system

Abstract

We provide the system. [Solution] A system including a server device connected to a data acquisition device, A means of collecting pedestrian flow data from multiple data sources and storing it in a database, A data preprocessing means for normalizing collected data and removing noise, A data analysis method that uses machine learning models to analyze data and generate pedestrian flow predictions, A means for generating a list of candidate locations based on event conditions entered by the user, A method for evaluating candidate sites using analysis results and selecting the optimal event location, A system that includes means for simulating staff deployment based on selected locations and generating proposals.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional event hosting, appropriate venue selection and personnel arrangement are important to achieve effective customer attraction. However, this largely relies on experience and intuition, and there is a problem that optimization takes a lot of time and effort. In addition, it has been difficult to utilize rapidly changing pedestrian flow data in real time and make accurate judgments. Therefore, there is a need for means to more efficiently and quickly select an optimal event venue and arrange personnel to maximize the effect of the event.

Means for Solving the Problems

[0005] This invention collects pedestrian flow data from multiple data sources using a server device and normalizes it through data preprocessing. Then, using a machine learning model, it performs predictive analysis of pedestrian flow and generates a list of candidate locations based on the event conditions entered by the user. Based on the analysis results and user conditions, the candidate locations are evaluated and the optimal event location is selected. Based on this selection, the optimal staffing is simulated and a proposal is generated, thereby providing a means to realize rapid and efficient event planning.

[0006] A "data acquisition device" is a device that has the function of acquiring necessary data from multiple data sources and transferring it to a server device.

[0007] A "server device" is a central device that collects, processes, and analyzes data, and based on that data, proposes the optimal venue and staffing arrangements for holding an event.

[0008] "People flow data" refers to information that shows how people move around in a specific area, how long they stay there, and how crowded it is.

[0009] "Data preprocessing" is the process of removing noise from collected raw data and shaping it into a format suitable for analysis.

[0010] A "machine learning model" is an algorithm used for data analysis, designed to predict future pedestrian traffic based on past data.

[0011] The "candidate location list" is a list of multiple event venues that match the conditions specified by the user, and is generated by the server device.

[0012] An "evaluation score" is a score calculated to evaluate a candidate site based on various factors, and is used to select the optimal site.

[0013] "Staffing simulation" is a process that calculates the appropriate number and location of staff based on the expected flow of people at the selected event location.

[0014] A "terminal" is a device used to visually present suggestions from a server device to the user. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory where information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that optimizes the selection of venues and staff allocation necessary for efficiently holding events. The core of the system is data collection, analysis, and optimization processing performed by a server device. The server first utilizes multiple data sources to collect pedestrian flow data in real time. This includes information on boarding and alighting from public transportation and location information from mobile devices.

[0037] The server preprocesses the collected data, removing noise and formatting it into a unified format. Next, a pre-trained machine learning model is used to analyze the pedestrian flow data and predict future patterns. This predicted data forms the basis for selecting the optimal event venue.

[0038] Users input event information into the system via a terminal. This information includes the attributes of the target audience, desired date and time, duration, budget, and required equipment. The server uses the conditions entered by the user and crowd flow prediction data to create a list of multiple potential event venues.

[0039] In the optimization process, the server evaluates each venue on the candidate site list, calculates an evaluation score, and selects the optimal venue. This evaluation score takes into account cost, accessibility, and the expected number of participants. Furthermore, it simulates the optimal staffing arrangement at the selected location and proposes solutions to ensure efficient event management.

[0040] As a result, the terminal visually presents the user with the optimal venue and staffing plan. For example, for a concert event held in an urban area on a specific date and time, the server analyzes pedestrian flow data to identify the areas where the most people gather during that time, and then constructs the overall plan necessary for the event's success.

[0041] This series of processes enables users to conduct events efficiently and effectively.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects pedestrian flow data in real time from multiple data sources. This includes information on boarding and alighting from public transportation, location data from smartphones, and public posts from social media. The server stores this data in a database.

[0045] Step 2:

[0046] The server performs data preprocessing on the collected data. Specifically, it removes noise, checks for outliers, and standardizes data formats to prepare the data for analysis. During this process, the server filters out inaccurate data.

[0047] Step 3:

[0048] The server applies a pre-trained machine learning model to analyze pre-processed data. This analysis generates historical pedestrian flow patterns and future predictions for specific areas. This makes it possible to identify peak times and popular areas.

[0049] Step 4:

[0050] The user enters details about the event they are hosting (target audience attributes, date and time, budget, etc.) through their device. The device then sends these details to the server.

[0051] Step 5:

[0052] The server generates a list of potential event venues by combining historical data and analysis results based on the event conditions provided by the user. The venues are selected considering their availability and usage conditions.

[0053] Step 6:

[0054] The server calculates an evaluation score for each venue on the candidate site list. This score is calculated considering factors such as accessibility, cost efficiency, and expected attendance. The venue with the highest score is selected as the optimal choice.

[0055] Step 7:

[0056] The server simulates the optimization of staff allocation based on congestion predictions at the selected event venue. It proposes the necessary number of staff and their allocation for efficient operation.

[0057] Step 8:

[0058] The terminal visualizes the optimization results from the server and presents them to the user. The user receives suggestions for the optimal event location and staffing, and can proceed with event preparations based on these suggestions.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] In traditional event planning, optimizing venue selection and staffing required significant time and effort, often resulting in inefficient operations. Furthermore, accurately predicting participant numbers and demographics was difficult due to the challenge of reflecting demographic changes in real time. This could lead to decreased participant satisfaction and cost overruns, especially in large-scale events.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for collecting demographic data from multiple information sources and storing it on a recording medium, means for preprocessing the collected data to organize it and remove errors, and means for analyzing the information using a learning algorithm to generate demographic forecasts. This enables efficient and effective optimization of event location selection and personnel allocation, and allows for real-time response.

[0064] A "data supply device" is a device that functions as an external source of information for providing demographic data.

[0065] An "information processing device" is a device that manages the entire system for performing analysis and evaluation based on collected data.

[0066] "Population dynamics data" refers to information about the movement and distribution of people in a specific region or time period.

[0067] A "recording medium" is a physical or virtual medium used to store data and make it accessible later.

[0068] "Information preprocessing means" refers to methods for removing errors and misinformation from collected data and converting it into an appropriate format that can be analyzed.

[0069] A "learning algorithm" is a computational procedure that analyzes patterns and trends based on input data to predict or classify new information.

[0070] "Information analysis methods" refer to methods and techniques for analyzing organized data in detail and deriving useful insights based on the results.

[0071] A "user" is an individual or group that operates the system and plans and manages events.

[0072] The "Candidate Region List" is a list of geographical locations suitable for holding events, selected based on the analysis results.

[0073] "Staffing" refers to assigning the appropriate number and skills of staff to specific locations and roles.

[0074] A "display device" is a device used to visually display the results transmitted from an information processing device.

[0075] This system optimizes venue selection and personnel allocation for event hosting, primarily through data supply and information processing devices. Specifically, the server collects demographic data in real time from various sources, including public transport operation data and location information from mobile devices. The data is stored on a recording medium and used for subsequent processing. The server organizes the collected data and performs preprocessing to remove errors and standardize the format. This preprocessing utilizes data cleaning and filtering algorithms.

[0076] Next, the server analyzes the preprocessed data using a pre-trained learning algorithm. This analysis predicts future demographic fluctuation patterns and generates a list of candidate regions based on these predictions. The server evaluates this list of candidate regions and uses it as a criterion for selecting the optimal activity location. For the selected locations, the server simulates staffing and proposes an efficient staffing plan.

[0077] Users access the system using a terminal and enter information about the event, including the target audience, preferred date and time, and budget. The server compares these conditions with forecast data to generate a list of optimal locations and placements.

[0078] Ultimately, the terminal visually displays information obtained from the server and provides the user with suggestions for the optimal venue and staffing arrangements. For example, in the case of a concert held in the city center on a specific date and time, the server indicates the predicted areas where people are likely to gather and programs directions accordingly.

[0079] An example of a prompt message would be: "Generate an optimal venue and staffing plan for an urban concert event based on the following parameters: target audience, soundproofing, accessibility, budget limit, and desired date."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects demographic data from multiple sources. This collection utilizes public transport APIs and mobile device location services. It receives traffic boarding / alighting data and location data as input, and saves this data to a recording medium in real time, preparing the foundational data for selecting potential event locations.

[0083] Step 2:

[0084] The server preprocesses the collected demographic data. Specifically, it imputes missing data, removes outliers, and normalizes the data into a unified format. This process processes the raw data provided as input and generates a clean dataset suitable for analysis as output.

[0085] Step 3:

[0086] The server uses pre-processed data to predict demographic patterns using a pre-trained generative AI model. It accepts normalized demographic data as input and generates predictions of pedestrian flow for specific time periods and regions as output. This facilitates the selection of potential future event locations.

[0087] Step 4:

[0088] Users input event-related conditions into the system via their terminal. For example, they enter target audience attributes, date and time, budget, and required equipment specifications. The entered conditions are sent to a server, where they are used as evaluation criteria for selecting potential venues.

[0089] Step 5:

[0090] The server generates a list of candidate locations by comparing user-provided conditions with predicted demographic data. Specifically, it evaluates the conditions provided as input, selects suitable geographical areas from the database, and creates a list of suitable candidate locations as output.

[0091] Step 6:

[0092] The server performs optimization processing based on the generated list of candidate locations. For each candidate location, it calculates evaluation scores such as cost, accessibility, and predicted number of participants. It receives the list of candidate locations as input, selects the most suitable event venue as output, and then creates an efficient staffing plan for the selected location.

[0093] Step 7:

[0094] The terminal visualizes and presents to the user the optimal venue and staffing plan sent from the server. For example, it displays the visually optimized results on the screen along with map information, providing the user with a concrete event plan. This output allows the user to make a final decision quickly.

[0095] (Application Example 1)

[0096] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0097] Traditional event planning has faced challenges such as the difficulty of selecting the optimal venue and efficiently allocating staff, making it challenging to attract a large audience. Predicting the appropriate date and time for an event was also difficult. This made it difficult to develop strategies necessary for event success, resulting in financial losses and missed opportunities.

[0098] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0099] In this invention, the server includes a function to collect movement data from multiple information sources and store it in a recording device, an information processing function to unify the collected information and remove unnecessary data, and an information analysis function to analyze the information using a learning model and generate movement predictions. This makes it possible to efficiently determine the optimal event location, time, and personnel allocation, and to support operations that increase the success rate.

[0100] An "information gathering device" is a device used to acquire data from multiple information sources.

[0101] An "information processing system" is a system for unifying, analyzing, and optimizing collected information.

[0102] A "recording device" is a device that has a storage function for saving collected data.

[0103] "Information sources" refer to the various media and platforms from which data is collected.

[0104] "Mobility data" refers to information about people's movements and flows, and is a collection of data that is gathered in real time.

[0105] "Standardization" is the process of aligning data from different formats to a certain standard, making it easier to analyze.

[0106] "Unnecessary data" refers to information that has little value in the analysis or decision-making process, or that is considered noise.

[0107] A "learning model" is an algorithm or mathematical model used for data analysis and prediction.

[0108] "Information analysis function" refers to the process of using collected data to obtain predictions and insights for various purposes.

[0109] The "List of Selected Locations" is a collection of information listing potential locations suitable for holding an event.

[0110] "Personnel allocation" refers to the assignment of staff necessary to efficiently carry out an event or task.

[0111] A "smartphone" is a portable communication device with multiple functions, such as displaying and operating information.

[0112] The system for realizing this application consists of an information gathering device, an information processing system, and a recording device. The server collects movement data from multiple information sources and stores it in the recording device. This enables real-time capture of human flow data. The collected data is processed through information processing functions that unify it and remove unnecessary data, making it suitable for analysis.

[0113] Next, the server uses a learning model to analyze the accumulated data. This analysis process generates future movement predictions based on past and present movement data. Users can then use the generated movement predictions to perform simulations for selecting event venues and staffing.

[0114] The optimal suggestions are presented to the user via the terminal. In this process, the server visualizes the selected information and provides it on a display device such as a smartphone. Based on this information, the user can formulate an effective event management plan.

[0115] A concrete example is a retailer planning a special weekend promotional event, who could use this system to determine the optimal store location and time slot. Such prediction-based decisions enable efficient customer attraction.

[0116] An example of a prompt might be: "Based on average foot traffic data from last year's weekend afternoons at 3 PM, predict the times when the most people will gather. Based on that prediction, propose appropriate staffing arrangements to ensure the event's success." This prompt utilizes advanced analysis powered by generative AI models to support event success.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects movement data from multiple sources. Inputs include boarding and alighting information from public transport and location information from mobile devices, and output is stored in a recording device in raw data format. In this step, data is acquired in real time and stored in a format suitable for subsequent processing.

[0120] Step 2:

[0121] The server unifies the collected movement data and removes unnecessary data. The input is the raw data stored in step 1, and the output is data that has been noise-free and formatted into a unified format. Specifically, it filters out redundant data and leaves only the necessary items.

[0122] Step 3:

[0123] The server uses a learning model to analyze unified movement data and generate movement predictions. The input is the data generated in step 2, and the output is the predicted pedestrian flow pattern. Machine learning algorithms are applied as data processing to extract future movement patterns.

[0124] Step 4:

[0125] The server generates a list of potential venues based on the event conditions entered by the user. The input is the event details provided by the user (date, time, target, etc.), and the output is a list of potential venues. Specifically, the process includes identifying and listing geographical locations that meet the conditions.

[0126] Step 5:

[0127] The server evaluates candidate locations and selects the optimal event venue. The inputs are the list of candidate locations generated in step 4 and the pedestrian flow patterns from step 3, and the output is the selection result for the optimal location. As a data calculation, an evaluation score is calculated for each candidate location, and the location with the highest score is selected.

[0128] Step 6:

[0129] The server simulates staffing based on the selected locations and generates proposals. The input is the selection result from step 5, and the output is a proposed staffing plan. Specifically, it determines the number of staff according to the scale of the event and simulates the optimal placement pattern.

