POST / send-instructions", and the user's device displays this information.

[1015] input:

[1016] Optimal guidance route.

[1017] output:

[1018] Instructions displayed on the user's device.

[1019] Step 6: Real-time monitoring and readjustment

[1020] The server receives real-time location information and movement speed from the user's device and readjusts the guidance route based on the newly collected data.

[1021] Specific behavior:

[1022] The server collects real-time data via WebSocket and generates new routes as needed and sends them again to the device.

[1023] input:

[1024] Location information and movement speed collected in real time.

[1025] output:

[1026] Realigned guidance path.

[1027] The above is the flow of program processing in this system.

[1028] (Application example 1)

[1029] 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."

[1030] Congestion in large facilities, commercial facilities, and other locations can be a factor that impairs the convenience and safety of users. There is a need to efficiently alleviate congestion caused by the flow of people in each area and time period and provide routes that allow users to move smoothly. However, a system that constantly monitors dynamically changing congestion conditions in real time and proposes optimal guidance routes has not yet been fully developed. It is also important to effectively utilize past congestion data to predict future congestion and develop countermeasures in advance. Therefore, the present invention aims to solve these problems by proposing a system that utilizes past people flow data to provide optimal guidance routes that adapt to dynamically changing congestion conditions in real time.

[1031] 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.

[1032] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data and identifying congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of guides and users, and means for proposing a route that optimizes the flow of users within a commercial facility based on past data. This makes it possible to effectively alleviate congestion within large facilities and commercial facilities and provide an environment in which users can move safely and comfortably.

[1033] "Past people flow data" refers to data including people's movement routes, location information, and duration of stay over a certain period of time in the past.

[1034] "Crowd patterns" are data that indicate the degree of crowding and congestion trends in a particular time period and area.

[1035] An "optimal route" is a recommended route to a specific destination that is generated to minimize congestion and evenly distribute waiting and travel times among users.

[1036] A "user device" is a portable electronic device carried by a user, such as a smartphone or tablet.

[1037] "Means for providing information in real time" refers to a system for instantly transmitting current congestion status and optimal route information to users' terminals.

[1038] "Actual congestion situation" refers to information that indicates the current state of people gathering and their travel routes at events or in everyday life.

[1039] "Guides" are personnel who are deployed on-site to provide instructions to users and support their movement.

[1040] A "commercial facility" is a building or surrounding area where many customers gather and make purchases, such as a shopping mall or department store.

[1041] "Flow lines" refer to the routes and directions that users take when moving within a facility.

[1042] The present invention is a system for optimizing user flow lines and alleviating congestion within large facilities and commercial facilities. This system collects and analyzes past people flow data, generates optimal guidance routes, sends instructions to user terminals, and makes adjustments in real time. Specific embodiments are described below.

[1043] 1. Data Collection and Analysis

[1044] The server retrieves past people flow data from a database. This data includes location information, movement paths, and duration of stay. The server analyzes this data using analytical tools (e.g., Python's Pandas or Scikit-learn) to identify the level of congestion for each time period and each area. This allows the server to extract the information necessary for predictions for the next event and for normal times.

[1045] As a specific example, the server analyzes data from a shopping mall during last year's Christmas season to discover areas that become crowded at specific times.

[1046] 2. Generating optimal guidance routes

[1047] Based on the analysis results, the server generates the optimal route to minimize congestion using AI algorithms (e.g., genetic algorithms and machine learning models). It also creates a plan to distribute passengers across routes to balance waiting time and travel time across all users and reduce unfairness.

[1048] As a specific example, the server generates routes that bypass areas where congestion is expected during specific times of the day, and plans to spread out users during those times.

[1049] 3. Send instructions to the user device

[1050] The server sends the generated route to the user's device, which analyzes the received instructions and notifies the user in real time.

[1051] As a specific example, the user's device may display the message, "Considering the current congestion situation, please turn right at the next intersection. Waiting time: approximately 15 minutes."

[1052] 4. Placement of guides and real-time adjustment

[1053] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[1054] As a specific example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends it to the user's terminal.

[1055] Prompt Sentence Examples

[1056] Design an application that analyzes the most efficient route within a specified shopping mall and notifies the user in real time. Crowd data will be based on past data and analyzed using KMeans clustering. Include specific data and the method of user notification.

[1057] As described above, in the embodiment of the present invention, it is possible to perform everything from past data analysis to real-time congestion management, centered on the server, which effectively alleviates congestion in large facilities and commercial facilities, and provides an environment in which users can move around safely and comfortably.

[1058] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1059] Step 1:

[1060] Data collection

[1061] The server retrieves historical people flow data from a database. This data includes location information, travel paths, and dwell times. The input is the historical data in the database, and the output is a dataset for analysis. Specifically, the server uses SQL queries to extract the required data from the database.

[1062] Step 2:

[1063] Data analysis

[1064] The server analyzes the acquired data using analysis tools (Python's Pandas and Scikit-learn) to identify the degree of congestion for each time period and each area. The input is the dataset acquired in step 1, and the output is the congestion pattern based on the analysis results. Specifically, the server performs clustering and statistical analysis to visualize the congestion pattern.

[1065] Step 3:

[1066] Generating optimal guidance routes

[1067] Based on the analysis results, the server generates the optimal guided route to minimize congestion. To do this, it uses an AI algorithm (genetic algorithm or machine learning model). The input is the congestion pattern identified in step 2, and the output is optimized route information. Specifically, the server runs the shortest route algorithm to generate optimal route data.

[1068] Step 4:

[1069] Sending guidance routes

[1070] The server sends the generated guidance route to the user's device. The input is the route information generated in step 3, and the output is route instructions to the user's device. Specifically, the server sends route data to the user's smartphone via API.

[1071] Step 5:

[1072] Real-time information provision

[1073] The device analyzes the instructions received from the server and notifies the user in real time. The input is the route instructions sent from the server, and the output is a notification message to the user. Specifically, the device uses the push notification function to notify the user of the next action.

[1074] Step 6:

[1075] Monitoring actual congestion status

[1076] The server receives real-time location information and movement speed from the user's device and monitors the current congestion situation based on that information. The input is real-time data sent from the user's device, and the output is the latest congestion situation. Specifically, the server analyzes the received data and displays it on a dashboard.

[1077] Step 7:

[1078] Re-adjustment of guidance route

[1079] The server readjusts the guidance route as needed based on the data collected in real time. The input is the real-time data obtained in step 6, and the output is the readjusted route information. Specifically, the server runs the route optimization algorithm again to generate a new route.

[1080] Step 8:

[1081] Sending revised guidance routes

[1082] The server sends the re-adjusted route to the guide and the user's device. The input is the route information regenerated in step 7, and the output is new instructions for the on-site guide and the user. Specifically, the server sends the updated information via the notification system.

[1083] 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.

[1084] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. In this system, a server collects and analyzes past people flow data to generate optimal guided routes, and an emotion engine is used to recognize the user's emotional state and adjust the guided route based on that, thereby increasing user satisfaction. Details of the system and a specific example implementation are provided below.

[1085] System Configuration

[1086] Data collection and analysis

[1087] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. The retrieved data is read using an analysis tool (such as Python's Pandas or Scikit-learn). The server analyzes the data to calculate congestion levels, number of people entering and leaving, average travel time, and other data for each time period and area, and identifies congestion patterns during the event.

[1088] Examples:

[1089] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1090] Generating optimal guidance methods

[1091] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[1092] Examples:

[1093] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[1094] Sending instructions to user terminal

[1095] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[1096] Examples:

[1097] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1098] Guide staff deployment and real-time adjustment

[1099] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[1100] Examples:

[1101] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[1102] User Emotion Recognition

[1103] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[1104] Examples:

[1105] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[1106] Emotion-based route adjustment

[1107] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, it can guide frustrated users to a route with a shorter waiting time to reduce stress.

[1108] Examples:

[1109] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[1110] Program processing

[1111] In this system, the program performs processing in the following procedure.

[1112] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[1113] Analysis of congestion patterns: The server identifies the degree of congestion for each time period and each area, and extracts congestion patterns based on that.

[1114] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[1115] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[1116] Real-time adjustment: The server monitors newly collected data and adjusts the guidance route and the deployment of guidance personnel as needed.

[1117] Emotion recognition: The server uses an emotion engine to recognize the user's emotional state and readjusts the guidance path based on the results.

[1118] As a result, the present invention realizes smooth people flow management and congestion relief during events, as well as improved travel efficiency and safety while taking into consideration the feelings of users.

[1119] The processing flow will be explained below.

[1120] Step 1:

[1121] The server retrieves people flow data collected from past events from the database, including participants' locations, routes, durations, and congestion levels.

