system

Abstract

We provide the system. [Solution] Means of collecting data from past events, A means of preprocessing the collected data and converting it into features, A means of creating a machine learning model using preprocessed data and verifying the analysis results, A method for predicting ticket prices based on new event information, A means to output predicted pricing and adjust it as needed, A means to finalize the pricing and save it in the system, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a 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 character of the chatbot, 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 small and medium-sized events, there is a lack of effective means to fully utilize past event performance information (such as weather, seat layout, sales performance, etc.) to set optimal seat prices. In the conventional method, price setting is often carried out based on the type of event and basic data, making it difficult to maximize revenue. In addition, there is also a lack of effective interaction means for users to intuitively adjust price setting and determine optimal price setting. Against this background, there is a demand for a seat price setting system that utilizes past data to maximize revenue even in small and medium-sized events.

Means for Solving the Problems

[0005] The present invention solves the above problems with a system that includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, and means for finalizing the pricing and saving it in the system. Specifically, the data from past events includes weather, seating layout, and sales performance, and these are collected as data. The collected data is converted into features, and analysis is performed using a machine learning model (such as a regression model or random forest) to achieve highly accurate price predictions. Users can input new event information and check and adjust the optimal pricing in real time. With this system, even small and medium-sized events can effectively utilize past data and set optimal seating prices to maximize revenue.

[0006] "Data collection methods" refer to the means of obtaining information such as past event types, weather conditions, seating layouts, and sales performance from a database.

[0007] "Data preprocessing means" refers to methods for converting collected data into a format suitable for analysis, such as imputing missing values, removing duplicate data, and normalizing the data.

[0008] A "feature transformation means" is a means for transforming preprocessed data into analyzable features (such as numerical data).

[0009] A "machine learning model creation method" refers to a means for creating an analytical model using machine learning algorithms such as regression models or random forests, based on preprocessed data.

[0010] "Methods for verifying analysis results" refer to means for verifying the accuracy of a machine learning model using methods such as cross-validation, and confirming the effectiveness of the model.

[0011] A "ticket price prediction method" is a method for inputting information about a new event and using a machine learning model to predict the optimal ticket price.

[0012] A "price setting output method" is a means of displaying the predicted ticket price to the user and adjusting it as needed.

[0013] A "price setting confirmation method" is a means of saving the price setting confirmed by the user to the system and recording it in the database.

[0014] "Weather" refers to the weather conditions (sunny, cloudy, rainy, temperature, etc.) at the time of past events.

[0015] "Seating layout" refers to the arrangement of seats and the structure of areas within an event venue.

[0016] "Sales performance" refers to the ticket sales status of past events (number of tickets sold, sales rate, revenue, etc.).

[0017] A "machine learning model" is a statistical model used to make predictions or classifications based on data, and includes regression models and random forests. [Brief explanation of the drawing]

[0018] [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] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the language used in the following description will be described.

[0021] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single 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), and APU (Accelerated Processing Unit).

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] 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).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing.

[0040] Data acquisition methods

[0041] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[0042] Data preprocessing means

[0043] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[0044] Feature transformation means

[0045] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[0046] Machine learning model creation methods

[0047] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[0048] Means for verifying analysis results

[0049] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[0050] Ticket price prediction method

[0051] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[0052] Price setting output method

[0053] The server outputs the predicted pricing to the user's terminal. The user can review the displayed pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[0054] Pricing confirmation method

[0055] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[0056] Specific example

[0057] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as "Summer Festivals," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[0058] This system allows for the use of historical data even for small and medium-sized events, enabling optimal seat pricing to maximize revenue.

[0059] The following describes the processing flow.

[0060] Step 1:

[0061] Users input past event data into their terminals. Specifically, they input information such as the type of event, weather, seating layout, and sales performance.

[0062] Step 2:

[0063] The server collects the input data and extracts relevant historical event information from the database. It then issues SQL queries to the database to retrieve the necessary data.