[0130] Step 7:

[0131] The terminal visualizes the suggestions obtained from the server and presents them to the user. The input is the suggestions from step 6, and the output is visual data displayed in a format that the user can review. In operation, event information and suggestions are displayed on the smartphone application screen, making them easily accessible to the user.

[0132] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0133] This invention combines a system that proposes optimal locations and staffing based on pedestrian flow data to maximize the effectiveness of event hosting with an emotion engine that recognizes user emotions and further enhances the event experience.

[0134] In the system's implementation, the server device first collects pedestrian flow data in real time from multiple data sources and stores it in a database. The collected data is preprocessed to remove noise and create a unified format. Then, a machine learning model is used to analyze the normalized data and generate pedestrian flow predictions for each region. This makes it possible to identify peak times and popular locations in specific areas.

[0135] The user inputs event conditions using a terminal. During this process, the emotion engine analyzes the user's voice and facial expressions to recognize their emotional state at the time of input. For example, if the user expresses joy, this information is incorporated into the system, allowing it to create a list of potential locations that align with the user's expectations. This enables the system to incorporate the user's emotional information into the list of potential locations.

[0136] Furthermore, the server evaluates candidate locations based on the analysis results and user sentiment information, and selects the optimal event location. In this process, sentiment information is reflected in the evaluation score, prioritizing the location that best suits the user's desired experience.

[0137] At the selected event location, the server simulates and generates suggestions for optimal staffing based on crowd flow predictions. The optimized results are presented to the user in a visualized form via a terminal. For example, if the emotion engine detects user anxiety, the system provides a more comfortable experience by suggesting options that avoid congestion.

[0138] This system allows users to receive suggestions based on event conditions while also taking emotions into consideration when preparing for the event.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects pedestrian flow data from multiple data sources. Specifically, it utilizes information on public transport usage, location data from smart devices, and social media traffic. This data is ingested into the database in real time.

[0142] Step 2:

[0143] The server preprocesses the collected pedestrian flow data. This includes standardizing the data format and removing outliers. After removing noise, the data is prepared in a format that allows for analysis by machine learning models.

[0144] Step 3:

[0145] The server uses machine learning models to perform analysis and generate predictions of pedestrian flow. These predictions include analysis results such as the number of people staying in a specific area and peak times, allowing for consideration of future pedestrian flow patterns.

[0146] Step 4:

[0147] When a user inputs event conditions via their device, their emotional state is recognized by the emotion engine. The system analyzes the user's facial expressions and voice to obtain emotional data such as joy and anxiety.

[0148] Step 5:

[0149] The server receives event conditions and sentiment data entered by the user and creates a list of optimal event venue candidates. The candidate selection process also incorporates customization based on the user's expectations and emotions.

[0150] Step 6:

[0151] The server calculates an evaluation score based on the list of candidate locations. This evaluation is based on accessibility, cost, and the appropriateness of the location selection according to user sentiment information.

[0152] Step 7:

[0153] The server selects the optimal event location and simulates the optimal staff deployment at that location. Based on the predicted crowd flow, it generates suggestions for the number and placement of staff.

[0154] Step 8:

[0155] The terminal visually presents the user with the optimized event location and staffing arrangements generated by the server. This allows the user to begin concrete event preparations based on the suggestions.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0158] When organizing an event, selecting the optimal location and appropriately allocating staff are crucial to maximizing participant satisfaction. However, traditional methods often involve manual analysis of travel data and venue selection, which is time-consuming and labor-intensive. Furthermore, selecting the optimal venue while considering participants' emotions presents a challenge.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for acquiring movement information from multiple information sources and storing it in a storage device, means for integrating the acquired movement information and removing unnecessary elements, and means for analyzing the information using a learning algorithm and generating movement predictions for each region. This enables efficient venue selection and staff allocation based on movement information, thereby increasing participant satisfaction. Furthermore, by including emotion analysis means that recognize the user's emotional state by analyzing voice and facial expressions and adjust venue candidates based on this information, it becomes possible to select the optimal venue that takes the user's emotions into consideration.

[0161] A "server" is a computing device that processes data obtained from multiple sources and provides analysis results.

[0162] "Mobility information" refers to data that shows the movement patterns of people and goods in a specific area.

[0163] A "storage device" is a device that has the function of storing data and retrieving and processing that data as needed.

[0164] A "data preparation method" is a system that integrates collected data into a consistent format and processes it to remove unnecessary information.

[0165] A "learning algorithm" is a computational method used to find rules and patterns in large amounts of data and to perform predictions and classifications.

[0166] An "information analysis tool" is a system that performs analysis based on obtained data to generate predictions and insights.

[0167] A "potential venue" is a list of several possible locations that are being considered for holding the event.

[0168] An "emotion analysis system" is a system that analyzes the user's voice and facial expressions to recognize their emotional state.

[0169] An "input / output device" is a device that allows a user to input information and to visually receive information from a computing device.

[0170] This invention is a system that automatically suggests the optimal location and staffing arrangement for an event. The system is configured and used as follows:

[0171] The server first collects movement information in real time from multiple sources. The collected data is stored in the server's storage device. Specifically, it utilizes information from APIs and sensors to collect data such as traffic volume and the usage status of public facilities. Next, the server processes this data using data preparation tools to remove noise and standardize the format. Standard data cleaning techniques are applied at this stage.

[0172] The server uses libraries such as TENSORFLOW® and PyTorch to execute learning algorithms. This allows it to analyze movement information and generate movement predictions for a specific region. Based on the obtained prediction data, it lists potential event locations according to the event conditions set by the user.

[0173] The user inputs event conditions into the system via a terminal. At this time, the terminal analyzes the user's voice and facial expressions using emotion analysis tools to recognize their emotional state. In this step, an emotion engine is used, employing standard voice analysis and facial recognition technologies for emotion recognition.

[0174] Based on user input data and sentiment information, the server evaluates potential event locations and selects the optimal venue. Sentiment information is a crucial element in this selection process. Furthermore, the server simulates the optimal staffing arrangement and generates this as a proposal.

[0175] The terminal visualizes and presents optimized suggestions sent from the server to the user. This includes displaying potential venues on a map and generating heatmaps that predict congestion.

[0176] As a concrete example, consider a scenario where a user wants to find the best location for an art festival scheduled for the following weekend. Taking into account the user's relaxed mood, we can list the best locations that avoid crowds.

[0177] An example of a prompt message might be: "Please suggest the best venues for the art festival scheduled for next weekend. Please list the most suitable locations, taking into account the expected crowd levels and the user's relaxed mood."

[0178] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0179] Step 1:

[0180] The server collects mobility information from multiple sources. Input data includes real-time traffic information from transportation APIs and data on the usage of public facilities. The server retrieves this data via API requests and stores it in storage. The output is a set of accumulated raw data.

[0181] Step 2:

[0182] The server processes the collected movement information. The input is the raw data obtained in step 1. Specifically, it performs tasks such as imputing missing data, removing outliers, and standardizing data formats. Data reliability is improved by using a denoising algorithm. The output is a normalized, high-quality dataset.

[0183] Step 3:

[0184] The server uses a learning algorithm to generate movement predictions from a normalized dataset. The input is the data prepared in step 2. Using machine learning libraries, it models movement patterns for each region by performing time series analysis and clustering. The output is analytical data predicting future human movement.

[0185] Step 4:

[0186] The user inputs event conditions using a terminal. The input data consists of detailed conditions and settings for the event desired by the user. The terminal sends this information to the server, which is then used to evaluate candidate locations. The output is a request from the user interface to the server.

[0187] Step 5:

[0188] The device acquires the user's voice and facial expressions and recognizes their emotional state using emotion analysis. Input consists of real-time acquired voice data and facial imagery. The emotion analysis engine analyzes the tone of the voice and facial features to determine the user's emotions. Output is the recognized emotion information.

[0189] Step 6:

[0190] The server evaluates potential event locations based on event conditions and sentiment information, and selects the optimal event location. The inputs are the pedestrian flow prediction data generated in step 3 and the information obtained in steps 4 and 5. The evaluation model is used to calculate a score for each candidate location, and the most suitable one is selected. The output is the selected optimal event location.

[0191] Step 7:

[0192] The server simulates staff deployment based on the selected venue information. The input is the venue information selected in step 6. The simulation designs the optimal staff deployment plan according to the predicted congestion. The output is the optimized staff deployment plan.

[0193] Step 8:

[0194] The terminal visualizes and presents optimal venue and staffing plans to the user. The input is the suggested content received from the server. The terminal visually displays the data using maps and graphs to make it easy for the user to understand. The output is the visualized information presented to the user.

[0195] (Application Example 2)

[0196] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0197] In recent years, optimal location selection and staffing at events and commercial facilities have become crucial for event success. However, many systems rely solely on predictions based on pedestrian flow data and fail to consider visitor sentiment, making it difficult to optimize the individual user experience. Furthermore, a lack of concrete suggestions for avoiding congestion also hinders a comfortable user experience.

[0198] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0199] In this invention, the server includes means for collecting pedestrian flow information from multiple information sources and storing it in an information aggregate, means for preprocessing the collected information to normalize it and remove unnecessary information, and means for analyzing the information using a machine learning model and generating pedestrian flow predictions. This makes it possible to propose the optimal event location and worker placement while taking into account the user's emotional information, and to provide a comfortable event experience that avoids congestion.

[0200] An "information processing device" is a computer system that collects data from multiple sources, analyzes it, and processes it.

[0201] An "information collection" is a database that stores collected data and manages it so that it can be used as needed.

[0202] "Information preprocessing means" refers to methods for processing collected data to convert it into a format that is easy to analyze, such as removing unnecessary information or standardizing the data format.

[0203] A "machine learning model" is an algorithm or method used to analyze data, find patterns, and make predictions.

[0204] An "information analysis tool" is a mechanism for performing analysis based on collected and pre-processed data, according to a specific purpose.

[0205] "Event conditions" refer to information that specifically defines the characteristics and requirements of an event that a user is planning to hold.

[0206] "Emotion recognition means" refers to technologies and methods for recognizing a user's emotional state at a given time by analyzing their facial expressions and voice.

[0207] An "evaluation score" is a numerical indicator that quantifies the extent to which specific conditions are met, generated based on analysis results and user sentiment information.

[0208] The server, acting as an information processing device, collects pedestrian flow information from multiple sources. This includes real-time data from sensors, cameras, and other sources. The collected data is quickly and efficiently de-noised and converted into a unified format using pre-processing tools. At this stage, cloud infrastructure such as Microsoft Azure and Google Cloud can be used.

[0209] After the data is normalized, the server uses a machine learning model to analyze the information and generate pedestrian flow predictions. Here, TensorFlow is used to predict peak times and congestion in specific areas. The analyzed data is stored in an information repository.

[0210] When a user sends event conditions to a server using their device, an emotion recognition mechanism is activated. The device can be, for example, a smartphone or tablet, and its camera and microphone collect the user's facial expressions and voice. This allows Microsoft Azure's emotion analysis service to identify the user's emotional state.

[0211] The server incorporates the analyzed sentiment information into an evaluation score and lists the most suitable candidate locations based on the user's request. Furthermore, if a suggested location is likely to be crowded, it presents alternative options to avoid the crowds based on the sentiment information.

[0212] Finally, the proposed content is visualized on the device and provided to the user. Based on this, the user can determine the optimal event plan and communicate that information to the staff via wireless communication.

[0213] As a concrete example, when an event is scheduled, the system predicts when attendees will be most concentrated and suggests alternative options to alleviate congestion. This results in a more comfortable experience for customers.

[0214] An example of a prompt using a generative AI model is: "Based on the latest customer sentiment data, please come up with suggestions to provide a better experience for customers so they can shop comfortably in the store."

[0215] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0216] Step 1:

[0217] The server collects pedestrian flow information in real time from multiple sources. It receives data from each sensor and camera via an interface and temporarily stores it in an information aggregate. At this stage, the raw data is enormous and may include incomplete information.

[0218] Step 2:

[0219] The server performs information preprocessing on the collected raw data. This process removes noise and formats the data into a consistent format. Data processing is achieved by filtering outliers, imputing missing values, and standardizing the data. The output is a clean dataset in a format suitable for analysis.

[0220] Step 3:

[0221] The server uses normalized data to perform analysis with machine learning models. Leveraging TensorFlow, it applies pedestrian flow pattern recognition and prediction models to the analysis. It predicts peak times from the input data and identifies when and where congestion occurs. The output is generated as a pedestrian flow prediction report in text and graph formats.

[0222] Step 4:

[0223] The user inputs event conditions from their device. This information is sent to the server and includes the starting point and scheduled date and time. The user's facial expressions and voice are recorded using the device's microphone and camera. Audio and image data that provide hints about emotions are acquired as input.

[0224] Step 5:

[0225] The server uses emotion recognition tools to analyze the user's emotional state from their facial expressions and voice. It generates an emotion score using the Microsoft Azure Emotion Analysis Service. This involves analyzing facial expression features and voice tone to identify emotions. The output is an evaluation score, quantified as emotion information.

[0226] Step 6:

[0227] The server incorporates sentiment scores into its evaluation and generates a list of candidate locations combined with crowd flow predictions. Based on this combination, it selects the optimal event location. Specifically, if a user's sentiment of happiness is high, options that meet that request are prioritized. The output is a ranked list of recommended event locations.

[0228] Step 7:

[0229] The server provides options to avoid congestion. Based on sentiment information and crowd flow predictions, it proposes a plan to avoid congestion. In this process, it generates recommendations for alternative routes and different time slots. The output is congestion avoidance suggestions.

[0230] Step 8:

[0231] The user visually reviews the suggestions generated by the server via their terminal. Visualized data of optimal locations and staff deployments are displayed on the terminal's screen. Based on this, the user makes a final decision. As output, confirmation information regarding the optimal location selected by the user is obtained.