[1122] Step 2:

[1123] The server analyzes the acquired people flow data using analytical tools (e.g., Python's Pandas or Scikit-learn), and calculates the congestion level, number of people entering and leaving, average travel time, etc. for each time period and area.

[1124] Step 3:

[1125] The server identifies congestion patterns. Specifically, based on the analysis results, it extracts patterns of congestion occurring in specific areas and time periods during events.

[1126] Examples:

[1127] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1128] Step 4:

[1129] Based on the identified congestion patterns, the server uses AI algorithms (e.g., genetic algorithms or machine learning models) to generate optimal guidance routes, taking into account the balance between waiting time and travel time for all participants.

[1130] Examples:

[1131] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[1132] Step 5:

[1133] The server then sends the generated optimal route to each user's device, including real-time travel instructions, congestion status, estimated waiting times, and other information.

[1134] Step 6:

[1135] The device analyzes the guidance instructions received from the server and notifies the user, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[1136] Examples:

[1137] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1138] Step 7:

[1139] The server also sends instructions to on-site traffic controllers, including where to position them during specific times and how to change their routes depending on traffic congestion.

[1140] Examples:

[1141] If the congestion becomes greater than expected at 8:40 p.m., the server sends an instruction to the attendant saying, "Please guide participants to use Route B."

[1142] Step 8:

[1143] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[1144] Examples:

[1145] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[1146] Step 9:

[1147] The server adjusts the route and waiting time based on the user's emotional state as recognized by the emotion engine. For example, it guides a frustrated user to a route with a shorter waiting time.

[1148] Examples:

[1149] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[1150] Step 10:

[1151] The server monitors newly collected data (location information and movement speed) in real time, allowing it to constantly understand the current congestion situation and readjust routes as necessary.

[1152] Examples:

[1153] The server will analyze the user's location data at 8:30 p.m., and if there is more congestion than expected, it will send new route instructions to the user's device and the guide.

[1154] Step 11:

[1155] The terminal receives new updated instructions from the server and notifies the user, so that the user is always provided with the latest route information.

[1156] Examples:

[1157] The terminal notifies the user of new instructions, such as "The congestion situation has changed, so please turn left at the next intersection."

[1158] Through these steps, the present invention achieves congestion relief during events, safer user movement, and improved convenience that takes user feelings into consideration.

[1159] Example 2

[1160] 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."

[1161] To alleviate congestion and improve participant movement efficiency at large-scale events, it is not enough to generate optimal guidance routes based on past data alone; it is also necessary to consider real-time congestion conditions and the emotional state of each user. Therefore, dynamic route adjustment based on emotional state is required to improve the user experience and ensure safe guidance.

[1162] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1163] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of the guide and the user, means for recognizing the user's emotional state, and means for adjusting the guide route based on the recognized emotional state. This enables flexible and effective guidance that takes into account real-time congestion conditions and the user's emotional state.

[1164] "People flow data" is data that records the movements of event participants, such as their location, route, length of stay, and level of congestion.

[1165] A "crowding pattern" is a tendency for participants to concentrate or disperse at a particular time or location, identified based on past people flow data.

[1166] A "guided route" is a route optimized to allow participants to move efficiently within the event venue.

[1167] A "user terminal" is a device held by a participant, such as a smartphone or tablet, that has the function of receiving and displaying information.

[1168] "Real-time monitoring" is a monitoring method that allows you to instantly grasp the congestion situation and movements of participants at an ongoing event.

[1169] "Emotional state" refers to the psychological state and emotions analyzed based on the user's facial expressions and biometric data.

[1170] An "emotion engine" is a system that includes software and algorithms for analyzing a user's emotional state.

[1171] A "genetic algorithm" is a computational method based on evolutionary theory and a type of AI algorithm used to find optimal solutions.

[1172] MODE FOR CARRYING OUT THE INVENTION

[1173] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. This system uses a server to collect and analyze past people flow data to generate optimal guide routes, and an emotion engine to recognize the user's emotional state and adjust the guide route based on that, thereby increasing user satisfaction.

[1174] Data collection and analysis

[1175] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. Using analysis tools such as Python's Pandas and Scikit-learn, the server reads the data and calculates congestion levels, number of people entering and leaving, average travel time, and other information for each time period and area, identifying congestion patterns during the event.

[1176] Examples:

[1177] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1178] Generating optimal guidance methods

[1179] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[1180] Examples:

[1181] The server plans to use routes B and C during the period from 8:00 p.m. to 9:00 p.m., as route A is congested.

[1182] Sending instructions to user terminal

[1183] The server sends the generated route to the user's device (e.g., smartphone or tablet), which then analyzes the received instructions and notifies the user in real time.

[1184] Examples:

[1185] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1186] Guide staff deployment and real-time adjustment

[1187] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[1188] Examples:

[1189] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[1190] User Emotion Recognition

[1191] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or feelings of unfairness felt by the user.

[1192] Examples:

[1193] The server collects facial expression data via the user's smartphone camera, analyzes it using an emotion engine, and detects whether the user is dissatisfied.

[1194] Emotion-based route adjustment

[1195] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, a frustrated user can be guided to a route with a shorter waiting time to reduce stress.

[1196] Examples:

[1197] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[1198] This system will not only streamline the movement of event attendees and reduce congestion, but also provide personalized guidance that takes into account the user's emotions, improving the overall user experience and enabling safe and efficient transportation.

[1199] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1200] Step 1: Data collection

[1201] Input: The server retrieves past event data from the database. People flow data includes participant location information, movement routes, stay time, congestion level, etc.

[1202] Processing: The server uses Python's Pandas to read the acquired data and manage it as a DataFrame. It then deletes unnecessary data and imputes missing values.

[1203] Output: A clean, pre-processed dataset.

[1204] Specific behavior:

[1205] The server queries the database to retrieve the data.

[1206] Read the data as a DataFrame using Pandas.

[1207] Remove unnecessary columns and impute missing values ​​appropriately.

[1208] Step 2: Analyze crowding patterns

[1209] Input: The server takes as input the dataset that has been preprocessed.

[1210] Processing: Use Pandas to aggregate the number of participants for each time period, and use Scikit-learn to apply K-means clustering to cluster congested areas.

[1211] Output: Quantified congestion levels for each time period and area.

[1212] Specific behavior:

[1213] Use Pandas to count the number of participants for specific time periods and areas.

[1214] Apply Scikit-learn's K-means clustering to identify the degree of congestion for each cluster.

[1215] Visualize (graph) the results.

[1216] Step 3: Generate optimal guidance path

[1217] Input: The server inputs the results of the congestion analysis.

[1218] Processing: Genetic algorithms are used to generate optimal guidance routes, balancing waiting and travel times across participants.

[1219] Output: A set of optimized guided paths.

[1220] Specific behavior:

[1221] The server generates initial routes and evaluates the latency and travel time of each route.

[1222] A fitness function is calculated and new paths are generated through crossover and mutation operations.

[1223] This process is repeated until the optimal route is found.

[1224] Step 4: Send instructions

[1225] Input: The server takes the optimized guided route as input.

[1226] Processing: The server generates and sends a message containing the appropriate route to each user's terminal.

[1227] Output: A message about the route delivered to the user's device.

[1228] Specific behavior:

[1229] The server generates a message to be sent to each user's terminal.

[1230] Sends a message to the user's terminal.

[1231] The user's device receives the message and displays a notification on the screen.

[1232] Step 5: Real-time adjustments

[1233] Input: The server takes as input the congestion status data newly collected in real time.

[1234] Processing: The server recalculates the current congestion level based on the collected data and regenerates the guidance route if necessary.

[1235] Output: The latest re-adjusted guidance path.

[1236] Specific behavior:

[1237] The server periodically collects current congestion data.

[1238] Analyze congestion data and generate new guidance routes as needed.

[1239] The regenerated route is sent to the user and the driver.

[1240] Step 6: Emotion Recognition

[1241] Input: The server inputs the user's facial expression data and biometric data.

[1242] Processing: Analyze the user's emotional state using an emotion engine. Determine the level of stress or frustration based on facial expression data and heart rate data.

[1243] Output: Analysis results about the user's emotional state.

[1244] Specific behavior:

[1245] The server acquires facial expression data through the user's smartphone camera.

[1246] Facial expression data and heart rate data are input into an emotion engine to determine emotions.

[1247] The emotion engine returns the analysis results to the server.

[1248] Step 7: Emotion-Based Path Adjustment

[1249] Input: The server takes the output data of the emotion engine as input.

[1250] Processing: Based on the emotional state of the user, we regenerate a more effective guidance route. In particular, for dissatisfied users, we make adjustments to reduce waiting time.

[1251] Output: New adjusted guidance path.

[1252] Specific behavior:

[1253] The server receives and analyzes the output from the emotion engine.

[1254] Regenerate new routes based on the user's emotional state.