[0064] Step 3:

[0065] The server preprocesses the collected data. Specifically, this involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity.

[0066] Step 4:

[0067] The server converts pre-processed data into features. Categorical data such as weather and seating layout is converted into numerical data, making it a format that can be applied to machine learning models.

[0068] Step 5:

[0069] The server uses the data, which has been converted into features, to create machine learning models. Here, the Scikit-learn library is used to train regression models and random forests.

[0070] Step 6:

[0071] The server validates the accuracy of the machine learning model. During this process, cross-validation is used to check the model's effectiveness, and hyperparameter tuning is performed as needed.

[0072] Step 7:

[0073] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (date, time, location, expected weather, etc.).

[0074] Step 8:

[0075] The server uses a machine learning model to predict seat prices based on newly entered event information. It calculates the optimal price while considering its relevance to past data.

[0076] Step 9:

[0077] The server outputs the predicted price to the terminal. The user can review this price setting and adjust it manually if necessary. The displayed price is, for example, 5500 yen for the standing area and 4500 yen for the seated area.

[0078] Step 10:

[0079] The user confirms the final pricing on their device. The adjusted price is finalized at this point.

[0080] Step 11:

[0081] The server saves the finalized pricing information to a database. This data is recorded for future event management and analysis.

[0082] Step 12:

[0083] The server integrates with the ticket sales system and reflects the published pricing. It uses an API to automatically transfer pricing information to the ticket sales system.

[0084] The above is a detailed explanation of the 12 steps in the program's processing flow. This system enables optimal seat pricing that maximizes revenue, even for small to medium-sized events, by utilizing past data.

[0085] (Example 1)

[0086] 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."

[0087] For small and medium-sized events, there is a need for a way to effectively utilize past event data and automate and optimize seat pricing to maximize revenue. However, current methods often rely heavily on manual settings, making efficient and accurate pricing difficult. Therefore, a system is needed that uses data analysis and prediction based on past event data to optimize pricing for new events.

[0088] 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.

[0089] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting the settings as necessary, means for finalizing the pricing and saving it in the system, and means for coordinating with the ticket sales system to reflect the settings. This makes it possible to effectively utilize past data and accurately and efficiently set optimal seat prices.

[0090] "Past event data" refers to information about past events, including weather conditions, seating arrangements, and sales figures.

[0091] "Means of collecting data" refers to methods for obtaining information about past events from databases, etc., and these are executed via a server.

[0092] "Preprocessing methods" refer to techniques used to maintain the integrity of collected data and convert it into a format that is easy to analyze, such as imputing missing values, removing duplicate data, and normalizing the data.

[0093] "Means of converting to features" refers to means of converting preprocessed data into a format that can be processed by a machine learning model, and includes, for example, converting it into numerical data.

[0094] "Means for creating machine learning models" refers to methods for training and creating machine learning models such as predictive models and decision trees using preprocessed data and features.

[0095] "Means for verifying analysis results" refer to methods such as cross-validation and hyperparameter tuning to confirm the accuracy and reliability of the created machine learning model.

[0096] "A method for predicting ticket prices based on new event information" refers to a method for inputting information about new events into a machine learning model to calculate the optimal ticket price.

[0097] "A means of outputting predicted pricing and allowing users to adjust the settings as needed" refers to a means of displaying predicted pricing on the user's device and allowing the user to adjust the pricing as needed.

[0098] "Means for finalizing and saving the final pricing" refers to the means by which the user's finalized pricing is saved in a database.

[0099] "Methods for linking with the ticket sales system to reflect settings" refers to methods of linking with the ticket sales system using APIs or similar means to reflect the finalized pricing settings in the ticket sales system.

[0100] This invention relates to a system for optimizing seat pricing for small and medium-sized events. This system collects, preprocesses, and features-transforms historical event data, creates a machine learning model based on it, verifies the analysis results, predicts seat pricing for new events, and provides a series of processes for users to confirm, adjust, and finalize the predicted pricing.