[0232] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0233] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0234] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0238] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0239] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0240] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0241] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0242] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0243] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0244] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0245] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0246] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0247] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0248] This invention is a system that optimizes the selection of venues and staff allocation necessary for efficiently holding events. The core of the system is data collection, analysis, and optimization processing performed by a server device. The server first utilizes multiple data sources to collect pedestrian flow data in real time. This includes information on boarding and alighting from public transportation and location information from mobile devices.

[0249] The server preprocesses the collected data, removing noise and formatting it into a unified format. Next, a pre-trained machine learning model is used to analyze the pedestrian flow data and predict future patterns. This predicted data forms the basis for selecting the optimal event venue.

[0250] Users input event information into the system via a terminal. This information includes the attributes of the target audience, desired date and time, duration, budget, and required equipment. The server uses the conditions entered by the user and crowd flow prediction data to create a list of multiple potential event venues.

[0251] In the optimization process, the server evaluates each venue on the candidate site list, calculates an evaluation score, and selects the optimal venue. This evaluation score takes into account cost, accessibility, and the expected number of participants. Furthermore, it simulates the optimal staffing arrangement at the selected location and proposes solutions to ensure efficient event management.

[0252] As a result, the terminal visually presents the user with the optimal venue and staffing plan. For example, for a concert event held in an urban area on a specific date and time, the server analyzes pedestrian flow data to identify the areas where the most people gather during that time, and then constructs the overall plan necessary for the event's success.

[0253] This series of processes enables users to conduct events efficiently and effectively.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The server collects pedestrian flow data in real time from multiple data sources. This includes information on boarding and alighting from public transportation, location data from smartphones, and public posts from social media. The server stores this data in a database.

[0257] Step 2:

[0258] The server performs data preprocessing on the collected data. Specifically, it removes noise, checks for outliers, and standardizes data formats to prepare the data for analysis. During this process, the server filters out inaccurate data.

[0259] Step 3:

[0260] The server applies a pre-trained machine learning model to analyze pre-processed data. This analysis generates historical pedestrian flow patterns and future predictions for specific areas. This makes it possible to identify peak times and popular areas.

[0261] Step 4:

[0262] The user enters details about the event they are hosting (target audience attributes, date and time, budget, etc.) through their device. The device then sends these details to the server.

[0263] Step 5:

[0264] The server generates a list of potential event venues by combining historical data and analysis results based on the event conditions provided by the user. The venues are selected considering their availability and usage conditions.

[0265] Step 6:

[0266] The server calculates an evaluation score for each venue on the candidate site list. This score is calculated considering factors such as accessibility, cost efficiency, and expected attendance. The venue with the highest score is selected as the optimal choice.

[0267] Step 7:

[0268] The server simulates the optimization of staff allocation based on congestion predictions at the selected event venue. It proposes the necessary number of staff and their allocation for efficient operation.

[0269] Step 8:

[0270] The terminal visualizes the optimization results from the server and presents them to the user. The user receives suggestions for the optimal event location and staffing, and can proceed with event preparations based on these suggestions.

[0271] (Example 1)

[0272] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0273] In traditional event planning, optimizing venue selection and staffing required significant time and effort, often resulting in inefficient operations. Furthermore, accurately predicting participant numbers and demographics was difficult due to the challenge of reflecting demographic changes in real time. This could lead to decreased participant satisfaction and cost overruns, especially in large-scale events.

[0274] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0275] In this invention, the server includes means for collecting demographic data from multiple information sources and storing it on a recording medium, means for preprocessing the collected data to organize it and remove errors, and means for analyzing the information using a learning algorithm to generate demographic forecasts. This enables efficient and effective optimization of event location selection and personnel allocation, and allows for real-time response.

[0276] A "data supply device" is a device that functions as an external source of information for providing demographic data.

[0277] The "information processing device" is a device that manages the entire system for performing analysis and evaluation based on the collected data.

[0278] The "demographic data" is information regarding the movement and distribution of people in a specific region or time.

[0279] The "recording medium" is a physical or virtual medium for storing data and making it accessible later.

[0280] The "information preprocessing means" is a method for removing errors and incorrect information from the collected data and converting it into an appropriate format for analysis.

[0281] The "learning algorithm" is a computational procedure for analyzing patterns and trends based on input data and predicting or classifying new information.

[0282] The "information analysis means" is a method or technique for analyzing the organized data in detail and drawing useful insights based on the results.

[0283] The "user" is an individual or group that operates the system and plans and manages events.

[0284] The "list of candidate regions" is a list of a series of geographical locations selected based on the analysis results and suitable for holding events.

[0285] "Staff allocation" means assigning appropriate numbers and skilled staff to specific locations and roles.

[0286] The "display device" is a device for visually displaying the results transmitted from the information processing device.

[0287] This system optimizes venue selection and personnel allocation for event hosting, primarily through data supply and information processing devices. Specifically, the server collects demographic data in real time from various sources, including public transport operation data and location information from mobile devices. The data is stored on a recording medium and used for subsequent processing. The server organizes the collected data and performs preprocessing to remove errors and standardize the format. This preprocessing utilizes data cleaning and filtering algorithms.

[0288] Next, the server analyzes the preprocessed data using a pre-trained learning algorithm. This analysis predicts future demographic fluctuation patterns and generates a list of candidate regions based on these predictions. The server evaluates this list of candidate regions and uses it as a criterion for selecting the optimal activity location. For the selected locations, the server simulates staffing and proposes an efficient staffing plan.

[0289] Users access the system using a terminal and enter information about the event, including the target audience, preferred date and time, and budget. The server compares these conditions with forecast data to generate a list of optimal locations and placements.

[0290] Ultimately, the terminal visually displays information obtained from the server and provides the user with suggestions for the optimal venue and staffing arrangements. For example, in the case of a concert held in the city center on a specific date and time, the server indicates the predicted areas where people are likely to gather and programs directions accordingly.

[0291] An example of a prompt message would be: "Generate an optimal venue and staffing plan for an urban concert event based on the following parameters: target audience, soundproofing, accessibility, budget limit, and desired date."

[0292] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0293] Step 1:

[0294] The server collects demographic data from multiple sources. This collection utilizes public transport APIs and mobile device location services. It receives traffic boarding / alighting data and location data as input, and saves this data to a recording medium in real time, preparing the foundational data for selecting potential event locations.

[0295] Step 2:

[0296] The server preprocesses the collected demographic data. Specifically, it imputes missing data, removes outliers, and normalizes the data into a unified format. This process processes the raw data provided as input and generates a clean dataset suitable for analysis as output.

[0297] Step 3:

[0298] The server uses pre-processed data to predict demographic patterns using a pre-trained generative AI model. It accepts normalized demographic data as input and generates predictions of pedestrian flow for specific time periods and regions as output. This facilitates the selection of potential future event locations.

[0299] Step 4:

[0300] Users input event-related conditions into the system via their terminal. For example, they enter target audience attributes, date and time, budget, and required equipment specifications. The entered conditions are sent to a server, where they are used as evaluation criteria for selecting potential venues.

[0301] Step 5:

[0302] The server generates a list of candidate locations by comparing the conditions from the user with the predicted population dynamics data. As a specific operation, it evaluates the conditions provided as input, selects the matching geographical areas from the database, and creates a list of matching candidate locations as output.

[0303] Step 6:

[0304] The server performs an optimization process based on the generated list of candidate locations. For each candidate location, it calculates evaluation scores such as cost, accessibility, and predicted number of participants. It receives the list of candidate locations as input, selects the most suitable event venue as output, and further creates an efficient staffing plan for the selected location.

[0305] Step 7:

[0306] The terminal visualizes the optimal venue and staffing plan sent from the server and presents them to the user. For example, it visually displays the optimized results together with map information on the screen and provides the user with a specific event plan. With this output, the user can quickly make a final decision.

[0307] (Application Example 1)

[0308] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0309] The problems in conventional event hosting are that the selection of the optimal location and efficient staff allocation are complicated, and it is difficult to achieve effective customer attraction. Also, it was difficult to predict the appropriate date and time for event hosting. As a result, it was difficult to build the strategies necessary for the success of the event, leading to problems such as economic losses and opportunity losses.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0311] In this invention, the server includes a function to collect movement data from multiple information sources and store it in a recording device, an information processing function to unify the collected information and remove unnecessary data, and an information analysis function to analyze the information using a learning model and generate movement predictions. This makes it possible to efficiently determine the optimal event location, time, and personnel allocation, and to support operations that increase the success rate.

[0312] An "information gathering device" is a device used to acquire data from multiple information sources.

[0313] An "information processing system" is a system for unifying, analyzing, and optimizing collected information.

[0314] A "recording device" is a device that has a storage function for saving collected data.

[0315] "Information sources" refer to the various media and platforms from which data is collected.

[0316] "Mobility data" refers to information about people's movements and flows, and is a collection of data that is gathered in real time.

[0317] "Standardization" is the process of aligning data from different formats to a certain standard, making it easier to analyze.

[0318] "Unnecessary data" refers to information that has little value in the analysis or decision-making process, or that is considered noise.

[0319] A "learning model" is an algorithm or mathematical model used for data analysis and prediction.

[0320] "Information analysis function" refers to the process of using collected data to obtain predictions and insights for various purposes.

[0321] The "List of Selected Locations" is a collection of information listing potential locations suitable for holding an event.

[0322] "Personnel allocation" refers to the assignment of staff necessary to efficiently carry out an event or task.

[0323] A "smartphone" is a portable communication device with multiple functions, such as displaying and operating information.

[0324] The system for realizing this application consists of an information gathering device, an information processing system, and a recording device. The server collects movement data from multiple information sources and stores it in the recording device. This enables real-time capture of human flow data. The collected data is processed through information processing functions that unify it and remove unnecessary data, making it suitable for analysis.

[0325] Next, the server uses a learning model to analyze the accumulated data. This analysis process generates future movement predictions based on past and present movement data. Users can then use the generated movement predictions to perform simulations for selecting event venues and staffing.

[0326] The optimal suggestions are presented to the user via the terminal. In this process, the server visualizes the selected information and provides it on a display device such as a smartphone. Based on this information, the user can formulate an effective event management plan.

[0327] A concrete example is a retailer planning a special weekend promotional event, who could use this system to determine the optimal store location and time slot. Such prediction-based decisions enable efficient customer attraction.

[0328] An example of a prompt might be: "Based on average foot traffic data from last year's weekend afternoons at 3 PM, predict the times when the most people will gather. Based on that prediction, propose appropriate staffing arrangements to ensure the event's success." This prompt utilizes advanced analysis powered by generative AI models to support event success.

[0329] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0330] Step 1:

[0331] The server collects movement data from multiple sources. Inputs include boarding and alighting information from public transport and location information from mobile devices, and output is stored in a recording device in raw data format. In this step, data is acquired in real time and stored in a format suitable for subsequent processing.

[0332] Step 2:

[0333] The server unifies the collected movement data and removes unnecessary data. The input is the raw data stored in step 1, and the output is data that has been noise-free and formatted into a unified format. Specifically, it filters out redundant data and leaves only the necessary items.

[0334] Step 3:

[0335] The server uses a learning model to analyze unified movement data and generate movement predictions. The input is the data generated in step 2, and the output is the predicted pedestrian flow pattern. Machine learning algorithms are applied as data processing to extract future movement patterns.

[0336] Step 4:

[0337] The server generates a list of potential venues based on the event conditions entered by the user. The input is the event details provided by the user (date, time, target, etc.), and the output is a list of potential venues. Specifically, the process includes identifying and listing geographical locations that meet the conditions.

[0338] Step 5:

[0339] The server evaluates candidate locations and selects the optimal event venue. The inputs are the list of candidate locations generated in step 4 and the pedestrian flow patterns from step 3, and the output is the selection result for the optimal location. As a data calculation, an evaluation score is calculated for each candidate location, and the location with the highest score is selected.

[0340] Step 6:

[0341] The server simulates staffing based on the selected locations and generates proposals. The input is the selection result from step 5, and the output is a proposed staffing plan. Specifically, it determines the number of staff according to the scale of the event and simulates the optimal placement pattern.

[0342] Step 7:

[0343] The terminal visualizes the suggestions obtained from the server and presents them to the user. The input is the suggestions from step 6, and the output is visual data displayed in a format that the user can review. In operation, event information and suggestions are displayed on the smartphone application screen, making them easily accessible to the user.

[0344] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0345] This invention combines a system that proposes optimal locations and staffing based on pedestrian flow data to maximize the effectiveness of event hosting with an emotion engine that recognizes user emotions and further enhances the event experience.

[0346] In the system's implementation, the server device first collects pedestrian flow data in real time from multiple data sources and stores it in a database. The collected data is preprocessed to remove noise and create a unified format. Then, a machine learning model is used to analyze the normalized data and generate pedestrian flow predictions for each region. This makes it possible to identify peak times and popular locations in specific areas.

[0347] The user inputs event conditions using a terminal. During this process, the emotion engine analyzes the user's voice and facial expressions to recognize their emotional state at the time of input. For example, if the user expresses joy, this information is incorporated into the system, allowing it to create a list of potential locations that align with the user's expectations. This enables the system to incorporate the user's emotional information into the list of potential locations.

[0348] Furthermore, the server evaluates candidate locations based on the analysis results and user sentiment information, and selects the optimal event location. In this process, sentiment information is reflected in the evaluation score, prioritizing the location that best suits the user's desired experience.

[0349] At the selected event location, the server simulates and generates suggestions for optimal staffing based on crowd flow predictions. The optimized results are presented to the user in a visualized form via a terminal. For example, if the emotion engine detects user anxiety, the system provides a more comfortable experience by suggesting options that avoid congestion.

[0350] This system allows users to receive suggestions based on event conditions while also taking emotions into consideration when preparing for the event.

[0351] The following describes the processing flow.

[0352] Step 1:

[0353] The server collects pedestrian flow data from multiple data sources. Specifically, it utilizes information on public transport usage, location data from smart devices, and social media traffic. This data is ingested into the database in real time.

[0354] Step 2:

[0355] The server preprocesses the collected pedestrian flow data. This includes standardizing the data format and removing outliers. After removing noise, the data is prepared in a format that allows for analysis by machine learning models.