[1255] The new route information is sent to the user's terminal.

[1256] (Application example 2)

[1257] 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."

[1258] Congestion in physical stores reduces customer movement efficiency and significantly reduces customer satisfaction. Congestion, especially during peak hours, can increase waiting times and make it difficult to move around. In the worst case, it can lead to customers leaving the store, negatively impacting sales. Furthermore, uniform guidance that does not take into account the emotional state of customers makes it difficult to meet the needs of individual customers. Therefore, there is a need for a method to efficiently manage congestion in stores and encourage optimal movement based on customers' emotional state.

[1259] 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.

[1260] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for collecting facial expression data and biometric data of users and recognizing their emotional state, means for adjusting the guide route based on the recognized emotional state, means for transmitting the generated or adjusted guide route to the user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, and means for transmitting the readjusted guide route to the terminals of guides and users. This effectively alleviates congestion in physical stores, improving customer movement efficiency and satisfaction.

[1261] "Past people flow data" refers to historical information collected at events and physical stores, such as the location information of customers, their movement routes, length of stay, and congestion levels.

[1262] "Congestion patterns" are analysis results that show the characteristics of people flow and density in specific time periods and areas.

[1263] An "invitation route" is a route designed to guide participants and visitors along a specific path to reduce congestion.

[1264] "Facial expression data" refers to information extracted from a user's facial expressions, and is data captured using a camera or image analysis technology.

[1265] "Biometric data" is data obtained by measuring a user's physical condition, such as heart rate or stress level.

[1266] "Emotional state" refers to the psychological state such as stress, dissatisfaction, or relief felt by the user.

[1267] "User terminal" refers to an information and communication device carried by an individual user, such as a smartphone or tablet.

[1268] "Real-time monitoring" means instantly observing and analyzing ongoing situations and taking immediate action if necessary.

[1269] "Readjustment" means reviewing and optimizing the initially set guidance route and layout according to the situation.

[1270] A "guide" is a person whose role is to actually guide people on-site.

[1271] This invention is a system for reducing congestion in brick-and-mortar stores and improving customer movement efficiency and satisfaction. In this system, a server collects and analyzes past people flow data to generate optimal guide routes, and an emotion engine recognizes the user's emotional state and adjusts the guide route based on that, thereby increasing user satisfaction.

[1272] System Configuration

[1273] Data collection and analysis

[1274] The server retrieves people flow data collected from past brick-and-mortar stores from the database. This people flow data includes information on customers' locations, movement routes, length of stay, and congestion levels. The server then analyzes the retrieved data using Python data analysis tools (e.g., Pandas and Scikit-learn). As a result of the analysis, congestion levels, number of people entering and leaving the store, and average travel times for each time period and area are calculated.

[1275] For example, the server analyzes data from 6:00 PM to 7:00 PM at a shopping mall on a Saturday last year and discovers that the food court is very crowded during this time.

[1276] Generating optimal guidance methods

[1277] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, balancing waiting time and travel time and planning multiple routes to reduce unfairness.

[1278] For example, the server may plan to prioritize a route that passes through the book section during the period when the food court is crowded between 6:00 PM and 7:00 PM.

[1279] Sending instructions to user terminal

[1280] The server sends the generated or adjusted route to the user's device (smartphone or tablet), which analyzes the received instructions and notifies the user in real time.

[1281] For example, the user may be notified with a message such as, "The food court is currently crowded. We recommend turning right and passing through the book section. Travel time: approximately 8 minutes."

[1282] Emotion recognition and re-routing

[1283] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or frustration.

[1284] For example, the server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect whether the user is feeling stressed.

[1285] The system adjusts routes and waiting times based on the user's perceived emotional state. For example, if a user feels stressed, the system will guide them to a less crowded route and shorten their waiting time.

[1286] Hardware and software used

[1287] Hardware: Server (data collection, analysis, route generation), smartphone (data collection and instruction display), smartphone camera (emotion recognition)

[1288] Software: Python (data analysis: Pandas, Scikit-learn), Scipy (optimization calculation), FER library (sentiment analysis)

[1289] Specific examples

[1290] An example of use in a brick-and-mortar shopping mall is shown below.

[1291] Prompt statement:

[1292] "Considering how crowded the shopping mall is right now at 6:00 PM, please tell me the easiest route."

[1293] (System response):

[1294] "The food court is currently crowded. We recommend turning right and taking the route via the book section. Travel time: approximately 8 minutes."

[1295] This system allows customers to move efficiently while avoiding crowds, while also improving customer satisfaction by providing the optimal route based on their emotional state.

[1296] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1297] Step 1:

[1298] The server retrieves past people flow data from the database. This data includes customer location information, movement paths, stay times, congestion levels, etc. The input is the past people flow data, and the output is the retrieved dataset. Specifically, the required information is extracted from the database using SQL queries.

[1299] Step 2:

[1300] The server analyzes the acquired people flow data using Python data analysis tools (such as Pandas). The input is the dataset acquired in step 1, and the output is the analysis results. Specifically, the data is grouped by time period and area, and the degree of congestion, number of people entering and leaving, and average travel time are calculated.

[1301] Step 3:

[1302] The server identifies congestion patterns based on the analysis results. This identification process uses a clustering algorithm (e.g., K-Means) from a machine learning model (such as Scikit-learn). The input is the analysis results, and the output is the congestion patterns for each time period and each area. Specifically, the visitor data is classified into clusters, and highly congested areas are identified.

[1303] Step 4:

[1304] The server generates the optimal guided route based on the results of analyzing congestion patterns. It uses AI algorithms (genetic algorithms and machine learning models) to create multiple routes and balance waiting time and travel time. The input is the congestion pattern, and the output is the guided route. Specifically, it runs a simulation to identify which route is optimal.

[1305] Step 5:

[1306] The server collects the user's facial expression data and biometric data. This data is acquired through the smartphone's camera and sensors. The input is the user's image data and biometric data, and the output is the processed raw data. Specifically, the image data is uploaded to the cloud, and the biometric data is collected via Bluetooth or other means.

[1307] Step 6:

[1308] The server uses an emotion engine to recognize the user's emotional state. This engine uses the FER library to analyze facial expression data and biometric data. The input is the facial expression data and biometric data collected in the previous step, and the output is the analysis result of the emotional state (e.g., stress, dissatisfaction, relief). Specifically, it performs image analysis and signal analysis to identify emotions.

[1309] Step 7:

[1310] The server adjusts the guidance route based on the recognized emotional state. Taking the emotional state into account, it recalculates the route to provide a more comfortable route. The input is the analysis result of the emotional state, and the output is the adjusted guidance route. Specifically, it responds by presenting a less crowded route to a user who is feeling stressed.

[1311] Step 8:

[1312] The server sends the generated or adjusted guided route to the user's device. The input is the adjusted guided route, and the output is a notification message to the device. Specifically, it sends instructions to the device in real time via an API.

[1313] Step 9:

[1314] The terminal provides real-time information based on the received guidance route. The input is the guidance route information from the server, and the output is a message to be displayed to the user. Specifically, the message is displayed to the user using the smartphone's notification function.

[1315] Step 10:

[1316] The server monitors the actual congestion situation in real time and readjusts the guided route as necessary. The input is real-time location information, movement speed, and emotional state data received from the device, and the output is the readjusted guided route. Specifically, it analyzes new data from the device and updates the guided route.

[1317] Step 11:

[1318] The server sends the readjusted guidance route to the guide and the user's device. The input is the readjusted guidance route, and the output is an instruction message to the guide and the device. Specifically, by distributing the recalculated route information again, optimal guidance tailored to the situation on site is realized.

[1319] 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.

[1320] 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.

[1321] 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.

[1322] [Fourth embodiment]

[1323] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1324] 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.

[1325] 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).

[1326] 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.

[1327] 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.

[1328] 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).

[1329] 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. 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.

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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."

[1336] This invention relates to a system that alleviates congestion during events and improves the efficiency of participant movement. This system enables safe and efficient movement of users by having a server collect and analyze past people flow data and generate optimal guide routes. Details of the system and a specific example implementation are provided below.

[1337] System Configuration

[1338] Data collection and analysis

[1339] The server retrieves people flow data (e.g., location information, movement paths, duration of stay, etc.) collected from past events from a database. The collected data is analyzed using analytical tools (e.g., Python's Pandas or Scikit-learn). The server generates indicators such as congestion level, number of people entering and leaving, and average travel time for each time period and each area, and extracts the information necessary for predicting the next event.

[1340] Examples:

[1341] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1342] Generating optimal guidance methods

[1343] The server generates optimal routes based on the analysis to minimize congestion, using AI algorithms (e.g., genetic algorithms and machine learning models), and creates a plan to distribute traffic among routes to balance waiting and travel times across all participants and reduce perceived unfairness.