[0101] Data acquisition methods

[0102] The server collects past event data. Specifically, the server connects to a database and retrieves past event information (weather conditions, seating arrangements, sales performance, etc.). Users grant permission to access the database through their terminals and enter the necessary information.

[0103] Specific example

[0104] When a user plans a new event called "Winter Music Festival," they access the database from their device and input data from past "Summer Festivals" and "Autumn Music Festivals." The server collects this data and stores it in the database.

[0105] Data preprocessing means

[0106] The data collected by the server is preprocessed. The Pandas library is used to impute missing values, remove duplicate data, and normalize the data.

[0107] Specific example

[0108] The server uses the Pandas library to impute missing weather data, for example, by using the mean. It also removes duplicate event data and performs normalization to maintain data consistency.

[0109] Feature transformation means

[0110] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it a format that is easy to apply to the model.

[0111] Specific example

[0112] The server quantifies weather information, assigning values ​​such as 1 for "sunny" and 0 for "rainy," and combines this with other sales performance data to generate features.

[0113] Machine learning model creation methods

[0114] The server uses the transformed features to create a machine learning model. It then trains regression models and decision trees using the Scikit-learn library.

[0115] Specific example

[0116] The server uses the Scikit-learn library to train a regression model based on past event data and create a sales forecast model for new events.

[0117] Means for verifying analysis results

[0118] The server verifies the model's effectiveness using methods such as cross-validation. If the accuracy is insufficient, hyperparameter tuning is performed to improve the model's accuracy.

[0119] Specific example

[0120] The server splits the model into training and test data and verifies the prediction accuracy through cross-validation. If the accuracy is less than 80%, the hyperparameters are adjusted and training is performed again.

[0121] Ticket price prediction method

[0122] The server uses a machine learning model to predict the optimal ticket price based on the new event information. The user enters the new event information from their device.

[0123] Specific example

[0124] Users input information about the "Winter Music Festival" from their terminals, and the server inputs that information into a machine learning model to calculate the optimal seating price. For example, it might predict that the standing area price is 5,500 yen and the seated area price is 4,500 yen.

[0125] Price setting output method

[0126] The server outputs the predicted charges to the user's terminal. The user reviews the displayed charges and adjusts them as needed.

[0127] Specific example

[0128] The user checks the pricing displayed on their device and sets the standing area to 5500 yen and the seated area to 4500 yen.

[0129] Pricing confirmation method

[0130] The user finalizes the pricing, and the server saves that information to a database. The server then integrates with the ticket sales system to reflect the published pricing.

[0131] Specific example

[0132] The user confirms the final settings, and the server saves those settings to the database. Next, the server uses an API to connect with the ticket sales system and publish the set price.

[0133] Examples of prompts to input into a generative AI model

[0134] "Please enter the data needed to predict pricing for the new event. For example, past event names, weather conditions, sales performance, etc."

[0135] This system allows even small and medium-sized events to effectively utilize past data and accurately and efficiently set optimal seating rates.

[0136] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0137] Step 1: Data Collection

[0138] The server collects past event data. Specifically, the server connects to a database and retrieves event information such as weather conditions, seating arrangements, and sales performance. Users grant permission to access the database through their terminals and enter the necessary information. The input data includes event name, location, date and time, weather, seating layout, and sales performance. The server then saves the collected data to the database.

[0139] Step 2: Data Preprocessing

[0140] The server preprocesses the collected data. Specifically, it uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The input data is the raw data collected in step 1, and the output data is the preprocessed, clean data. The server imputes missing values ​​with the mean and removes duplicate data. Normalization maintains data consistency.

[0141] Step 3: Feature transformation

[0142] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it easier to apply to the model. The input data is preprocessed clean data, and the output data is numerical or encoded feature data. For example, weather information is converted to "sunny → 1" and "rainy → 0".