[0356] Step 3:

[0357] The server uses machine learning models to perform analysis and generate predictions of pedestrian flow. These predictions include analysis results such as the number of people staying in a specific area and peak times, allowing for consideration of future pedestrian flow patterns.

[0358] Step 4:

[0359] When a user inputs event conditions via their device, their emotional state is recognized by the emotion engine. The system analyzes the user's facial expressions and voice to obtain emotional data such as joy and anxiety.

[0360] Step 5:

[0361] The server receives event conditions and sentiment data entered by the user and creates a list of optimal event venue candidates. The candidate selection process also incorporates customization based on the user's expectations and emotions.

[0362] Step 6:

[0363] The server calculates an evaluation score based on the list of candidate locations. This evaluation is based on accessibility, cost, and the appropriateness of the location selection according to user sentiment information.

[0364] Step 7:

[0365] The server selects the optimal event location and simulates the optimal staff deployment at that location. Based on the predicted crowd flow, it generates suggestions for the number and placement of staff.

[0366] Step 8:

[0367] The terminal visually presents the user with the optimized event location and staffing arrangements generated by the server. This allows the user to begin concrete event preparations based on the suggestions.

[0368] (Example 2)

[0369] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0370] When organizing an event, selecting the optimal location and appropriately allocating staff are crucial to maximizing participant satisfaction. However, traditional methods often involve manual analysis of travel data and venue selection, which is time-consuming and labor-intensive. Furthermore, selecting the optimal venue while considering participants' emotions presents a challenge.

[0371] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0372] In this invention, the server includes means for acquiring movement information from multiple information sources and storing it in a storage device, means for integrating the acquired movement information and removing unnecessary elements, and means for analyzing the information using a learning algorithm and generating movement predictions for each region. This enables efficient venue selection and staff allocation based on movement information, thereby increasing participant satisfaction. Furthermore, by including emotion analysis means that recognize the user's emotional state by analyzing voice and facial expressions and adjust venue candidates based on this information, it becomes possible to select the optimal venue that takes the user's emotions into consideration.

[0373] A "server" is a computing device that processes data obtained from multiple sources and provides analysis results.

[0374] "Mobility information" refers to data that shows the movement patterns of people and goods in a specific area.

[0375] A "storage device" is a device that has the function of storing data and retrieving and processing that data as needed.

[0376] A "data preparation method" is a system that integrates collected data into a consistent format and processes it to remove unnecessary information.

[0377] A "learning algorithm" is a computational method used to find rules and patterns in large amounts of data and to perform predictions and classifications.

[0378] An "information analysis tool" is a system that performs analysis based on obtained data to generate predictions and insights.

[0379] A "potential venue" is a list of several possible locations that are being considered for holding the event.

[0380] An "emotion analysis system" is a system that analyzes the user's voice and facial expressions to recognize their emotional state.

[0381] An "input / output device" is a device that allows a user to input information and to visually receive information from a computing device.

[0382] This invention is a system that automatically suggests the optimal location and staffing arrangement for an event. The system is configured and used as follows:

[0383] The server first collects movement information in real time from multiple sources. The collected data is stored in the server's storage device. Specifically, it utilizes information from APIs and sensors to collect data such as traffic volume and the usage status of public facilities. Next, the server processes this data using data preparation tools to remove noise and standardize the format. Standard data cleaning techniques are applied at this stage.

[0384] The server uses libraries such as TensorFlow and PyTorch to execute learning algorithms. This allows it to analyze movement data and generate movement predictions for a specific region. Based on the obtained prediction data, it lists potential event locations according to the event conditions set by the user.

[0385] The user inputs event conditions into the system via a terminal. At this time, the terminal analyzes the user's voice and facial expressions using emotion analysis tools to recognize their emotional state. In this step, an emotion engine is used, employing standard voice analysis and facial recognition technologies for emotion recognition.

[0386] Based on user input data and sentiment information, the server evaluates potential event locations and selects the optimal venue. Sentiment information is a crucial element in this selection process. Furthermore, the server simulates the optimal staffing arrangement and generates this as a proposal.

[0387] The terminal visualizes and presents optimized suggestions sent from the server to the user. This includes displaying potential venues on a map and generating heatmaps that predict congestion.

[0388] As a concrete example, consider a scenario where a user wants to find the best location for an art festival scheduled for the following weekend. Taking into account the user's relaxed mood, we can list the best locations that avoid crowds.

[0389] An example of a prompt message might be: "Please suggest the best venues for the art festival scheduled for next weekend. Please list the most suitable locations, taking into account the expected crowd levels and the user's relaxed mood."

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The server collects mobility information from multiple sources. Input data includes real-time traffic information from transportation APIs and data on the usage of public facilities. The server retrieves this data via API requests and stores it in storage. The output is a set of accumulated raw data.

[0393] Step 2:

[0394] The server processes the collected movement information. The input is the raw data obtained in step 1. Specifically, it performs tasks such as imputing missing data, removing outliers, and standardizing data formats. Data reliability is improved by using a denoising algorithm. The output is a normalized, high-quality dataset.

[0395] Step 3:

[0396] The server uses a learning algorithm to generate movement predictions from a normalized dataset. The input is the data prepared in step 2. Using machine learning libraries, it models movement patterns for each region by performing time series analysis and clustering. The output is analytical data predicting future human movement.

[0397] Step 4:

[0398] The user inputs event conditions using a terminal. The input data consists of detailed conditions and settings for the event desired by the user. The terminal sends this information to the server, which is then used to evaluate candidate locations. The output is a request from the user interface to the server.

[0399] Step 5:

[0400] The device acquires the user's voice and facial expressions and recognizes their emotional state using emotion analysis. Input consists of real-time acquired voice data and facial imagery. The emotion analysis engine analyzes the tone of the voice and facial features to determine the user's emotions. Output is the recognized emotion information.

[0401] Step 6:

[0402] The server evaluates potential event locations based on event conditions and sentiment information, and selects the optimal event location. The inputs are the pedestrian flow prediction data generated in step 3 and the information obtained in steps 4 and 5. The evaluation model is used to calculate a score for each candidate location, and the most suitable one is selected. The output is the selected optimal event location.

[0403] Step 7:

[0404] The server simulates staff deployment based on the selected venue information. The input is the venue information selected in step 6. The simulation designs the optimal staff deployment plan according to the predicted congestion. The output is the optimized staff deployment plan.

[0405] Step 8:

[0406] The terminal visualizes and presents optimal venue and staffing plans to the user. The input is the suggested content received from the server. The terminal visually displays the data using maps and graphs to make it easy for the user to understand. The output is the visualized information presented to the user.

[0407] (Application Example 2)

[0408] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0409] In recent years, optimal location selection and staffing at events and commercial facilities have become crucial for event success. However, many systems rely solely on predictions based on pedestrian flow data and fail to consider visitor sentiment, making it difficult to optimize the individual user experience. Furthermore, a lack of concrete suggestions for avoiding congestion also hinders a comfortable user experience.

[0410] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0411] In this invention, the server includes means for collecting pedestrian flow information from multiple information sources and storing it in an information aggregate, means for preprocessing the collected information to normalize it and remove unnecessary information, and means for analyzing the information using a machine learning model and generating pedestrian flow predictions. This makes it possible to propose the optimal event location and worker placement while taking into account the user's emotional information, and to provide a comfortable event experience that avoids congestion.

[0412] An "information processing device" is a computer system that collects data from multiple sources, analyzes it, and processes it.

[0413] An "information collection" is a database that stores collected data and manages it so that it can be used as needed.

[0414] "Information preprocessing means" refers to methods for processing collected data to convert it into a format that is easy to analyze, such as removing unnecessary information or standardizing the data format.

[0415] A "machine learning model" is an algorithm or method used to analyze data, find patterns, and make predictions.

[0416] An "information analysis tool" is a mechanism for performing analysis based on collected and pre-processed data, according to a specific purpose.

[0417] "Event conditions" refer to information that specifically defines the characteristics and requirements of an event that a user is planning to hold.

[0418] "Emotion recognition means" refers to technologies and methods for recognizing a user's emotional state at a given time by analyzing their facial expressions and voice.

[0419] An "evaluation score" is a numerical indicator that quantifies the extent to which specific conditions are met, generated based on analysis results and user sentiment information.

[0420] The server, acting as an information processing device, collects pedestrian flow information from multiple sources. This includes real-time data from sensors, cameras, and other sources. The collected data is quickly and efficiently de-noised and converted into a unified format using pre-processing tools. At this stage, cloud infrastructure such as Microsoft Azure and Google Cloud can be used.

[0421] After the data is normalized, the server uses a machine learning model to analyze the information and generate pedestrian flow predictions. Here, TensorFlow is used to predict peak times and congestion in specific areas. The analyzed data is stored in an information repository.

[0422] When a user sends event conditions to a server using their device, an emotion recognition mechanism is activated. The device can be, for example, a smartphone or tablet, and its camera and microphone collect the user's facial expressions and voice. This allows Microsoft Azure's emotion analysis service to identify the user's emotional state.

[0423] The server incorporates the analyzed sentiment information into an evaluation score and lists the most suitable candidate locations based on the user's request. Furthermore, if a suggested location is likely to be crowded, it presents alternative options to avoid the crowds based on the sentiment information.

[0424] Finally, the proposed content is visualized on the device and provided to the user. Based on this, the user can determine the optimal event plan and communicate that information to the staff via wireless communication.

[0425] As a concrete example, when an event is scheduled, the system predicts when attendees will be most concentrated and suggests alternative options to alleviate congestion. This results in a more comfortable experience for customers.

[0426] An example of a prompt using a generative AI model is: "Based on the latest customer sentiment data, please come up with suggestions to provide a better experience for customers so they can shop comfortably in the store."

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server collects pedestrian flow information in real time from multiple sources. It receives data from each sensor and camera via an interface and temporarily stores it in an information aggregate. At this stage, the raw data is enormous and may include incomplete information.

[0430] Step 2:

[0431] The server performs information preprocessing on the collected raw data. This process removes noise and formats the data into a consistent format. Data processing is achieved by filtering outliers, imputing missing values, and standardizing the data. The output is a clean dataset in a format suitable for analysis.

[0432] Step 3:

[0433] The server uses normalized data to perform analysis with machine learning models. Leveraging TensorFlow, it applies pedestrian flow pattern recognition and prediction models to the analysis. It predicts peak times from the input data and identifies when and where congestion occurs. The output is generated as a pedestrian flow prediction report in text and graph formats.

[0434] Step 4:

[0435] The user inputs event conditions from their device. This information is sent to the server and includes the starting point and scheduled date and time. The user's facial expressions and voice are recorded using the device's microphone and camera. Audio and image data that provide hints about emotions are acquired as input.

[0436] Step 5:

[0437] The server uses emotion recognition tools to analyze the user's emotional state from their facial expressions and voice. It generates an emotion score using the Microsoft Azure Emotion Analysis Service. This involves analyzing facial expression features and voice tone to identify emotions. The output is an evaluation score, quantified as emotion information.

[0438] Step 6:

[0439] The server incorporates sentiment scores into its evaluation and generates a list of candidate locations combined with crowd flow predictions. Based on this combination, it selects the optimal event location. Specifically, if a user's sentiment of happiness is high, options that meet that request are prioritized. The output is a ranked list of recommended event locations.

[0440] Step 7:

[0441] The server provides options to avoid congestion. Based on sentiment information and crowd flow predictions, it proposes a plan to avoid congestion. In this process, it generates recommendations for alternative routes and different time slots. The output is congestion avoidance suggestions.

[0442] Step 8:

[0443] The user visually reviews the suggestions generated by the server via their terminal. Visualized data of optimal locations and staff deployments are displayed on the terminal's screen. Based on this, the user makes a final decision. As output, confirmation information regarding the optimal location selected by the user is obtained.

[0444] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0445] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0446] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0447] [Third Embodiment]

[0448] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0449] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0450] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0451] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0452] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0453] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0454] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0455] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0456] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0457] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0458] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0459] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0460] This invention is a system that optimizes the selection of venues and staff allocation necessary for efficiently holding events. The core of the system is data collection, analysis, and optimization processing performed by a server device. The server first utilizes multiple data sources to collect pedestrian flow data in real time. This includes information on boarding and alighting from public transportation and location information from mobile devices.

[0461] The server preprocesses the collected data, removing noise and formatting it into a unified format. Next, a pre-trained machine learning model is used to analyze the pedestrian flow data and predict future patterns. This predicted data forms the basis for selecting the optimal event venue.

[0462] Users input event information into the system via a terminal. This information includes the attributes of the target audience, desired date and time, duration, budget, and required equipment. The server uses the conditions entered by the user and crowd flow prediction data to create a list of multiple potential event venues.

[0463] In the optimization process, the server evaluates each venue on the candidate site list, calculates an evaluation score, and selects the optimal venue. This evaluation score takes into account cost, accessibility, and the expected number of participants. Furthermore, it simulates the optimal staffing arrangement at the selected location and proposes solutions to ensure efficient event management.

[0464] As a result, the terminal visually presents the user with the optimal venue and staffing plan. For example, for a concert event held in an urban area on a specific date and time, the server analyzes pedestrian flow data to identify the areas where the most people gather during that time, and then constructs the overall plan necessary for the event's success.

[0465] This series of processes enables users to conduct events efficiently and effectively.

[0466] The following describes the processing flow.

[0467] Step 1:

[0468] The server collects pedestrian flow data in real time from multiple data sources. This includes information on boarding and alighting from public transportation, location data from smartphones, and public posts from social media. The server stores this data in a database.

[0469] Step 2:

[0470] The server performs data preprocessing on the collected data. Specifically, it removes noise, checks for outliers, and standardizes data formats to prepare the data for analysis. During this process, the server filters out inaccurate data.

[0471] Step 3:

[0472] The server applies a pre-trained machine learning model to analyze pre-processed data. This analysis generates historical pedestrian flow patterns and future predictions for specific areas. This makes it possible to identify peak times and popular areas.

[0473] Step 4:

[0474] The user enters details about the event they are hosting (target audience attributes, date and time, budget, etc.) through their device. The device then sends these details to the server.