[1344] Examples:

[1345] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[1346] Sending instructions to user terminal

[1347] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[1348] Examples:

[1349] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1350] Guide staff deployment and real-time adjustment

[1351] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[1352] Examples:

[1353] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[1354] Program processing

[1355] In this system, the program performs processing in the following procedure.

[1356] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[1357] Analysis of congestion patterns: The server uses analytical tools to identify the level of congestion for each time period and area, and extracts congestion patterns based on that.

[1358] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[1359] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[1360] Real-time adjustment: The server monitors newly collected data and adjusts the guidance routes and the deployment of guidance staff as needed, allowing it to respond to changing congestion conditions in real time.

[1361] As a result, the present invention alleviates congestion during events and improves safety for participants.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] The server retrieves people flow data collected from past events from the database, including participant location information, movement paths, stay times, congestion levels, etc. The retrieved data is read using analysis tools (e.g., Python's Pandas or Scikit-learn).

[1365] Step 2:

[1366] The server analyzes the acquired data. Specifically, it calculates the degree of congestion, the number of people entering and leaving, and the average travel time for each time period and each area. Based on the analysis results, it identifies the congestion patterns that will occur in specific areas and routes during the event.

[1367] Step 3:

[1368] Based on the analysis results, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, and plans to distribute participants across multiple routes to balance waiting and travel times for all participants.

[1369] Step 4:

[1370] The server then sends the generated route to each user's device. The route includes real-time travel instructions, congestion information, estimated waiting time, and other information, allowing each user's device to receive individual instructions.

[1371] Step 5:

[1372] The device analyzes the guidance instructions received from the server and notifies the user in real time, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[1373] Step 6:

[1374] The server also sends instructions to on-site guides, including where to position them during specific times and how to change routes depending on congestion levels, enabling appropriate guidance at the site.

[1375] Step 7:

[1376] Users follow the notification from their device and travel along the designated route. Real-time instructions allow users to avoid congestion and reach their destination efficiently.

[1377] Step 8:

[1378] The server monitors newly collected data in real time (for example, user location information and movement speed), which allows the current congestion situation to be continuously grasped.

[1379] Step 9:

[1380] The server analyzes the collected real-time data and adjusts the guidance route and the deployment of guides as necessary. The adjusted guidance route is then sent back to the user's device and the guide.

[1381] Step 10:

[1382] The terminal then notifies the user of the updated instructions, allowing the user to receive route instructions that reflect the latest congestion conditions.

[1383] Through these steps, the system will enable smooth people flow management and congestion relief during events.

[1384] Example 1

[1385] 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."

[1386] During events, large numbers of participants gather in specific areas or routes at the same time, causing congestion that reduces safety, comfort, and travel efficiency. It is important to eliminate this congestion and establish guidance methods that allow participants to move around efficiently and safely. However, conventional methods have difficulty grasping congestion situations in real time and providing appropriate guidance routes based on that information, making them ineffective. Therefore, a system that can solve these issues, efficiently alleviate congestion, and improve safety and comfort is needed.

[1387] 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.

[1388] In this invention, the server includes means for acquiring past people flow data, means for identifying congestion patterns using an analysis tool for analyzing the acquired people flow data, means for generating an optimal guide route using an AI algorithm based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for notifying the user's terminal based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary based on newly collected data, and means for transmitting the readjusted guide route to the terminals of guides and users. This enables real-time understanding of congestion conditions and subsequent rapid and accurate guidance.

[1389] "Past people flow data" refers to information such as the location, movement route, and length of stay of individual users collected at past events.

[1390] "Analysis Tools" refers to software tools used to analyze data, including commonly used data analysis libraries and algorithms.

[1391] A "congestion pattern" indicates the tendency for people to concentrate and move around in a particular time period or area, and is determined based on indicators such as the degree of congestion, the number of people entering and leaving, and average travel time.

[1392] "AI algorithm" refers to a computational method for deriving optimal solutions using artificial intelligence technology, and specifically includes genetic algorithms and machine learning models.

[1393] A "guided route" is a route that a user should follow when moving from one point to another, and is designed to ensure optimal movement.

[1394] "User Device" means an electronic device held by a User that receives and displays instructions and notifications, including a smartphone or tablet.

[1395] "Real-time monitoring" refers to the immediate observation, analysis, and processing of ongoing situations, including the location and speed of users.

[1396] A "guide" refers to a person in charge of guiding participants at the event site, and is responsible for changing their location and route based on instructions from the server.

[1397] This invention relates to a system that alleviates congestion at events and improves the efficiency of participant movement. This system generates optimal guided routes based on past people flow data and readjusts the routes according to real-time congestion conditions, ensuring safe and efficient movement.

[1398] The server connects to a database to retrieve historical people flow data, including location information, movement paths, and dwell times collected during past events. Data is retrieved using standard database queries.

[1399] The server then analyzes the data using Python analysis tools (such as Pandas or Scikit-learn). Specifically, it calculates the congestion level, number of people entering and leaving, and average travel time for each area and time period. To identify congestion patterns, it uses a clustering algorithm (such as K-means) to extract time periods and areas where large-scale congestion occurs.

[1400] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal routes. The algorithms perform calculations to minimize congestion and travel time. The generated routes are designed to balance total travel time and evenly distribute waiting time among all participants.

[1401] The server then sends the generated route guidance to the user's device (smartphone or tablet). The device receives the instructions and notifies the user in real time. The message displayed on the user's device includes specific instructions such as "Turn right at the next intersection. Waiting time: approximately 15 minutes."

[1402] The server also receives real-time location information and movement speed from each device and readjusts the guidance route based on the newly collected data. This process involves collecting real-time data using WebSockets and generating new routes as needed and sending them back to the device.

[1403] The server also sends instructions to traffic controllers to assist them in guiding traffic at specific times and locations. For example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends this to the devices of the traffic controllers and users.

[1404] Specific examples

[1405] Analysis based on data from 8:00 p.m. to 9:00 p.m. at last year's fireworks display predicted that certain routes would be extremely congested, so the server planned to use routes B and C.

[1406] Prompt Sentence Examples

[1407] "Based on data from last year's fireworks display, identify routes that are most congested between 8:00 and 9:00 p.m."

[1408] "Suggest multiple routes that are most efficient at a given time to reduce congestion."

[1409] "Adjust the optimal route based on the user's location information in real time."

[1410] As described above, the present invention alleviates congestion during events and improves safety for participants.

[1411] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1412] System program processing flow

[1413] Step 1: Data collection

[1414] The server retrieves people flow data from a database of past events, which stores location information, movement paths, and duration of stays collected from past events.

[1415] Specific behavior:

[1416] The server connects to the database using an SQL query to retrieve data for a specific date: SELECT FROM EventData WHERE Date = '2022-07-30'.

[1417] input:

[1418] People flow data stored in a database.

[1419] output:

[1420] A people flow dataset to be passed to analysis tools.

[1421] Step 2: Data analysis

[1422] The server analyzes the acquired data using Python libraries such as Pandas and Scikit-learn, calculating the congestion level, number of people entering and leaving, and average travel time for each area and time period.

[1423] Specific behavior:

[1424] The server creates a data frame using Pandas and executes "df.groupby(['Area', 'Time']).size()" to calculate the congestion level for each area and time period.

[1425] input:

[1426] Acquired people flow data.

[1427] output:

[1428] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[1429] Step 3: Extracting congestion patterns

[1430] The server extracts congestion patterns from the analysis results. Specifically, it identifies specific congestion patterns using a clustering algorithm (e.g., K-means).

[1431] Specific behavior:

[1432] The server uses Scikit-learn to perform clustering using code like "kmeans = KMeans(n_clusters=3).fit(df[['Congestion', 'FlowIn', 'FlowOut']])" to classify congestion patterns.

[1433] input:

[1434] Congestion level, number of people entering and leaving, and average travel time for each area and time period.

[1435] output:

[1436] Congestion patterns by time of day and area.

[1437] Step 4: Generate optimal guidance path

[1438] Based on the identified congestion patterns, the server uses AI algorithms (such as genetic algorithms and machine learning models) to generate optimal guidance routes.

[1439] Specific behavior:

[1440] The server uses a genetic algorithm to search for the optimal solution with code like "result = genetic_algorithm.optimize(objective_function, population_size=100, generations=50)".

[1441] input:

[1442] Crowding pattern.

[1443] output:

[1444] Optimal guidance route.

[1445] Step 5: Send instructions

[1446] The server sends the generated guided route to the user's terminal, which analyzes it and notifies the user.

[1447] Specific behavior:

[1448] The server uses the REST API to send the guidance route to the endpoint "POST / send-instructions", and the user's device displays this information.

[1449] input:

[1450] Optimal guidance route.