[0143] Step 4: Create a machine learning model

[0144] The server creates a machine learning model using the transformed features. Specifically, it trains regression models and decision trees using the Scikit-learn library. The input data is data that has been transformed into features, and the output data is the trained machine learning model. The server uses the regression model to create a sales forecast model based on past event data.

[0145] Step 5: Verification of analysis results

[0146] The server validates the model's effectiveness using methods such as cross-validation. Specifically, it splits the data, checks the prediction accuracy on test data, and improves the model's accuracy through hyperparameter tuning. The input data is a trained machine learning model, and the output data is the evaluation result of the prediction accuracy. The server performs cross-validation, and adjusts the hyperparameters if the prediction accuracy is less than 80%.

[0147] Step 6: Predicting Ticket Prices

[0148] The server uses a machine learning model to predict the optimal ticket price based on new event information. The user inputs new event information from their terminal. The input data is the new event information and the trained model, and the output data is the predicted pricing. The user inputs information about the "Winter Music Festival," and the server calculates the ticket price based on that. For example, it predicts a standing area price of 5500 yen and a seated area price of 4500 yen.

[0149] Step 7: Output pricing settings

[0150] The server outputs the predicted pricing to the user's terminal. Specifically, it displays the predicted pricing on the user's terminal, allowing the user to review and adjust it. The input data is the predicted pricing, and the output data is the adjustable pricing displayed to the user. The user reviews the pricing displayed on their terminal and sets the standing area to 5500 yen and the seated area to 4500 yen.

[0151] Step 8: Confirm pricing

[0152] The user finalizes the pricing, and the server saves this information to the database. The server then integrates with the ticket sales system to reflect the published pricing. The input data is the finalized pricing, while the output data is the pricing saved in the database and its reflection in the sales system. The user finalizes the settings on their terminal, and the server saves these settings to the database. The server then uses an API to integrate with the ticket sales system and publishes the set prices.

[0153] (Application Example 1)

[0154] 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."

[0155] For small to medium-sized events, setting efficient and optimal seating rates is a crucial challenge for organizers. To maximize revenue, it is necessary to accurately predict pricing based on past event data, and furthermore, to smoothly present this information to users at physical locations and allow them to make appropriate adjustments.

[0156] 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.

[0157] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for finalizing the pricing and saving it to the system, and means for displaying the collected data and predicted pricing using a smartphone application used in physical stores, allowing the user to make adjustments and final settings. This makes it possible to set optimal seat prices to maximize revenue by utilizing past event data.

[0158] "Past event data" refers to information about events that were actually held in the past, including data such as weather, seating layout, and sales performance.

[0159] "Means of data collection" refers to the processes and technical means for accumulating information about past events on a server.

[0160] "Methods for preprocessing data and converting it into features" refer to the process of preparing collected data into an analyzable format by imputing missing values, removing duplicate data, performing numerical conversions, etc.

[0161] A "machine learning model" is an algorithm and computational model used to make predictions about future events based on historically collected data.

[0162] "Means for verifying analysis results" refer to methods and processes for evaluating the accuracy and effectiveness of results generated by machine learning models.

[0163] "Methods for predicting ticket prices" refer to the processes and technical means for predicting optimal seat prices based on new event information.

[0164] "Means for outputting pricing and adjusting it as needed" refers to an interface and technical means for displaying predicted pricing to the user and allowing manual adjustments as necessary.

[0165] "Means for finalizing pricing and saving it to the system" refers to the technical means for saving the final pricing information confirmed by the user to a database.

[0166] A "smartphone application" is software that runs on a smartphone and allows users to input past event data, check price prediction results, and adjust and finalize price settings.

[0167] A "physical store" refers to a store that exists in a physical location and is a place where events are held.