[0475] Step 5:

[0476] The server generates a list of potential event venues by combining historical data and analysis results based on the event conditions provided by the user. The venues are selected considering their availability and usage conditions.

[0477] Step 6:

[0478] The server calculates an evaluation score for each venue on the candidate site list. This score is calculated considering factors such as accessibility, cost efficiency, and expected attendance. The venue with the highest score is selected as the optimal choice.

[0479] Step 7:

[0480] The server simulates the optimization of staff allocation based on congestion predictions at the selected event venue. It proposes the necessary number of staff and their allocation for efficient operation.

[0481] Step 8:

[0482] The terminal visualizes the optimization results from the server and presents them to the user. The user receives suggestions for the optimal event location and staffing, and can proceed with event preparations based on these suggestions.

[0483] (Example 1)

[0484] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0485] In traditional event planning, optimizing venue selection and staffing required significant time and effort, often resulting in inefficient operations. Furthermore, accurately predicting participant numbers and demographics was difficult due to the challenge of reflecting demographic changes in real time. This could lead to decreased participant satisfaction and cost overruns, especially in large-scale events.

[0486] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0487] In this invention, the server includes means for collecting demographic data from multiple information sources and storing it on a recording medium, means for preprocessing the collected data to organize it and remove errors, and means for analyzing the information using a learning algorithm to generate demographic forecasts. This enables efficient and effective optimization of event location selection and personnel allocation, and allows for real-time response.

[0488] A "data supply device" is a device that functions as an external source of information for providing demographic data.

[0489] An "information processing device" is a device that manages the entire system for performing analysis and evaluation based on collected data.

[0490] "Population dynamics data" refers to information about the movement and distribution of people in a specific region or time period.

[0491] A "recording medium" is a physical or virtual medium used to store data and make it accessible later.

[0492] "Information preprocessing means" refers to methods for removing errors and misinformation from collected data and converting it into an appropriate format that can be analyzed.

[0493] A "learning algorithm" is a computational procedure that analyzes patterns and trends based on input data to predict or classify new information.

[0494] "Information analysis methods" refer to methods and techniques for analyzing organized data in detail and deriving useful insights based on the results.

[0495] A "user" is an individual or group that operates the system and plans and manages events.

[0496] The "Candidate Region List" is a list of geographical locations suitable for holding events, selected based on the analysis results.

[0497] "Staffing" refers to assigning the appropriate number and skills of staff to specific locations and roles.

[0498] A "display device" is a device used to visually display the results transmitted from an information processing device.

[0499] This system optimizes venue selection and personnel allocation for event hosting, primarily through data supply and information processing devices. Specifically, the server collects demographic data in real time from various sources, including public transport operation data and location information from mobile devices. The data is stored on a recording medium and used for subsequent processing. The server organizes the collected data and performs preprocessing to remove errors and standardize the format. This preprocessing utilizes data cleaning and filtering algorithms.

[0500] Next, the server analyzes the preprocessed data using a pre-trained learning algorithm. This analysis predicts future demographic fluctuation patterns and generates a list of candidate regions based on these predictions. The server evaluates this list of candidate regions and uses it as a criterion for selecting the optimal activity location. For the selected locations, the server simulates staffing and proposes an efficient staffing plan.

[0501] Users access the system using a terminal and enter information about the event, including the target audience, preferred date and time, and budget. The server compares these conditions with forecast data to generate a list of optimal locations and placements.

[0502] Ultimately, the terminal visually displays information obtained from the server and provides the user with suggestions for the optimal venue and staffing arrangements. For example, in the case of a concert held in the city center on a specific date and time, the server indicates the predicted areas where people are likely to gather and programs directions accordingly.

[0503] An example of a prompt message would be: "Generate an optimal venue and staffing plan for an urban concert event based on the following parameters: target audience, soundproofing, accessibility, budget limit, and desired date."

[0504] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0505] Step 1:

[0506] The server collects demographic data from multiple sources. This collection utilizes public transport APIs and mobile device location services. It receives traffic boarding / alighting data and location data as input, and saves this data to a recording medium in real time, preparing the foundational data for selecting potential event locations.

[0507] Step 2:

[0508] The server preprocesses the collected demographic data. Specifically, it imputes missing data, removes outliers, and normalizes the data into a unified format. This process processes the raw data provided as input and generates a clean dataset suitable for analysis as output.

[0509] Step 3:

[0510] The server uses pre-processed data to predict demographic patterns using a pre-trained generative AI model. It accepts normalized demographic data as input and generates predictions of pedestrian flow for specific time periods and regions as output. This facilitates the selection of potential future event locations.

[0511] Step 4:

[0512] Users input event-related conditions into the system via their terminal. For example, they enter target audience attributes, date and time, budget, and required equipment specifications. The entered conditions are sent to a server, where they are used as evaluation criteria for selecting potential venues.

[0513] Step 5:

[0514] The server generates a list of candidate locations by comparing user-provided conditions with predicted demographic data. Specifically, it evaluates the conditions provided as input, selects suitable geographical areas from the database, and creates a list of suitable candidate locations as output.

[0515] Step 6:

[0516] The server performs optimization processing based on the generated list of candidate locations. For each candidate location, it calculates evaluation scores such as cost, accessibility, and predicted number of participants. It receives the list of candidate locations as input, selects the most suitable event venue as output, and then creates an efficient staffing plan for the selected location.

[0517] Step 7:

[0518] The terminal visualizes and presents to the user the optimal venue and staffing plan sent from the server. For example, it displays the visually optimized results on the screen along with map information, providing the user with a concrete event plan. This output allows the user to make a final decision quickly.

[0519] (Application Example 1)

[0520] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0521] Traditional event planning has faced challenges such as the difficulty of selecting the optimal venue and efficiently allocating staff, making it challenging to attract a large audience. Predicting the appropriate date and time for an event was also difficult. This made it difficult to develop strategies necessary for event success, resulting in financial losses and missed opportunities.

[0522] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0523] In this invention, the server includes a function to collect movement data from multiple information sources and store it in a recording device, an information processing function to unify the collected information and remove unnecessary data, and an information analysis function to analyze the information using a learning model and generate movement predictions. This makes it possible to efficiently determine the optimal event location, time, and personnel allocation, and to support operations that increase the success rate.

[0524] An "information gathering device" is a device used to acquire data from multiple information sources.

[0525] An "information processing system" is a system for unifying, analyzing, and optimizing collected information.

[0526] A "recording device" is a device that has a storage function for saving collected data.

[0527] "Information sources" refer to the various media and platforms from which data is collected.

[0528] "Mobility data" refers to information about people's movements and flows, and is a collection of data that is gathered in real time.

[0529] "Standardization" is the process of aligning data from different formats to a certain standard, making it easier to analyze.

[0530] "Unnecessary data" refers to information that has little value in the analysis or decision-making process, or that is considered noise.

[0531] A "learning model" is an algorithm or mathematical model used for data analysis and prediction.

[0532] "Information analysis function" refers to the process of using collected data to obtain predictions and insights for various purposes.

[0533] The "List of Selected Locations" is a collection of information listing potential locations suitable for holding an event.

[0534] "Personnel allocation" refers to the assignment of staff necessary to efficiently carry out an event or task.

[0535] A "smartphone" is a portable communication device with multiple functions, such as displaying and operating information.

[0536] The system for realizing this application consists of an information gathering device, an information processing system, and a recording device. The server collects movement data from multiple information sources and stores it in the recording device. This enables real-time capture of human flow data. The collected data is processed through information processing functions that unify it and remove unnecessary data, making it suitable for analysis.

[0537] Next, the server uses a learning model to analyze the accumulated data. This analysis process generates future movement predictions based on past and present movement data. Users can then use the generated movement predictions to perform simulations for selecting event venues and staffing.

[0538] The optimal suggestions are presented to the user via the terminal. In this process, the server visualizes the selected information and provides it on a display device such as a smartphone. Based on this information, the user can formulate an effective event management plan.

[0539] A concrete example is a retailer planning a special weekend promotional event, who could use this system to determine the optimal store location and time slot. Such prediction-based decisions enable efficient customer attraction.

[0540] An example of a prompt might be: "Based on average foot traffic data from last year's weekend afternoons at 3 PM, predict the times when the most people will gather. Based on that prediction, propose appropriate staffing arrangements to ensure the event's success." This prompt utilizes advanced analysis powered by generative AI models to support event success.

[0541] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0542] Step 1:

[0543] The server collects movement data from multiple sources. Inputs include boarding and alighting information from public transport and location information from mobile devices, and output is stored in a recording device in raw data format. In this step, data is acquired in real time and stored in a format suitable for subsequent processing.

[0544] Step 2:

[0545] The server unifies the collected movement data and removes unnecessary data. The input is the raw data stored in step 1, and the output is data that has been noise-free and formatted into a unified format. Specifically, it filters out redundant data and leaves only the necessary items.

[0546] Step 3:

[0547] The server uses a learning model to analyze unified movement data and generate movement predictions. The input is the data generated in step 2, and the output is the predicted pedestrian flow pattern. Machine learning algorithms are applied as data processing to extract future movement patterns.

[0548] Step 4:

[0549] The server generates a list of potential venues based on the event conditions entered by the user. The input is the event details provided by the user (date, time, target, etc.), and the output is a list of potential venues. Specifically, the process includes identifying and listing geographical locations that meet the conditions.

[0550] Step 5:

[0551] The server evaluates candidate locations and selects the optimal event venue. The inputs are the list of candidate locations generated in step 4 and the pedestrian flow patterns from step 3, and the output is the selection result for the optimal location. As a data calculation, an evaluation score is calculated for each candidate location, and the location with the highest score is selected.

[0552] Step 6:

[0553] The server simulates staffing based on the selected locations and generates proposals. The input is the selection result from step 5, and the output is a proposed staffing plan. Specifically, it determines the number of staff according to the scale of the event and simulates the optimal placement pattern.

[0554] Step 7:

[0555] The terminal visualizes the suggestions obtained from the server and presents them to the user. The input is the suggestions from step 6, and the output is visual data displayed in a format that the user can review. In operation, event information and suggestions are displayed on the smartphone application screen, making them easily accessible to the user.

[0556] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0557] This invention combines a system that proposes optimal locations and staffing based on pedestrian flow data to maximize the effectiveness of event hosting with an emotion engine that recognizes user emotions and further enhances the event experience.

[0558] In the system's implementation, the server device first collects pedestrian flow data in real time from multiple data sources and stores it in a database. The collected data is preprocessed to remove noise and create a unified format. Then, a machine learning model is used to analyze the normalized data and generate pedestrian flow predictions for each region. This makes it possible to identify peak times and popular locations in specific areas.

[0559] The user inputs event conditions using a terminal. During this process, the emotion engine analyzes the user's voice and facial expressions to recognize their emotional state at the time of input. For example, if the user expresses joy, this information is incorporated into the system, allowing it to create a list of potential locations that align with the user's expectations. This enables the system to incorporate the user's emotional information into the list of potential locations.

[0560] Furthermore, the server evaluates candidate locations based on the analysis results and user sentiment information, and selects the optimal event location. In this process, sentiment information is reflected in the evaluation score, prioritizing the location that best suits the user's desired experience.

[0561] At the selected event location, the server simulates and generates suggestions for optimal staffing based on crowd flow predictions. The optimized results are presented to the user in a visualized form via a terminal. For example, if the emotion engine detects user anxiety, the system provides a more comfortable experience by suggesting options that avoid congestion.

[0562] This system allows users to receive suggestions based on event conditions while also taking emotions into consideration when preparing for the event.

[0563] The following describes the processing flow.

[0564] Step 1:

[0565] The server collects pedestrian flow data from multiple data sources. Specifically, it utilizes information on public transport usage, location data from smart devices, and social media traffic. This data is ingested into the database in real time.

[0566] Step 2:

[0567] The server preprocesses the collected pedestrian flow data. This includes standardizing the data format and removing outliers. After removing noise, the data is prepared in a format that allows for analysis by machine learning models.

[0568] Step 3:

[0569] The server uses machine learning models to perform analysis and generate predictions of pedestrian flow. These predictions include analysis results such as the number of people staying in a specific area and peak times, allowing for consideration of future pedestrian flow patterns.

[0570] Step 4:

[0571] When a user inputs event conditions via their device, their emotional state is recognized by the emotion engine. The system analyzes the user's facial expressions and voice to obtain emotional data such as joy and anxiety.

[0572] Step 5:

[0573] The server receives event conditions and sentiment data entered by the user and creates a list of optimal event venue candidates. The candidate selection process also incorporates customization based on the user's expectations and emotions.

[0574] Step 6:

[0575] The server calculates an evaluation score based on the list of candidate locations. This evaluation is based on accessibility, cost, and the appropriateness of the location selection according to user sentiment information.

[0576] Step 7:

[0577] The server selects the optimal event location and simulates the optimal staff deployment at that location. Based on the predicted crowd flow, it generates suggestions for the number and placement of staff.

[0578] Step 8:

[0579] The terminal visually presents the user with the optimized event location and staffing arrangements generated by the server. This allows the user to begin concrete event preparations based on the suggestions.

[0580] (Example 2)

[0581] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0582] When organizing an event, selecting the optimal location and appropriately allocating staff are crucial to maximizing participant satisfaction. However, traditional methods often involve manual analysis of travel data and venue selection, which is time-consuming and labor-intensive. Furthermore, selecting the optimal venue while considering participants' emotions presents a challenge.

[0583] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0584] In this invention, the server includes means for acquiring movement information from multiple information sources and storing it in a storage device, means for integrating the acquired movement information and removing unnecessary elements, and means for analyzing the information using a learning algorithm and generating movement predictions for each region. This enables efficient venue selection and staff allocation based on movement information, thereby increasing participant satisfaction. Furthermore, by including emotion analysis means that recognize the user's emotional state by analyzing voice and facial expressions and adjust venue candidates based on this information, it becomes possible to select the optimal venue that takes the user's emotions into consideration.