[1451] output:

[1452] Instructions displayed on the user's device.

[1453] Step 6: Real-time monitoring and readjustment

[1454] The server receives real-time location information and movement speed from the user's device and readjusts the guidance route based on the newly collected data.

[1455] Specific behavior:

[1456] The server collects real-time data via WebSocket and generates new routes as needed and sends them again to the device.

[1457] input:

[1458] Location information and movement speed collected in real time.

[1459] output:

[1460] Realigned guidance path.

[1461] The above is the flow of program processing in this system.

[1462] (Application example 1)

[1463] 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."

[1464] Congestion in large facilities, commercial facilities, and other locations can be a factor that impairs the convenience and safety of users. There is a need to efficiently alleviate congestion caused by the flow of people in each area and time period and provide routes that allow users to move smoothly. However, a system that constantly monitors dynamically changing congestion conditions in real time and proposes optimal guidance routes has not yet been fully developed. It is also important to effectively utilize past congestion data to predict future congestion and develop countermeasures in advance. Therefore, the present invention aims to solve these problems by proposing a system that utilizes past people flow data to provide optimal guidance routes that adapt to dynamically changing congestion conditions in real time.

[1465] 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.

[1466] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data and identifying congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of guides and users, and means for proposing a route that optimizes the flow of users within a commercial facility based on past data. This makes it possible to effectively alleviate congestion within large facilities and commercial facilities and provide an environment in which users can move safely and comfortably.

[1467] "Past people flow data" refers to data including people's movement routes, location information, and duration of stay over a certain period of time in the past.

[1468] "Crowd patterns" are data that indicate the degree of crowding and congestion trends in a particular time period and area.

[1469] An "optimal route" is a recommended route to a specific destination that is generated to minimize congestion and evenly distribute waiting and travel times among users.

[1470] A "user device" is a portable electronic device carried by a user, such as a smartphone or tablet.

[1471] "Means for providing information in real time" refers to a system for instantly transmitting current congestion status and optimal route information to users' terminals.

[1472] "Actual congestion situation" refers to information that indicates the current state of people gathering and their travel routes at events or in everyday life.

[1473] "Guides" are personnel who are deployed on-site to provide instructions to users and support their movement.

[1474] A "commercial facility" is a building or surrounding area where many customers gather and make purchases, such as a shopping mall or department store.

[1475] "Flow lines" refer to the routes and directions that users take when moving within a facility.

[1476] The present invention is a system for optimizing user flow lines and alleviating congestion within large facilities and commercial facilities. This system collects and analyzes past people flow data, generates optimal guidance routes, sends instructions to user terminals, and makes adjustments in real time. Specific embodiments are described below.

[1477] 1. Data Collection and Analysis

[1478] The server retrieves past people flow data from a database. This data includes location information, movement paths, and duration of stay. The server analyzes this data using analytical tools (e.g., Python's Pandas or Scikit-learn) to identify the level of congestion for each time period and each area. This allows the server to extract the information necessary for predictions for the next event and for normal times.

[1479] As a specific example, the server analyzes data from a shopping mall during last year's Christmas season to discover areas that become crowded at specific times.

[1480] 2. Generating optimal guidance routes

[1481] Based on the analysis results, the server generates the optimal route to minimize congestion using AI algorithms (e.g., genetic algorithms and machine learning models). It also creates a plan to distribute passengers across routes to balance waiting time and travel time across all users and reduce unfairness.

[1482] As a specific example, the server generates routes that bypass areas where congestion is expected during specific times of the day, and plans to spread out users during those times.

[1483] 3. Send instructions to the user device

[1484] The server sends the generated route to the user's device, which analyzes the received instructions and notifies the user in real time.

[1485] As a specific example, the user's device may display the message, "Considering the current congestion situation, please turn right at the next intersection. Waiting time: approximately 15 minutes."

[1486] 4. Placement of guides and real-time adjustment

[1487] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes if necessary. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the route as needed.

[1488] As a specific example, if unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, such as "Turn left at the next intersection," and sends it to the user's terminal.

[1489] Prompt Sentence Examples

[1490] Design an application that analyzes the most efficient route within a specified shopping mall and notifies the user in real time. Crowd data will be based on past data and analyzed using KMeans clustering. Include specific data and the method of user notification.

[1491] As described above, in the embodiment of the present invention, it is possible to perform everything from past data analysis to real-time congestion management, centered on the server, which effectively alleviates congestion in large facilities and commercial facilities, and provides an environment in which users can move around safely and comfortably.

[1492] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1493] Step 1:

[1494] Data collection

[1495] The server retrieves historical people flow data from a database. This data includes location information, travel paths, and dwell times. The input is the historical data in the database, and the output is a dataset for analysis. Specifically, the server uses SQL queries to extract the required data from the database.

[1496] Step 2:

[1497] Data analysis

[1498] The server analyzes the acquired data using analysis tools (Python's Pandas and Scikit-learn) to identify the degree of congestion for each time period and each area. The input is the dataset acquired in step 1, and the output is the congestion pattern based on the analysis results. Specifically, the server performs clustering and statistical analysis to visualize the congestion pattern.

[1499] Step 3:

[1500] Generating optimal guidance routes

[1501] Based on the analysis results, the server generates the optimal guided route to minimize congestion. To do this, it uses an AI algorithm (genetic algorithm or machine learning model). The input is the congestion pattern identified in step 2, and the output is optimized route information. Specifically, the server runs the shortest route algorithm to generate optimal route data.

[1502] Step 4:

[1503] Sending guidance routes

[1504] The server sends the generated guidance route to the user's device. The input is the route information generated in step 3, and the output is route instructions to the user's device. Specifically, the server sends route data to the user's smartphone via API.

[1505] Step 5:

[1506] Real-time information provision

[1507] The device analyzes the instructions received from the server and notifies the user in real time. The input is the route instructions sent from the server, and the output is a notification message to the user. Specifically, the device uses the push notification function to notify the user of the next action.

[1508] Step 6:

[1509] Monitoring actual congestion status

[1510] The server receives real-time location information and movement speed from the user's device and monitors the current congestion situation based on that information. The input is real-time data sent from the user's device, and the output is the latest congestion situation. Specifically, the server analyzes the received data and displays it on a dashboard.

[1511] Step 7:

[1512] Re-adjustment of guidance route

[1513] The server readjusts the guidance route as needed based on the data collected in real time. The input is the real-time data obtained in step 6, and the output is the readjusted route information. Specifically, the server runs the route optimization algorithm again to generate a new route.

[1514] Step 8:

[1515] Sending revised guidance routes

[1516] The server sends the re-adjusted route to the guide and the user's device. The input is the route information regenerated in step 7, and the output is new instructions for the on-site guide and the user. Specifically, the server sends the updated information via the notification system.

[1517] 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.

[1518] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. In this system, a server collects and analyzes past people flow data to generate optimal guided routes, and an emotion engine is used to recognize the user's emotional state and adjust the guided route based on that, thereby increasing user satisfaction. Details of the system and a specific example implementation are provided below.

[1519] System Configuration

[1520] Data collection and analysis

[1521] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. The retrieved data is read using an analysis tool (such as Python's Pandas or Scikit-learn). The server analyzes the data to calculate congestion levels, number of people entering and leaving, average travel time, and other data for each time period and area, and identifies congestion patterns during the event.

[1522] Examples:

[1523] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1524] Generating optimal guidance methods

[1525] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[1526] Examples:

[1527] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[1528] Sending instructions to user terminal

[1529] The server sends the generated guidance route to the user's device (e.g., smartphone, tablet), which analyzes the received instructions and notifies the user in real time.

[1530] Examples:

[1531] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1532] Guide staff deployment and real-time adjustment

[1533] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[1534] Examples:

[1535] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[1536] User Emotion Recognition

[1537] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[1538] Examples:

[1539] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[1540] Emotion-based route adjustment

[1541] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, it can guide frustrated users to a route with a shorter waiting time to reduce stress.

[1542] Examples:

[1543] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[1544] Program processing

[1545] In this system, the program performs processing in the following procedure.

[1546] Data collection: The server retrieves past event data from the database and analyzes it using analysis tools.

[1547] Analysis of congestion patterns: The server identifies the degree of congestion for each time period and each area, and extracts congestion patterns based on that.

[1548] Route generation: The server uses an AI algorithm to generate an optimal route based on the analysis results, balancing waiting time and travel time for all participants.

[1549] Instruction transmission: The server transmits the generated guidance route to the user's device in real time. The user's device notifies the user of the received instructions.

[1550] Real-time adjustment: The server monitors newly collected data and adjusts the guidance route and the deployment of guidance personnel as needed.

[1551] Emotion recognition: The server uses an emotion engine to recognize the user's emotional state and readjusts the guidance path based on the results.