[0585] A "server" is a computing device that processes data obtained from multiple sources and provides analysis results.

[0586] "Mobility information" refers to data that shows the movement patterns of people and goods in a specific area.

[0587] A "storage device" is a device that has the function of storing data and retrieving and processing that data as needed.

[0588] A "data preparation method" is a system that integrates collected data into a consistent format and processes it to remove unnecessary information.

[0589] A "learning algorithm" is a computational method used to find rules and patterns in large amounts of data and to perform predictions and classifications.

[0590] An "information analysis tool" is a system that performs analysis based on obtained data to generate predictions and insights.

[0591] A "potential venue" is a list of several possible locations that are being considered for holding the event.

[0592] An "emotion analysis system" is a system that analyzes the user's voice and facial expressions to recognize their emotional state.

[0593] An "input / output device" is a device that allows a user to input information and to visually receive information from a computing device.

[0594] This invention is a system that automatically suggests the optimal location and staffing arrangement for an event. The system is configured and used as follows:

[0595] The server first collects movement information in real time from multiple sources. The collected data is stored in the server's storage device. Specifically, it utilizes information from APIs and sensors to collect data such as traffic volume and the usage status of public facilities. Next, the server processes this data using data preparation tools to remove noise and standardize the format. Standard data cleaning techniques are applied at this stage.

[0596] The server uses libraries such as TensorFlow and PyTorch to execute learning algorithms. This allows it to analyze movement data and generate movement predictions for a specific region. Based on the obtained prediction data, it lists potential event locations according to the event conditions set by the user.

[0597] The user inputs event conditions into the system via a terminal. At this time, the terminal analyzes the user's voice and facial expressions using emotion analysis tools to recognize their emotional state. In this step, an emotion engine is used, employing standard voice analysis and facial recognition technologies for emotion recognition.

[0598] Based on user input data and sentiment information, the server evaluates potential event locations and selects the optimal venue. Sentiment information is a crucial element in this selection process. Furthermore, the server simulates the optimal staffing arrangement and generates this as a proposal.

[0599] The terminal visualizes and presents optimized suggestions sent from the server to the user. This includes displaying potential venues on a map and generating heatmaps that predict congestion.

[0600] As a concrete example, consider a scenario where a user wants to find the best location for an art festival scheduled for the following weekend. Taking into account the user's relaxed mood, we can list the best locations that avoid crowds.

[0601] An example of a prompt message might be: "Please suggest the best venues for the art festival scheduled for next weekend. Please list the most suitable locations, taking into account the expected crowd levels and the user's relaxed mood."

[0602] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0603] Step 1:

[0604] The server collects mobility information from multiple sources. Input data includes real-time traffic information from transportation APIs and data on the usage of public facilities. The server retrieves this data via API requests and stores it in storage. The output is a set of accumulated raw data.

[0605] Step 2:

[0606] The server processes the collected movement information. The input is the raw data obtained in step 1. Specifically, it performs tasks such as imputing missing data, removing outliers, and standardizing data formats. Data reliability is improved by using a denoising algorithm. The output is a normalized, high-quality dataset.

[0607] Step 3:

[0608] The server uses a learning algorithm to generate movement predictions from a normalized dataset. The input is the data prepared in step 2. Using machine learning libraries, it models movement patterns for each region by performing time series analysis and clustering. The output is analytical data predicting future human movement.

[0609] Step 4:

[0610] The user inputs event conditions using a terminal. The input data consists of detailed conditions and settings for the event desired by the user. The terminal sends this information to the server, which is then used to evaluate candidate locations. The output is a request from the user interface to the server.

[0611] Step 5:

[0612] The device acquires the user's voice and facial expressions and recognizes their emotional state using emotion analysis. Input consists of real-time acquired voice data and facial imagery. The emotion analysis engine analyzes the tone of the voice and facial features to determine the user's emotions. Output is the recognized emotion information.

[0613] Step 6:

[0614] The server evaluates potential event locations based on event conditions and sentiment information, and selects the optimal event location. The inputs are the pedestrian flow prediction data generated in step 3 and the information obtained in steps 4 and 5. The evaluation model is used to calculate a score for each candidate location, and the most suitable one is selected. The output is the selected optimal event location.

[0615] Step 7:

[0616] The server simulates staff deployment based on the selected venue information. The input is the venue information selected in step 6. The simulation designs the optimal staff deployment plan according to the predicted congestion. The output is the optimized staff deployment plan.

[0617] Step 8:

[0618] The terminal visualizes and presents optimal venue and staffing plans to the user. The input is the suggested content received from the server. The terminal visually displays the data using maps and graphs to make it easy for the user to understand. The output is the visualized information presented to the user.

[0619] (Application Example 2)

[0620] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0621] In recent years, optimal location selection and staffing at events and commercial facilities have become crucial for event success. However, many systems rely solely on predictions based on pedestrian flow data and fail to consider visitor sentiment, making it difficult to optimize the individual user experience. Furthermore, a lack of concrete suggestions for avoiding congestion also hinders a comfortable user experience.

[0622] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0623] In this invention, the server includes means for collecting pedestrian flow information from multiple information sources and storing it in an information aggregate, means for preprocessing the collected information to normalize it and remove unnecessary information, and means for analyzing the information using a machine learning model and generating pedestrian flow predictions. This makes it possible to propose the optimal event location and worker placement while taking into account the user's emotional information, and to provide a comfortable event experience that avoids congestion.

[0624] An "information processing device" is a computer system that collects data from multiple sources, analyzes it, and processes it.

[0625] An "information collection" is a database that stores collected data and manages it so that it can be used as needed.

[0626] "Information preprocessing means" refers to methods for processing collected data to convert it into a format that is easy to analyze, such as removing unnecessary information or standardizing the data format.

[0627] A "machine learning model" is an algorithm or method used to analyze data, find patterns, and make predictions.

[0628] An "information analysis tool" is a mechanism for performing analysis based on collected and pre-processed data, according to a specific purpose.

[0629] "Event conditions" refer to information that specifically defines the characteristics and requirements of an event that a user is planning to hold.

[0630] "Emotion recognition means" refers to technologies and methods for recognizing a user's emotional state at a given time by analyzing their facial expressions and voice.

[0631] An "evaluation score" is a numerical indicator that quantifies the extent to which specific conditions are met, generated based on analysis results and user sentiment information.

[0632] The server, acting as an information processing device, collects pedestrian flow information from multiple sources. This includes real-time data from sensors, cameras, and other sources. The collected data is quickly and efficiently de-noised and converted into a unified format using pre-processing tools. At this stage, cloud infrastructure such as Microsoft Azure and Google Cloud can be used.

[0633] After the data is normalized, the server uses a machine learning model to analyze the information and generate pedestrian flow predictions. Here, TensorFlow is used to predict peak times and congestion in specific areas. The analyzed data is stored in an information repository.

[0634] When a user sends event conditions to a server using their device, an emotion recognition mechanism is activated. The device can be, for example, a smartphone or tablet, and its camera and microphone collect the user's facial expressions and voice. This allows Microsoft Azure's emotion analysis service to identify the user's emotional state.

[0635] The server incorporates the analyzed sentiment information into an evaluation score and lists the most suitable candidate locations based on the user's request. Furthermore, if a suggested location is likely to be crowded, it presents alternative options to avoid the crowds based on the sentiment information.

[0636] Finally, the proposed content is visualized on the device and provided to the user. Based on this, the user can determine the optimal event plan and communicate that information to the staff via wireless communication.

[0637] As a concrete example, when an event is scheduled, the system predicts when attendees will be most concentrated and suggests alternative options to alleviate congestion. This results in a more comfortable experience for customers.

[0638] An example of a prompt using a generative AI model is: "Based on the latest customer sentiment data, please come up with suggestions to provide a better experience for customers so they can shop comfortably in the store."

[0639] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0640] Step 1:

[0641] The server collects pedestrian flow information in real time from multiple sources. It receives data from each sensor and camera via an interface and temporarily stores it in an information aggregate. At this stage, the raw data is enormous and may include incomplete information.

[0642] Step 2:

[0643] The server performs information preprocessing on the collected raw data. This process removes noise and formats the data into a consistent format. Data processing is achieved by filtering outliers, imputing missing values, and standardizing the data. The output is a clean dataset in a format suitable for analysis.

[0644] Step 3:

[0645] The server uses normalized data to perform analysis with machine learning models. Leveraging TensorFlow, it applies pedestrian flow pattern recognition and prediction models to the analysis. It predicts peak times from the input data and identifies when and where congestion occurs. The output is generated as a pedestrian flow prediction report in text and graph formats.

[0646] Step 4:

[0647] The user inputs event conditions from their device. This information is sent to the server and includes the starting point and scheduled date and time. The user's facial expressions and voice are recorded using the device's microphone and camera. Audio and image data that provide hints about emotions are acquired as input.

[0648] Step 5:

[0649] The server uses emotion recognition tools to analyze the user's emotional state from their facial expressions and voice. It generates an emotion score using the Microsoft Azure Emotion Analysis Service. This involves analyzing facial expression features and voice tone to identify emotions. The output is an evaluation score, quantified as emotion information.

[0650] Step 6:

[0651] The server incorporates sentiment scores into its evaluation and generates a list of candidate locations combined with crowd flow predictions. Based on this combination, it selects the optimal event location. Specifically, if a user's sentiment of happiness is high, options that meet that request are prioritized. The output is a ranked list of recommended event locations.

[0652] Step 7:

[0653] The server provides options to avoid congestion. Based on sentiment information and crowd flow predictions, it proposes a plan to avoid congestion. In this process, it generates recommendations for alternative routes and different time slots. The output is congestion avoidance suggestions.

[0654] Step 8:

[0655] The user visually reviews the suggestions generated by the server via their terminal. Visualized data of optimal locations and staff deployments are displayed on the terminal's screen. Based on this, the user makes a final decision. As output, confirmation information regarding the optimal location selected by the user is obtained.

[0656] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0657] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0658] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0659] [Fourth Embodiment]

[0660] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0661] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0662] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0663] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0664] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0665] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0666] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0667] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0668] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0669] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0670] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0671] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0672] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0673] This invention is a system that optimizes the selection of venues and staff allocation necessary for efficiently holding events. The core of the system is data collection, analysis, and optimization processing performed by a server device. The server first utilizes multiple data sources to collect pedestrian flow data in real time. This includes information on boarding and alighting from public transportation and location information from mobile devices.

[0674] The server preprocesses the collected data, removing noise and formatting it into a unified format. Next, a pre-trained machine learning model is used to analyze the pedestrian flow data and predict future patterns. This predicted data forms the basis for selecting the optimal event venue.

[0675] Users input event information into the system via a terminal. This information includes the attributes of the target audience, desired date and time, duration, budget, and required equipment. The server uses the conditions entered by the user and crowd flow prediction data to create a list of multiple potential event venues.

[0676] In the optimization process, the server evaluates each venue on the candidate site list, calculates an evaluation score, and selects the optimal venue. This evaluation score takes into account cost, accessibility, and the expected number of participants. Furthermore, it simulates the optimal staffing arrangement at the selected location and proposes solutions to ensure efficient event management.

[0677] As a result, the terminal visually presents the user with the optimal venue and staffing plan. For example, for a concert event held in an urban area on a specific date and time, the server analyzes pedestrian flow data to identify the areas where the most people gather during that time, and then constructs the overall plan necessary for the event's success.

[0678] This series of processes enables users to conduct events efficiently and effectively.

[0679] The following describes the processing flow.

[0680] Step 1:

[0681] The server collects pedestrian flow data in real time from multiple data sources. This includes information on boarding and alighting from public transportation, location data from smartphones, and public posts from social media. The server stores this data in a database.

[0682] Step 2:

[0683] The server performs data preprocessing on the collected data. Specifically, it removes noise, checks for outliers, and standardizes data formats to prepare the data for analysis. During this process, the server filters out inaccurate data.

[0684] Step 3:

[0685] The server applies a pre-trained machine learning model to analyze pre-processed data. This analysis generates historical pedestrian flow patterns and future predictions for specific areas. This makes it possible to identify peak times and popular areas.

[0686] Step 4:

[0687] The user enters details about the event they are hosting (target audience attributes, date and time, budget, etc.) through their device. The device then sends these details to the server.

[0688] Step 5:

[0689] The server generates a list of potential event venues by combining historical data and analysis results based on the event conditions provided by the user. The venues are selected considering their availability and usage conditions.

[0690] Step 6:

[0691] The server calculates an evaluation score for each venue on the candidate site list. This score is calculated considering factors such as accessibility, cost efficiency, and expected attendance. The venue with the highest score is selected as the optimal choice.

[0692] Step 7:

[0693] The server simulates the optimization of staff allocation based on congestion predictions at the selected event venue. It proposes the necessary number of staff and their allocation for efficient operation.

[0694] Step 8:

[0695] The terminal visualizes the optimization results from the server and presents them to the user. The user receives suggestions for the optimal event location and staffing, and can proceed with event preparations based on these suggestions.

[0696] (Example 1)

[0697] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In traditional event planning, optimizing venue selection and staffing required significant time and effort, often resulting in inefficient operations. Furthermore, accurately predicting participant numbers and demographics was difficult due to the challenge of reflecting demographic changes in real time. This could lead to decreased participant satisfaction and cost overruns, especially in large-scale events.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0700] In this invention, the server includes means for collecting demographic data from multiple information sources and storing it on a recording medium, means for preprocessing the collected data to organize it and remove errors, and means for analyzing the information using a learning algorithm to generate demographic forecasts. This enables efficient and effective optimization of event location selection and personnel allocation, and allows for real-time response.

[0701] A "data supply device" is a device that functions as an external source of information for providing demographic data.

[0702] An "information processing device" is a device that manages the entire system for performing analysis and evaluation based on collected data.

[0703] "Population dynamics data" refers to information about the movement and distribution of people in a specific region or time period.

[0704] A "recording medium" is a physical or virtual medium used to store data and make it accessible later.

[0705] "Information preprocessing means" refers to methods for removing errors and misinformation from collected data and converting it into an appropriate format that can be analyzed.