[1552] As a result, the present invention realizes smooth people flow management and congestion relief during events, as well as improved travel efficiency and safety while taking into consideration the feelings of users.

[1553] The processing flow will be explained below.

[1554] Step 1:

[1555] The server retrieves people flow data collected from past events from the database, including participants' locations, routes, durations, and congestion levels.

[1556] Step 2:

[1557] The server analyzes the acquired people flow data using analytical tools (e.g., Python's Pandas or Scikit-learn), and calculates the congestion level, number of people entering and leaving, average travel time, etc. for each time period and area.

[1558] Step 3:

[1559] The server identifies congestion patterns. Specifically, based on the analysis results, it extracts patterns of congestion occurring in specific areas and time periods during events.

[1560] Examples:

[1561] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1562] Step 4:

[1563] Based on the identified congestion patterns, the server uses AI algorithms (e.g., genetic algorithms or machine learning models) to generate optimal guidance routes, taking into account the balance between waiting time and travel time for all participants.

[1564] Examples:

[1565] The server plans to use routes B and C during the hours between 8:00 PM and 9:00 PM, since route A is congested during this time.

[1566] Step 5:

[1567] The server then sends the generated optimal route to each user's device, including real-time travel instructions, congestion status, estimated waiting times, and other information.

[1568] Step 6:

[1569] The device analyzes the guidance instructions received from the server and notifies the user, including specific directions, how to move, and instructions on how to change routes to avoid congestion.

[1570] Examples:

[1571] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1572] Step 7:

[1573] The server also sends instructions to on-site traffic controllers, including where to position them during specific times and how to change their routes depending on traffic congestion.

[1574] Examples:

[1575] If the congestion becomes greater than expected at 8:40 p.m., the server sends an instruction to the attendant saying, "Please guide participants to use Route B."

[1576] Step 8:

[1577] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect the stress or sense of unfairness the user is feeling.

[1578] Examples:

[1579] The server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect when the user is feeling dissatisfied.

[1580] Step 9:

[1581] The server adjusts the route and waiting time based on the user's emotional state as recognized by the emotion engine. For example, it guides a frustrated user to a route with a shorter waiting time.

[1582] Examples:

[1583] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[1584] Step 10:

[1585] The server monitors newly collected data (location information and movement speed) in real time, allowing it to constantly understand the current congestion situation and readjust routes as necessary.

[1586] Examples:

[1587] The server will analyze the user's location data at 8:30 p.m., and if there is more congestion than expected, it will send new route instructions to the user's device and the guide.

[1588] Step 11:

[1589] The terminal receives new updated instructions from the server and notifies the user, so that the user is always provided with the latest route information.

[1590] Examples:

[1591] The terminal notifies the user of new instructions, such as "The congestion situation has changed, so please turn left at the next intersection."

[1592] Through these steps, the present invention achieves congestion relief during events, safer user movement, and improved convenience that takes user feelings into consideration.

[1593] Example 2

[1594] 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."

[1595] To alleviate congestion and improve participant movement efficiency at large-scale events, it is not enough to generate optimal guidance routes based on past data alone; it is also necessary to consider real-time congestion conditions and the emotional state of each user. Therefore, dynamic route adjustment based on emotional state is required to improve the user experience and ensure safe guidance.

[1596] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1597] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for transmitting the generated guide route to a user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, means for transmitting the readjusted guide route to the terminals of the guide and the user, means for recognizing the user's emotional state, and means for adjusting the guide route based on the recognized emotional state. This enables flexible and effective guidance that takes into account real-time congestion conditions and the user's emotional state.

[1598] "People flow data" is data that records the movements of event participants, such as their location, route, length of stay, and level of congestion.

[1599] A "crowding pattern" is a tendency for participants to concentrate or disperse at a particular time or location, identified based on past people flow data.

[1600] A "guided route" is a route optimized to allow participants to move efficiently within the event venue.

[1601] A "user terminal" is a device held by a participant, such as a smartphone or tablet, that has the function of receiving and displaying information.

[1602] "Real-time monitoring" is a monitoring method that allows you to instantly grasp the congestion situation and movements of participants at an ongoing event.

[1603] "Emotional state" refers to the psychological state and emotions analyzed based on the user's facial expressions and biometric data.

[1604] An "emotion engine" is a system that includes software and algorithms for analyzing a user's emotional state.

[1605] A "genetic algorithm" is a computational method based on evolutionary theory and a type of AI algorithm used to find optimal solutions.

[1606] MODE FOR CARRYING OUT THE INVENTION

[1607] This invention relates to a system that alleviates congestion during events, improves participant movement efficiency, and recognizes and optimizes user emotions. This system uses a server to collect and analyze past people flow data to generate optimal guide routes, and an emotion engine to recognize the user's emotional state and adjust the guide route based on that, thereby increasing user satisfaction.

[1608] Data collection and analysis

[1609] The server retrieves people flow data collected from past events from the database. This data includes participants' location information, movement routes, length of stay, and congestion levels. Using analysis tools such as Python's Pandas and Scikit-learn, the server reads the data and calculates congestion levels, number of people entering and leaving, average travel time, and other information for each time period and area, identifying congestion patterns during the event.

[1610] Examples:

[1611] The server analyzes data from 8:00 p.m. to 9:00 p.m. from last year's fireworks festival and discovers that certain routes are extremely congested during this time.

[1612] Generating optimal guidance methods

[1613] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion. In doing so, it balances waiting time and travel time for all participants and creates a plan to distribute people across multiple routes to reduce unfairness.

[1614] Examples:

[1615] The server plans to use routes B and C during the period from 8:00 p.m. to 9:00 p.m., as route A is congested.

[1616] Sending instructions to user terminal

[1617] The server sends the generated route to the user's device (e.g., smartphone or tablet), which then analyzes the received instructions and notifies the user in real time.

[1618] Examples:

[1619] The user's device will display the message, "Please turn right at the next intersection, taking into account the current congestion situation. Waiting time: approximately 15 minutes."

[1620] Guide staff deployment and real-time adjustment

[1621] The server also sends instructions to on-site guides, including where to place them during specific times and how to change their routes depending on congestion. The server also monitors newly collected data in real time (e.g., user location and speed) and adjusts the guided routes as needed.

[1622] Examples:

[1623] If unexpected congestion occurs at 8:40 p.m., the server generates a new instruction, "Turn left at the next intersection," and sends it to the user's device.

[1624] User Emotion Recognition

[1625] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or feelings of unfairness felt by the user.

[1626] Examples:

[1627] The server collects facial expression data via the user's smartphone camera, analyzes it using an emotion engine, and detects whether the user is dissatisfied.

[1628] Emotion-based route adjustment

[1629] The server adjusts the route and waiting time based on the emotional state recognized by the emotion engine. For example, a frustrated user can be guided to a route with a shorter waiting time to reduce stress.

[1630] Examples:

[1631] After detecting the user's dissatisfaction, the server generates a new optimal route and sends the instruction "Turn left at the next intersection. The waiting time is approximately 5 minutes" to the user's device.

[1632] This system will not only streamline the movement of event attendees and reduce congestion, but also provide personalized guidance that takes into account the user's emotions, improving the overall user experience and enabling safe and efficient transportation.

[1633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1634] Step 1: Data collection

[1635] Input: The server retrieves past event data from the database. People flow data includes participant location information, movement routes, stay time, congestion level, etc.

[1636] Processing: The server uses Python's Pandas to read the acquired data and manage it as a DataFrame. It then deletes unnecessary data and imputes missing values.

[1637] Output: A clean, pre-processed dataset.

[1638] Specific behavior:

[1639] The server queries the database to retrieve the data.

[1640] Read the data as a DataFrame using Pandas.

[1641] Remove unnecessary columns and impute missing values ​​appropriately.

[1642] Step 2: Analyze crowding patterns

[1643] Input: The server takes as input the dataset that has been preprocessed.

[1644] Processing: Use Pandas to aggregate the number of participants for each time period, and use Scikit-learn to apply K-means clustering to cluster congested areas.

[1645] Output: Quantified congestion levels for each time period and area.

[1646] Specific behavior:

[1647] Use Pandas to count the number of participants for specific time periods and areas.

[1648] Apply Scikit-learn's K-means clustering to identify the degree of congestion for each cluster.

[1649] Visualize (graph) the results.

[1650] Step 3: Generate optimal guidance path

[1651] Input: The server inputs the results of the congestion analysis.

[1652] Processing: Genetic algorithms are used to generate optimal guidance routes, balancing waiting and travel times across participants.

[1653] Output: A set of optimized guided paths.

[1654] Specific behavior:

[1655] The server generates initial routes and evaluates the latency and travel time of each route.

[1656] A fitness function is calculated and new paths are generated through crossover and mutation operations.

[1657] This process is repeated until the optimal route is found.

[1658] Step 4: Send instructions

[1659] Input: The server takes the optimized guided route as input.

[1660] Processing: The server generates and sends a message containing the appropriate route to each user's terminal.

[1661] Output: A message about the route delivered to the user's device.

[1662] Specific behavior:

[1663] The server generates a message to be sent to each user's terminal.

[1664] Sends a message to the user's terminal.

[1665] The user's device receives the message and displays a notification on the screen.

[1666] Step 5: Real-time adjustments

[1667] Input: The server takes as input the congestion status data newly collected in real time.

[1668] Processing: The server recalculates the current congestion level based on the collected data and regenerates the guidance route if necessary.

[1669] Output: The latest re-adjusted guidance path.

[1670] Specific behavior:

[1671] The server periodically collects current congestion data.

[1672] Analyze congestion data and generate new guidance routes as needed.

[1673] The regenerated route is sent to the user and the driver.

[1674] Step 6: Emotion Recognition

[1675] Input: The server inputs the user's facial expression data and biometric data.

[1676] Processing: Analyze the user's emotional state using an emotion engine. Determine the level of stress or frustration based on facial expression data and heart rate data.

[1677] Output: Analysis results about the user's emotional state.

[1678] Specific behavior:

[1679] The server acquires facial expression data through the user's smartphone camera.

[1680] Facial expression data and heart rate data are input into an emotion engine to determine emotions.

[1681] The emotion engine returns the analysis results to the server.

[1682] Step 7: Emotion-Based Path Adjustment

[1683] Input: The server takes the output data of the emotion engine as input.

[1684] Processing: Based on the emotional state of the user, we regenerate a more effective guidance route. In particular, for dissatisfied users, we make adjustments to reduce waiting time.

[1685] Output: New adjusted guidance path.

[1686] Specific behavior:

[1687] The server receives and analyzes the output from the emotion engine.

[1688] Regenerate new routes based on the user's emotional state.

[1689] The new route information is sent to the user's terminal.

[1690] (Application example 2)

[1691] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1692] Congestion in physical stores reduces customer movement efficiency and significantly reduces customer satisfaction. Congestion, especially during peak hours, can increase waiting times and make it difficult to move around. In the worst case, it can lead to customers leaving the store, negatively impacting sales. Furthermore, uniform guidance that does not take into account the emotional state of customers makes it difficult to meet the needs of individual customers. Therefore, there is a need for a method to efficiently manage congestion in stores and encourage optimal movement based on customers' emotional state.

[1693] 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.

[1694] In this invention, the server includes means for acquiring past people flow data, means for analyzing the acquired people flow data to identify congestion patterns, means for generating an optimal guide route based on the identified congestion pattern, means for collecting facial expression data and biometric data of users and recognizing their emotional state, means for adjusting the guide route based on the recognized emotional state, means for transmitting the generated or adjusted guide route to the user's terminal, means for providing information in real time based on the transmitted guide route, means for monitoring actual congestion conditions in real time and readjusting the guide route as necessary, and means for transmitting the readjusted guide route to the terminals of guides and users. This effectively alleviates congestion in physical stores, improving customer movement efficiency and satisfaction.

[1695] "Past people flow data" refers to historical information collected at events and physical stores, such as the location information of customers, their movement routes, length of stay, and congestion levels.

[1696] "Congestion patterns" are analysis results that show the characteristics of people flow and density in specific time periods and areas.

[1697] An "invitation route" is a route designed to guide participants and visitors along a specific path to reduce congestion.

[1698] "Facial expression data" refers to information extracted from a user's facial expressions, and is data captured using a camera or image analysis technology.

[1699] "Biometric data" is data obtained by measuring a user's physical condition, such as heart rate or stress level.

[1700] "Emotional state" refers to the psychological state such as stress, dissatisfaction, or relief felt by the user.

[1701] "User terminal" refers to an information and communication device carried by an individual user, such as a smartphone or tablet.

[1702] "Real-time monitoring" means instantly observing and analyzing ongoing situations and taking immediate action if necessary.

[1703] "Readjustment" means reviewing and optimizing the initially set guidance route and layout according to the situation.

[1704] A "guide" is a person whose role is to actually guide people on-site.

[1705] This invention is a system for reducing congestion in brick-and-mortar stores and improving customer movement efficiency and satisfaction. In this system, a server collects and analyzes past people flow data to generate optimal guide routes, and an emotion engine recognizes the user's emotional state and adjusts the guide route based on that, thereby increasing user satisfaction.

[1706] System Configuration

[1707] Data collection and analysis

[1708] The server retrieves people flow data collected from past brick-and-mortar stores from the database. This people flow data includes information on customers' locations, movement routes, length of stay, and congestion levels. The server then analyzes the retrieved data using Python data analysis tools (e.g., Pandas and Scikit-learn). As a result of the analysis, congestion levels, number of people entering and leaving the store, and average travel times for each time period and area are calculated.

[1709] For example, the server analyzes data from 6:00 PM to 7:00 PM at a shopping mall on a Saturday last year and discovers that the food court is very crowded during this time.

[1710] Generating optimal guidance methods

[1711] Based on the analysis of congestion patterns, the server uses AI algorithms (e.g., genetic algorithms and machine learning models) to generate optimal routes to minimize congestion, balancing waiting time and travel time and planning multiple routes to reduce unfairness.

[1712] For example, the server may plan to prioritize a route that passes through the book section during the period when the food court is crowded between 6:00 PM and 7:00 PM.

[1713] Sending instructions to user terminal

[1714] The server sends the generated or adjusted route to the user's device (smartphone or tablet), which analyzes the received instructions and notifies the user in real time.

[1715] For example, the user may be notified with a message such as, "The food court is currently crowded. We recommend turning right and passing through the book section. Travel time: approximately 8 minutes."

[1716] Emotion recognition and re-routing

[1717] The server recognizes the user's emotional state using an emotion engine, which analyzes the user's facial expression data and biometric data (e.g., heart rate, stress level) to detect stress or frustration.

[1718] For example, the server collects facial expression data via the user's smartphone camera and analyzes it with an emotion engine to detect whether the user is feeling stressed.

[1719] The system adjusts routes and waiting times based on the user's perceived emotional state. For example, if a user feels stressed, the system will guide them to a less crowded route and shorten their waiting time.

[1720] Hardware and software used

[1721] Hardware: Server (data collection, analysis, route generation), smartphone (data collection and instruction display), smartphone camera (emotion recognition)

[1722] Software: Python (data analysis: Pandas, Scikit-learn), Scipy (optimization calculation), FER library (sentiment analysis)

[1723] Specific examples

[1724] An example of use in a brick-and-mortar shopping mall is shown below.

[1725] Prompt statement:

[1726] "Considering how crowded the shopping mall is right now at 6:00 PM, please tell me the easiest route."

[1727] (System response):

[1728] "The food court is currently crowded. We recommend turning right and taking the route via the book section. Travel time: approximately 8 minutes."

[1729] This system allows customers to move efficiently while avoiding crowds, while also improving customer satisfaction by providing the optimal route based on their emotional state.

[1730] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1731] Step 1:

[1732] The server retrieves past people flow data from the database. This data includes customer location information, movement paths, stay times, congestion levels, etc. The input is the past people flow data, and the output is the retrieved dataset. Specifically, the required information is extracted from the database using SQL queries.

[1733] Step 2:

[1734] The server analyzes the acquired people flow data using Python data analysis tools (such as Pandas). The input is the dataset acquired in step 1, and the output is the analysis results. Specifically, the data is grouped by time period and area, and the degree of congestion, number of people entering and leaving, and average travel time are calculated.

[1735] Step 3:

[1736] The server identifies congestion patterns based on the analysis results. This identification process uses a clustering algorithm (e.g., K-Means) from a machine learning model (such as Scikit-learn). The input is the analysis results, and the output is the congestion patterns for each time period and each area. Specifically, the visitor data is classified into clusters, and highly congested areas are identified.

[1737] Step 4:

[1738] The server generates the optimal guided route based on the results of analyzing congestion patterns. It uses AI algorithms (genetic algorithms and machine learning models) to create multiple routes and balance waiting time and travel time. The input is the congestion pattern, and the output is the guided route. Specifically, it runs a simulation to identify which route is optimal.

[1739] Step 5:

[1740] The server collects the user's facial expression data and biometric data. This data is acquired through the smartphone's camera and sensors. The input is the user's image data and biometric data, and the output is the processed raw data. Specifically, the image data is uploaded to the cloud, and the biometric data is collected via Bluetooth or other means.