[0706] A "learning algorithm" is a computational procedure that analyzes patterns and trends based on input data to predict or classify new information.

[0707] "Information analysis methods" refer to methods and techniques for analyzing organized data in detail and deriving useful insights based on the results.

[0708] A "user" is an individual or group that operates the system and plans and manages events.

[0709] The "Candidate Region List" is a list of geographical locations suitable for holding events, selected based on the analysis results.

[0710] "Staffing" refers to assigning the appropriate number and skills of staff to specific locations and roles.

[0711] A "display device" is a device used to visually display the results transmitted from an information processing device.

[0712] This system optimizes venue selection and personnel allocation for event hosting, primarily through data supply and information processing devices. Specifically, the server collects demographic data in real time from various sources, including public transport operation data and location information from mobile devices. The data is stored on a recording medium and used for subsequent processing. The server organizes the collected data and performs preprocessing to remove errors and standardize the format. This preprocessing utilizes data cleaning and filtering algorithms.

[0713] Next, the server analyzes the preprocessed data using a pre-trained learning algorithm. This analysis predicts future demographic fluctuation patterns and generates a list of candidate regions based on these predictions. The server evaluates this list of candidate regions and uses it as a criterion for selecting the optimal activity location. For the selected locations, the server simulates staffing and proposes an efficient staffing plan.

[0714] Users access the system using a terminal and enter information about the event, including the target audience, preferred date and time, and budget. The server compares these conditions with forecast data to generate a list of optimal locations and placements.

[0715] Ultimately, the terminal visually displays information obtained from the server and provides the user with suggestions for the optimal venue and staffing arrangements. For example, in the case of a concert held in the city center on a specific date and time, the server indicates the predicted areas where people are likely to gather and programs directions accordingly.

[0716] An example of a prompt message would be: "Generate an optimal venue and staffing plan for an urban concert event based on the following parameters: target audience, soundproofing, accessibility, budget limit, and desired date."

[0717] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0718] Step 1:

[0719] The server collects demographic data from multiple sources. This collection utilizes public transport APIs and mobile device location services. It receives traffic boarding / alighting data and location data as input, and saves this data to a recording medium in real time, preparing the foundational data for selecting potential event locations.

[0720] Step 2:

[0721] The server preprocesses the collected demographic data. Specifically, it imputes missing data, removes outliers, and normalizes the data into a unified format. This process processes the raw data provided as input and generates a clean dataset suitable for analysis as output.

[0722] Step 3:

[0723] The server uses pre-processed data to predict demographic patterns using a pre-trained generative AI model. It accepts normalized demographic data as input and generates predictions of pedestrian flow for specific time periods and regions as output. This facilitates the selection of potential future event locations.

[0724] Step 4:

[0725] Users input event-related conditions into the system via their terminal. For example, they enter target audience attributes, date and time, budget, and required equipment specifications. The entered conditions are sent to a server, where they are used as evaluation criteria for selecting potential venues.

[0726] Step 5:

[0727] The server generates a list of candidate locations by comparing user-provided conditions with predicted demographic data. Specifically, it evaluates the conditions provided as input, selects suitable geographical areas from the database, and creates a list of suitable candidate locations as output.

[0728] Step 6:

[0729] The server performs optimization processing based on the generated list of candidate locations. For each candidate location, it calculates evaluation scores such as cost, accessibility, and predicted number of participants. It receives the list of candidate locations as input, selects the most suitable event venue as output, and then creates an efficient staffing plan for the selected location.

[0730] Step 7:

[0731] The terminal visualizes and presents to the user the optimal venue and staffing plan sent from the server. For example, it displays the visually optimized results on the screen along with map information, providing the user with a concrete event plan. This output allows the user to make a final decision quickly.

[0732] (Application Example 1)

[0733] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0734] Traditional event planning has faced challenges such as the difficulty of selecting the optimal venue and efficiently allocating staff, making it challenging to attract a large audience. Predicting the appropriate date and time for an event was also difficult. This made it difficult to develop strategies necessary for event success, resulting in financial losses and missed opportunities.

[0735] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0736] In this invention, the server includes a function to collect movement data from multiple information sources and store it in a recording device, an information processing function to unify the collected information and remove unnecessary data, and an information analysis function to analyze the information using a learning model and generate movement predictions. This makes it possible to efficiently determine the optimal event location, time, and personnel allocation, and to support operations that increase the success rate.

[0737] An "information gathering device" is a device used to acquire data from multiple information sources.

[0738] An "information processing system" is a system for unifying, analyzing, and optimizing collected information.

[0739] A "recording device" is a device that has a storage function for saving collected data.

[0740] "Information sources" refer to the various media and platforms from which data is collected.

[0741] "Mobility data" refers to information about people's movements and flows, and is a collection of data that is gathered in real time.

[0742] "Standardization" is the process of aligning data from different formats to a certain standard, making it easier to analyze.

[0743] "Unnecessary data" refers to information that has little value in the analysis or decision-making process, or that is considered noise.

[0744] A "learning model" is an algorithm or mathematical model used for data analysis and prediction.

[0745] "Information analysis function" refers to the process of using collected data to obtain predictions and insights for various purposes.

[0746] The "List of Selected Locations" is a collection of information listing potential locations suitable for holding an event.

[0747] "Personnel allocation" refers to the assignment of staff necessary to efficiently carry out an event or task.

[0748] A "smartphone" is a portable communication device with multiple functions, such as displaying and operating information.

[0749] The system for realizing this application consists of an information gathering device, an information processing system, and a recording device. The server collects movement data from multiple information sources and stores it in the recording device. This enables real-time capture of human flow data. The collected data is processed through information processing functions that unify it and remove unnecessary data, making it suitable for analysis.

[0750] Next, the server uses a learning model to analyze the accumulated data. This analysis process generates future movement predictions based on past and present movement data. Users can then use the generated movement predictions to perform simulations for selecting event venues and staffing.

[0751] The optimal suggestions are presented to the user via the terminal. In this process, the server visualizes the selected information and provides it on a display device such as a smartphone. Based on this information, the user can formulate an effective event management plan.

[0752] A concrete example is a retailer planning a special weekend promotional event, who could use this system to determine the optimal store location and time slot. Such prediction-based decisions enable efficient customer attraction.

[0753] An example of a prompt might be: "Based on average foot traffic data from last year's weekend afternoons at 3 PM, predict the times when the most people will gather. Based on that prediction, propose appropriate staffing arrangements to ensure the event's success." This prompt utilizes advanced analysis powered by generative AI models to support event success.

[0754] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0755] Step 1:

[0756] The server collects movement data from multiple sources. Inputs include boarding and alighting information from public transport and location information from mobile devices, and output is stored in a recording device in raw data format. In this step, data is acquired in real time and stored in a format suitable for subsequent processing.

[0757] Step 2:

[0758] The server unifies the collected movement data and removes unnecessary data. The input is the raw data stored in step 1, and the output is data that has been noise-free and formatted into a unified format. Specifically, it filters out redundant data and leaves only the necessary items.

[0759] Step 3:

[0760] The server uses a learning model to analyze unified movement data and generate movement predictions. The input is the data generated in step 2, and the output is the predicted pedestrian flow pattern. Machine learning algorithms are applied as data processing to extract future movement patterns.

[0761] Step 4:

[0762] The server generates a list of potential venues based on the event conditions entered by the user. The input is the event details provided by the user (date, time, target, etc.), and the output is a list of potential venues. Specifically, the process includes identifying and listing geographical locations that meet the conditions.

[0763] Step 5:

[0764] The server evaluates candidate locations and selects the optimal event venue. The inputs are the list of candidate locations generated in step 4 and the pedestrian flow patterns from step 3, and the output is the selection result for the optimal location. As a data calculation, an evaluation score is calculated for each candidate location, and the location with the highest score is selected.

[0765] Step 6:

[0766] The server simulates staffing based on the selected locations and generates proposals. The input is the selection result from step 5, and the output is a proposed staffing plan. Specifically, it determines the number of staff according to the scale of the event and simulates the optimal placement pattern.

[0767] Step 7:

[0768] The terminal visualizes the suggestions obtained from the server and presents them to the user. The input is the suggestions from step 6, and the output is visual data displayed in a format that the user can review. In operation, event information and suggestions are displayed on the smartphone application screen, making them easily accessible to the user.

[0769] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0770] This invention combines a system that proposes optimal locations and staffing based on pedestrian flow data to maximize the effectiveness of event hosting with an emotion engine that recognizes user emotions and further enhances the event experience.

[0771] In the system's implementation, the server device first collects pedestrian flow data in real time from multiple data sources and stores it in a database. The collected data is preprocessed to remove noise and create a unified format. Then, a machine learning model is used to analyze the normalized data and generate pedestrian flow predictions for each region. This makes it possible to identify peak times and popular locations in specific areas.

[0772] The user inputs event conditions using a terminal. During this process, the emotion engine analyzes the user's voice and facial expressions to recognize their emotional state at the time of input. For example, if the user expresses joy, this information is incorporated into the system, allowing it to create a list of potential locations that align with the user's expectations. This enables the system to incorporate the user's emotional information into the list of potential locations.

[0773] Furthermore, the server evaluates candidate locations based on the analysis results and user sentiment information, and selects the optimal event location. In this process, sentiment information is reflected in the evaluation score, prioritizing the location that best suits the user's desired experience.

[0774] At the selected event location, the server simulates and generates suggestions for optimal staffing based on crowd flow predictions. The optimized results are presented to the user in a visualized form via a terminal. For example, if the emotion engine detects user anxiety, the system provides a more comfortable experience by suggesting options that avoid congestion.

[0775] This system allows users to receive suggestions based on event conditions while also taking emotions into consideration when preparing for the event.

[0776] The following describes the processing flow.

[0777] Step 1:

[0778] The server collects pedestrian flow data from multiple data sources. Specifically, it utilizes information on public transport usage, location data from smart devices, and social media traffic. This data is ingested into the database in real time.

[0779] Step 2:

[0780] The server preprocesses the collected pedestrian flow data. This includes standardizing the data format and removing outliers. After removing noise, the data is prepared in a format that allows for analysis by machine learning models.

[0781] Step 3:

[0782] The server uses machine learning models to perform analysis and generate predictions of pedestrian flow. These predictions include analysis results such as the number of people staying in a specific area and peak times, allowing for consideration of future pedestrian flow patterns.

[0783] Step 4:

[0784] When a user inputs event conditions via their device, their emotional state is recognized by the emotion engine. The system analyzes the user's facial expressions and voice to obtain emotional data such as joy and anxiety.

[0785] Step 5:

[0786] The server receives event conditions and sentiment data entered by the user and creates a list of optimal event venue candidates. The candidate selection process also incorporates customization based on the user's expectations and emotions.

[0787] Step 6:

[0788] The server calculates an evaluation score based on the list of candidate locations. This evaluation is based on accessibility, cost, and the appropriateness of the location selection according to user sentiment information.

[0789] Step 7:

[0790] The server selects the optimal event location and simulates the optimal staff deployment at that location. Based on the predicted crowd flow, it generates suggestions for the number and placement of staff.

[0791] Step 8:

[0792] The terminal visually presents the user with the optimized event location and staffing arrangements generated by the server. This allows the user to begin concrete event preparations based on the suggestions.

[0793] (Example 2)

[0794] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0795] When organizing an event, selecting the optimal location and appropriately allocating staff are crucial to maximizing participant satisfaction. However, traditional methods often involve manual analysis of travel data and venue selection, which is time-consuming and labor-intensive. Furthermore, selecting the optimal venue while considering participants' emotions presents a challenge.

[0796] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0797] In this invention, the server includes means for acquiring movement information from multiple information sources and storing it in a storage device, means for integrating the acquired movement information and removing unnecessary elements, and means for analyzing the information using a learning algorithm and generating movement predictions for each region. This enables efficient venue selection and staff allocation based on movement information, thereby increasing participant satisfaction. Furthermore, by including emotion analysis means that recognize the user's emotional state by analyzing voice and facial expressions and adjust venue candidates based on this information, it becomes possible to select the optimal venue that takes the user's emotions into consideration.

[0798] A "server" is a computing device that processes data obtained from multiple sources and provides analysis results.

[0799] "Mobility information" refers to data that shows the movement patterns of people and goods in a specific area.

[0800] A "storage device" is a device that has the function of storing data and retrieving and processing that data as needed.

[0801] A "data preparation method" is a system that integrates collected data into a consistent format and processes it to remove unnecessary information.

[0802] A "learning algorithm" is a computational method used to find rules and patterns in large amounts of data and to perform predictions and classifications.

[0803] An "information analysis tool" is a system that performs analysis based on obtained data to generate predictions and insights.

[0804] A "potential venue" is a list of several possible locations that are being considered for holding the event.

[0805] An "emotion analysis system" is a system that analyzes the user's voice and facial expressions to recognize their emotional state.

[0806] An "input / output device" is a device that allows a user to input information and to visually receive information from a computing device.

[0807] This invention is a system that automatically suggests the optimal location and staffing arrangement for an event. The system is configured and used as follows:

[0808] The server first collects movement information in real time from multiple sources. The collected data is stored in the server's storage device. Specifically, it utilizes information from APIs and sensors to collect data such as traffic volume and the usage status of public facilities. Next, the server processes this data using data preparation tools to remove noise and standardize the format. Standard data cleaning techniques are applied at this stage.

[0809] The server uses libraries such as TensorFlow and PyTorch to execute learning algorithms. This allows it to analyze movement data and generate movement predictions for a specific region. Based on the obtained prediction data, it lists potential event locations according to the event conditions set by the user.

[0810] The user inputs event conditions into the system via a terminal. At this time, the terminal analyzes the user's voice and facial expressions using emotion analysis tools to recognize their emotional state. In this step, an emotion engine is used, employing standard voice analysis and facial recognition technologies for emotion recognition.

[0811] Based on user input data and sentiment information, the server evaluates potential event locations and selects the optimal venue. Sentiment information is a crucial element in this selection process. Furthermore, the server simulates the optimal staffing arrangement and generates this as a proposal.

[0812] The terminal visualizes and presents optimized suggestions sent from the server to the user. This includes displaying potential venues on a map and generating heatmaps that predict congestion.

[0813] As a concrete example, consider a scenario where a user wants to find the best location for an art festival scheduled for the following weekend. Taking into account the user's relaxed mood, we can list the best locations that avoid crowds.

[0814] An example of a prompt message might be: "Please suggest the best venues for the art festival scheduled for next weekend. Please list the most suitable locations, taking into account the expected crowd levels and the user's relaxed mood."

[0815] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0816] Step 1:

[0817] The server collects mobility information from multiple sources. Input data includes real-time traffic information from transportation APIs and data on the usage of public facilities. The server retrieves this data via API requests and stores it in storage. The output is a set of accumulated raw data.

[0818] Step 2:

[0819] The server processes the collected movement information. The input is the raw data obtained in step 1. Specifically, it performs tasks such as imputing missing data, removing outliers, and standardizing data formats. Data reliability is improved by using a denoising algorithm. The output is a normalized, high-quality dataset.

[0820] Step 3:

[0821] The server uses a learning algorithm to generate movement predictions from a normalized dataset. The input is the data prepared in step 2. Using machine learning libraries, it models movement patterns for each region by performing time series analysis and clustering. The output is analytical data predicting future human movement.

[0822] Step 4:

[0823] The user inputs event conditions using a terminal. The input data consists of detailed conditions and settings for the event desired by the user. The terminal sends this information to the server, which is then used to evaluate candidate locations. The output is a request from the user interface to the server.

[0824] Step 5:

[0825] The device acquires the user's voice and facial expressions and recognizes their emotional state using emotion analysis. Input consists of real-time acquired voice data and facial imagery. The emotion analysis engine analyzes the tone of the voice and facial features to determine the user's emotions. Output is the recognized emotion information.

[0826] Step 6:

[0827] The server evaluates potential event locations based on event conditions and sentiment information, and selects the optimal event location. The inputs are the pedestrian flow prediction data generated in step 3 and the information obtained in steps 4 and 5. The evaluation model is used to calculate a score for each candidate location, and the most suitable one is selected. The output is the selected optimal event location.

[0828] Step 7:

[0829] The server simulates staff deployment based on the selected venue information. The input is the venue information selected in step 6. The simulation designs the optimal staff deployment plan according to the predicted congestion. The output is the optimized staff deployment plan.

[0830] Step 8:

[0831] The terminal visualizes and presents optimal venue and staffing plans to the user. The input is the suggested content received from the server. The terminal visually displays the data using maps and graphs to make it easy for the user to understand. The output is the visualized information presented to the user.

[0832] (Application Example 2)

[0833] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0834] In recent years, optimal location selection and staffing at events and commercial facilities have become crucial for event success. However, many systems rely solely on predictions based on pedestrian flow data and fail to consider visitor sentiment, making it difficult to optimize the individual user experience. Furthermore, a lack of concrete suggestions for avoiding congestion also hinders a comfortable user experience.

[0835] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0836] In this invention, the server includes means for collecting pedestrian flow information from multiple information sources and storing it in an information aggregate, means for preprocessing the collected information to normalize it and remove unnecessary information, and means for analyzing the information using a machine learning model and generating pedestrian flow predictions. This makes it possible to propose the optimal event location and worker placement while taking into account the user's emotional information, and to provide a comfortable event experience that avoids congestion.

[0837] An "information processing device" is a computer system that collects data from multiple sources, analyzes it, and processes it.

[0838] An "information collection" is a database that stores collected data and manages it so that it can be used as needed.

[0839] "Information preprocessing means" refers to methods for processing collected data to convert it into a format that is easy to analyze, such as removing unnecessary information or standardizing the data format.

[0840] A "machine learning model" is an algorithm or method used to analyze data, find patterns, and make predictions.

[0841] An "information analysis tool" is a mechanism for performing analysis based on collected and pre-processed data, according to a specific purpose.

[0842] "Event conditions" refer to information that specifically defines the characteristics and requirements of an event that a user is planning to hold.

[0843] "Emotion recognition means" refers to technologies and methods for recognizing a user's emotional state at a given time by analyzing their facial expressions and voice.

[0844] An "evaluation score" is a numerical indicator that quantifies the extent to which specific conditions are met, generated based on analysis results and user sentiment information.

[0845] The server, acting as an information processing device, collects pedestrian flow information from multiple sources. This includes real-time data from sensors, cameras, and other sources. The collected data is quickly and efficiently de-noised and converted into a unified format using pre-processing tools. At this stage, cloud infrastructure such as Microsoft Azure and Google Cloud can be used.

[0846] After the data is normalized, the server uses a machine learning model to analyze the information and generate pedestrian flow predictions. Here, TensorFlow is used to predict peak times and congestion in specific areas. The analyzed data is stored in an information repository.

[0847] When a user sends event conditions to a server using their device, an emotion recognition mechanism is activated. The device can be, for example, a smartphone or tablet, and its camera and microphone collect the user's facial expressions and voice. This allows Microsoft Azure's emotion analysis service to identify the user's emotional state.

[0848] The server incorporates the analyzed sentiment information into an evaluation score and lists the most suitable candidate locations based on the user's request. Furthermore, if a suggested location is likely to be crowded, it presents alternative options to avoid the crowds based on the sentiment information.

[0849] Finally, the proposed content is visualized on the device and provided to the user. Based on this, the user can determine the optimal event plan and communicate that information to the staff via wireless communication.

[0850] As a concrete example, when an event is scheduled, the system predicts when attendees will be most concentrated and suggests alternative options to alleviate congestion. This results in a more comfortable experience for customers.

[0851] An example of a prompt using a generative AI model is: "Based on the latest customer sentiment data, please come up with suggestions to provide a better experience for customers so they can shop comfortably in the store."

[0852] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0853] Step 1:

[0854] The server collects pedestrian flow information in real time from multiple sources. It receives data from each sensor and camera via an interface and temporarily stores it in an information aggregate. At this stage, the raw data is enormous and may include incomplete information.

[0855] Step 2:

[0856] The server performs information preprocessing on the collected raw data. This process removes noise and formats the data into a consistent format. Data processing is achieved by filtering outliers, imputing missing values, and standardizing the data. The output is a clean dataset in a format suitable for analysis.

[0857] Step 3:

[0858] The server uses normalized data to perform analysis with machine learning models. Leveraging TensorFlow, it applies pedestrian flow pattern recognition and prediction models to the analysis. It predicts peak times from the input data and identifies when and where congestion occurs. The output is generated as a pedestrian flow prediction report in text and graph formats.

[0859] Step 4:

[0860] The user inputs event conditions from their device. This information is sent to the server and includes the starting point and scheduled date and time. The user's facial expressions and voice are recorded using the device's microphone and camera. Audio and image data that provide hints about emotions are acquired as input.

[0861] Step 5:

[0862] The server uses emotion recognition tools to analyze the user's emotional state from their facial expressions and voice. It generates an emotion score using the Microsoft Azure Emotion Analysis Service. This involves analyzing facial expression features and voice tone to identify emotions. The output is an evaluation score, quantified as emotion information.

[0863] Step 6:

[0864] The server incorporates sentiment scores into its evaluation and generates a list of candidate locations combined with crowd flow predictions. Based on this combination, it selects the optimal event location. Specifically, if a user's sentiment of happiness is high, options that meet that request are prioritized. The output is a ranked list of recommended event locations.

[0865] Step 7:

[0866] The server provides options to avoid congestion. Based on sentiment information and crowd flow predictions, it proposes a plan to avoid congestion. In this process, it generates recommendations for alternative routes and different time slots. The output is congestion avoidance suggestions.

[0867] Step 8:

[0868] The user visually reviews the suggestions generated by the server via their terminal. Visualized data of optimal locations and staff deployments are displayed on the terminal's screen. Based on this, the user makes a final decision. As output, confirmation information regarding the optimal location selected by the user is obtained.

[0869] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0870] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0871] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0872] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0873] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0874] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0875] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0876] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0877] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0878] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0879] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0880] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0881] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0882] 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.

[0883] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0884] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0885] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0886] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0887] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0888] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0889] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0890] The following is further disclosed regarding the embodiments described above.

[0891] (Claim 1)

[0892] A server device connected to a data acquisition device,

[0893] A means of collecting pedestrian flow data from multiple data sources and storing it in a database,

[0894] A data preprocessing means for normalizing collected data and removing noise,

[0895] A data analysis method that uses machine learning models to analyze data and generate pedestrian flow predictions,

[0896] A means for generating a list of candidate locations based on event conditions entered by the user,

[0897] A method for evaluating candidate sites using analysis results and selecting the optimal event location,

[0898] A system that includes means for simulating staff deployment based on selected locations and generating proposals.

[0899] (Claim 2)

[0900] The system according to claim 1, which visualizes and presents to the user on a terminal the optimal event location and staffing arrangement suggestions obtained from the server device.

[0901] (Claim 3)

[0902] The system according to claim 1, in which a user uses a terminal to review proposals generated by a server device and prepares to hold an event based on the selected information.

[0903] "Example 1"

[0904] (Claim 1)

[0905] An information processing device connected to a data supply device,

[0906] A means for collecting demographic data from multiple sources and storing it on a recording medium,

[0907] Information preprocessing means for organizing collected data and removing errors,

[0908] An information analysis means that uses a learning algorithm to analyze information and generate demographic forecasts,

[0909] A means for generating a list of candidate regions based on the activity conditions entered by the user,

[0910] A method for evaluating candidate areas using analysis results and selecting the optimal activity location,

[0911] A system that includes means for simulating personnel deployment based on selected locations and generating proposals.

[0912] (Claim 2)

[0913] The system according to claim 1, which visualizes the optimal activity location and personnel allocation suggestions obtained from the information processing device on a display device and presents them to the user.

[0914] (Claim 3)

[0915] The system according to claim 1, wherein the user uses a display device to confirm a proposal generated by an information processing device and prepares for an activity based on the selected information.

[0916] "Application Example 1"

[0917] (Claim 1)

[0918] An information processing system connected to an information gathering device,

[0919] The function of collecting movement data from multiple sources and storing it in a recording device,

[0920] Information processing function that unifies collected information and removes unnecessary data,

[0921] Information analysis function that uses a learning model to analyze information and generate movement predictions,

[0922] A function that generates a list of selected locations based on the event conditions entered by the user,

[0923] The system uses the analysis results to evaluate the selected locations and select the most suitable venue for the event.

[0924] A function that simulates staffing arrangements based on the selected location and generates proposals,

[0925] A function that suggests the optimal time for holding events,

[0926] A system that includes a function to provide an application that supports event management using smartphones.

[0927] (Claim 2)

[0928] The system according to claim 1, which visualizes and presents to the user the optimal location, time, and staffing arrangements for an event obtained from an information processing system using a display device.

[0929] (Claim 3)

[0930] The system according to claim 1, wherein a user uses a display device to confirm a proposal generated by an information processing system and prepares for holding an event based on the selected information.

[0931] "Example 2 of combining an emotion engine"

[0932] (Claim 1)

[0933] A computing device connected to a storage device for storing movement information collected from multiple sources,

[0934] A means for acquiring movement information from multiple sources and storing it in a storage device,

[0935] A data preparation method that integrates acquired movement information and removes unnecessary elements,

[0936] An information analysis means that uses a learning algorithm to analyze information and generate regional movement predictions,

[0937] A means for generating a list of potential venues based on conditions set by the user,

[0938] A method for evaluating potential host locations based on analysis results and determining the optimal host location,

[0939] A means of planning staffing arrangements and generating proposals based on the selected venue,

[0940] A system that includes an emotion analysis means to recognize the user's emotional state by analyzing their voice and facial expressions, and to adjust potential venues based on this information.

[0941] (Claim 2)

[0942] The system according to claim 1, which visualizes the optimal venue and personnel allocation suggestions obtained from a computing device using an input / output device and presents them to the user.

[0943] (Claim 3)

[0944] The system according to claim 1, wherein a user uses an input / output device to review proposals generated by a computing device and proceeds with preparations for holding an event based on the selected information.

[0945] "Application example 2 when combining with an emotional engine"

[0946] (Claim 1)

[0947] An information processing device connected to a data collection device,

[0948] A means for collecting human flow information from multiple sources and storing it in an information aggregate,

[0949] Information preprocessing means for normalizing collected information and removing unnecessary information,

[0950] An information analysis means that uses a machine learning model to analyze information and generate a prediction of pedestrian flow,

[0951] A means for generating a list of candidate locations based on event conditions entered by the user,

[0952] A method for evaluating candidate sites using analysis results and selecting the optimal location for the event,

[0953] A means for simulating worker placement based on selected locations and generating proposals,

[0954] An emotion recognition means that analyzes the user's facial expressions and voice to recognize their emotional state,

[0955] A means of reflecting emotional information in evaluation scores and providing the optimal event location,

[0956] A system that includes means of presenting options to avoid crowds based on emotional information.

[0957] (Claim 2)

[0958] The system according to claim 1, which visualizes and presents to the user the optimal event location and worker placement suggestions obtained from the information processing device on a terminal.

[0959] (Claim 3)

[0960] The system according to claim 1, wherein the user uses a terminal to confirm a proposal generated by an information processing device and prepares for an event based on the selected information. [Explanation of symbols]

[0961] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A system including a server device connected to a data acquisition device, A means of collecting pedestrian flow data from multiple data sources and storing it in a database, A data preprocessing means for normalizing collected data and removing noise, A data analysis method that uses machine learning models to analyze data and generate pedestrian flow predictions, A means for generating a list of candidate locations based on event conditions entered by the user, A method for evaluating candidate sites using analysis results and selecting the optimal event location, A system that includes means for simulating staff deployment based on selected locations and generating proposals.

2. The system according to claim 1, which visualizes and presents to the user on a terminal the optimal event location and staffing arrangement suggested by the server device.

3. The system according to claim 1, in which a user uses a terminal to review proposals generated by a server device and prepares to hold an event based on the selected information.

Images