[1741] Step 6:

[1742] The server uses an emotion engine to recognize the user's emotional state. This engine uses the FER library to analyze facial expression data and biometric data. The input is the facial expression data and biometric data collected in the previous step, and the output is the analysis result of the emotional state (e.g., stress, dissatisfaction, relief). Specifically, it performs image analysis and signal analysis to identify emotions.

[1743] Step 7:

[1744] The server adjusts the guidance route based on the recognized emotional state. Taking the emotional state into account, it recalculates the route to provide a more comfortable route. The input is the analysis result of the emotional state, and the output is the adjusted guidance route. Specifically, it responds by presenting a less crowded route to a user who is feeling stressed.

[1745] Step 8:

[1746] The server sends the generated or adjusted guided route to the user's device. The input is the adjusted guided route, and the output is a notification message to the device. Specifically, it sends instructions to the device in real time via an API.

[1747] Step 9:

[1748] The terminal provides real-time information based on the received guidance route. The input is the guidance route information from the server, and the output is a message to be displayed to the user. Specifically, the message is displayed to the user using the smartphone's notification function.

[1749] Step 10:

[1750] The server monitors the actual congestion situation in real time and readjusts the guided route as necessary. The input is real-time location information, movement speed, and emotional state data received from the device, and the output is the readjusted guided route. Specifically, it analyzes new data from the device and updates the guided route.

[1751] Step 11:

[1752] The server sends the readjusted guidance route to the guide and the user's device. The input is the readjusted guidance route, and the output is an instruction message to the guide and the device. Specifically, by distributing the recalculated route information again, optimal guidance tailored to the situation on site is realized.

[1753] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1754] 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.

[1755] 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 robot 414.

[1756] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1757] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1758] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1759] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1760] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1761] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1762] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1763] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1764] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1765] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1766] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1767] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1768] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1769] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1770] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1771] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1772] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1773] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1774] The following is further disclosed regarding the above embodiment.

[1775] (Claim 1)

[1776] A means of obtaining past people flow data;

[1777] A means for analyzing the acquired people flow data and identifying congestion patterns;

[1778] means for generating an optimal guide route based on the identified congestion pattern;

[1779] means for transmitting the generated guidance route to a user's terminal;

[1780] means for providing real-time information based on the transmitted guidance route;

[1781] A means of monitoring actual congestion in real time and readjusting the guidance route as necessary.

[1782] a means for transmitting the readjusted guidance route to the terminals of the guide and the user;

[1783] A system including:

[1784] (Claim 2)

[1785] The system includes a means for analyzing past people flow data and identifying the degree of congestion for each time period and each area, and a means for generating an optimal guide route based on the identified degree of congestion so as to evenly distribute the waiting time of all users.

[1786] 10. The system of claim 1.

[1787] (Claim 3)

[1788] and means for receiving location information and movement speed from the user's terminal in real time, analyzing newly obtained data based on the received data, and readjusting the guidance route as necessary.

[1789] 10. The system of claim 1.

[1790] "Example 1"

[1791] (Claim 1)

[1792] A means of obtaining past people flow data;

[1793] a means for identifying congestion patterns using analytical tools for analyzing the acquired people flow data;

[1794] a means for generating an optimal route using an AI algorithm based on the identified congestion patterns;

[1795] means for transmitting the generated guidance route to a user's terminal;

[1796] a means for notifying a user's terminal based on the transmitted guidance route;

[1797] A means of monitoring actual congestion conditions in real time and readjusting routes as needed based on newly collected data;

[1798] a means for transmitting the readjusted guidance route to the terminals of the guide and the user;

[1799] A system including:

[1800] (Claim 2)

[1801] The system includes a means for analyzing past people flow data and identifying the degree of congestion for each time period and each area, and a means for generating an optimal guide route based on the identified degree of congestion to balance the waiting time and travel time of all users.

[1802] 10. The system of claim 1.

[1803] (Claim 3)

[1804] and means for receiving location information and movement speed from the user's terminal in real time, analyzing new data based on the received data, and readjusting the guidance route as necessary.

[1805] 10. The system of claim 1.

[1806] "Application Example 1"

[1807] (Claim 1)

[1808] A means of obtaining past people flow data;

[1809] A means for analyzing the acquired people flow data and identifying congestion patterns;

[1810] means for generating an optimal guide route based on the identified congestion pattern;

[1811] means for transmitting the generated guidance route to a user's terminal;

[1812] means for providing real-time information based on the transmitted guidance route;

[1813] A means of monitoring actual congestion in real time and readjusting the guidance route as necessary.

[1814] a means for transmitting the readjusted guidance route to the terminals of the guide and the user;

[1815] A method to propose routes that optimize the flow of users within a commercial facility based on past data,

[1816] A system including:

[1817] (Claim 2)

[1818] The system includes a means for analyzing past people flow data and identifying the degree of congestion for each time period and each area, a means for generating an optimal guide route based on the identified degree of congestion so as to evenly distribute the waiting time of all users, and a means for proposing an optimal route based on the user's current location and destination location.

[1819] 10. The system of claim 1.

[1820] (Claim 3)

[1821] The system includes a means for receiving location information and movement speed from a user's terminal in real time, analyzing newly obtained data based on the received data, and readjusting the guided route as necessary, and a means for integrating past movement data and real-time data to identify the latest congestion patterns and regenerate the optimal route.

[1822] 10. The system of claim 1.

[1823] "Example 2: Combining Emotion Engines"

[1824] (Claim 1)

[1825] A means of obtaining past people flow data;

[1826] A means for analyzing the acquired people flow data and identifying congestion patterns;

[1827] means for generating an optimal guide route based on the identified congestion pattern;

[1828] means for transmitting the generated guidance route to a user's terminal;

[1829] means for providing real-time information based on the transmitted guidance route;

[1830] A means of monitoring actual congestion in real time and readjusting the guidance route as necessary.

[1831] a means for transmitting the readjusted guidance route to the terminals of the guide and the user;

[1832] means for recognizing the emotional state of a user;

[1833] means for adjusting a guidance path based on the perceived emotional state;

[1834] A system including:

[1835] (Claim 2)

[1836] The system includes a means for analyzing past people flow data and specifying the degree of congestion for each time period and each area, a means for generating an optimal guide route based on the specified degree of congestion so as to evenly distribute the waiting time of all users, a means for analyzing user emotion data and specifying an emotional state, and a means for optimizing the waiting time based on the emotional state.

[1837] 10. The system of claim 1.

[1838] (Claim 3)

[1839] The system includes a means for receiving location information and movement speed from a user's terminal in real time, analyzing newly obtained data based on the received data, and readjusting the guide route as necessary, and a means for receiving user's emotional data, analyzing the user's emotional state in real time, and readjusting the guide route according to the results of the analysis.

[1840] 10. The system of claim 1.

[1841] "Application example 2 when combining emotion engines"

[1842] (Claim 1)

[1843] A means of obtaining past people flow data;

[1844] A means for analyzing the acquired people flow data and identifying congestion patterns;

[1845] means for generating an optimal guide route based on the identified congestion pattern;

[1846] A means for collecting facial expression data and biometric data of a user and recognizing the user's emotional state;

[1847] means for adjusting a guidance path based on the perceived emotional state;

[1848] means for transmitting the generated or adjusted guidance route to a user's terminal;

[1849] means for providing real-time information based on the transmitted guidance route;

[1850] A means of monitoring actual congestion in real time and readjusting the guidance route as necessary.

[1851] a means for transmitting the readjusted guidance route to the terminals of the guide and the user;

[1852] A system including:

[1853] (Claim 2)

[1854] The system includes a means for analyzing past people flow data and identifying the degree of congestion for each time period and each area, a means for generating an optimal guide route based on the identified degree of congestion so as to evenly distribute the waiting time of all users, and a means for recognizing an emotional state and adjusting the route.

[1855] 10. The system of claim 1.

[1856] (Claim 3)

[1857] and means for receiving location information, movement speed, and emotional state data from the user's terminal in real time, analyzing newly obtained data based on the received data, and readjusting the guidance route as necessary.

[1858] 10. The system of claim 1. [Explanation of symbols]

[1859] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining past people flow data; A means for analyzing the acquired people flow data and identifying congestion patterns; means for generating an optimal guide route based on the identified congestion pattern; means for transmitting the generated guidance route to a user's terminal; means for providing real-time information based on the transmitted guidance route; A means of monitoring actual congestion in real time and readjusting the guidance route as necessary. a means for transmitting the readjusted guidance route to the terminals of the guide and the user; A system including:

2. The system includes a means for analyzing past people flow data and identifying the degree of congestion for each time period and each area, and a means for generating an optimal guide route based on the identified degree of congestion so as to evenly distribute the waiting time of all users. The system of claim 1 .

3. and means for receiving location information and movement speed from the user's terminal in real time, analyzing newly obtained data based on the received data, and readjusting the guidance route as necessary. The system of claim 1 .

Images