[0168] This invention relates to a smartphone application and its backend structure for streamlining event management at physical stores. The system includes a series of processes: collecting historical event data, performing data preprocessing and feature transformation, creating machine learning models, and predicting ticket prices for new events. The results of this process are presented to the user through the smartphone application, allowing the user to adjust and finalize the pricing.

[0169] The server accesses a database to retrieve past event information as a means of collecting historical event data. This information includes weather, seating layout, and sales performance. Users complete data collection by entering the necessary data through a smartphone application and sending it to the server.

[0170] Since the collected data is not suitable for analysis in its raw form, the server uses data preprocessing to impute missing values, remove duplicate data, and normalize the data. This preprocessing uses data preprocessing libraries such as Pandas and NumPy. Subsequently, feature transformation is used to convert categorical data, such as weather, into numerical data.

[0171] Based on the preprocessed and feature-transformed data, the server creates a machine learning model. This model uses Scikit-learn's regression model or random forest. The accuracy of the analysis results of the created model is checked using validation methods such as cross-validation.

[0172] When new event information is entered, the server uses a machine learning model to predict ticket prices. These predictions are presented to the user via a smartphone application, allowing them to review the pricing and make adjustments as needed. These adjustments can be made through the user interface.

[0173] The finalized pricing is saved to a database by the server and reflected in the ticket sales system. This saving and updating of information is automated using an API.

[0174] For example, if a user plans a new event called "Winter Music Festival," the process would proceed as follows: The user inputs data from a past event, such as "Summer Festival," from their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[0175] Example of a prompt:

[0176] To predict the optimal ticket price for the new event "Winter Music Festival 2023," please use data from the past "Summer Festival 2022" (weather: sunny, seating layout: standing, sales: 5000 tickets) to determine the price.

[0177] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0178] Step 1:

[0179] The user enters information about a new event into a smartphone application.

[0180] Input: Basic information for the new event (e.g., event name, date, venue, seating layout, etc.)

[0181] Output: The input event information is sent to the server.

[0182] Specific operation: When a user enters event details into an input form on their smartphone and presses the "Submit" button, the data is sent to the server.

[0183] Step 2:

[0184] The server collects past event data from the database.

[0185] Input: Conditions of past events (e.g., dates of similar events, weather, seating layout, etc.)

[0186] Output: Historical event dataset

[0187] Specific operation: The server queries the database and retrieves past event data that matches the specified conditions.

[0188] Step 3:

[0189] The server preprocesses the data it collects.

[0190] Input: Collected historical event data

[0191] Output: A normalized dataset with missing values ​​imputed and duplicate data removed.

[0192] Specific operation: Using the Pandas and Numpy libraries, the system performs mean imputation of missing values, removes duplicate data, and normalizes the data using MinMaxScaler.

[0193] Step 4:

[0194] The server converts the pre-processed data into features.

[0195] Input: Preprocessed dataset

[0196] Output: Feature data converted to a format applicable to machine learning models.

[0197] Specific operation: One-hot encoding is performed to convert categorical data (e.g., weather) into numerical data.

[0198] Step 5:

[0199] The server creates a machine learning model and verifies the analysis results.

[0200] Input: Dataset converted into features

[0201] Output: Trained machine learning model and validation results

[0202] Specific operation: Use Scikit-learn to train a regression model or a random forest model, and then evaluate the accuracy using cross-validation.

[0203] Step 6:

[0204] The server predicts ticket prices based on new event information.

[0205] Input: New event information and a trained machine learning model

[0206] Output: Predicted ticket price

[0207] Specific operation: Input the features of the new event into the model and calculate the predicted price.

[0208] Step 7:

[0209] The server outputs the predicted pricing to the smartphone application.

[0210] Input: Predicted ticket price

[0211] Output: Pricing displayed on the smartphone application

[0212] Specific operation: The server sends pricing data to the application via the API and displays it in the user interface.

[0213] Step 8:

[0214] Users can check the pricing settings through the application and make adjustments as needed.

[0215] Input: Pricing displayed on the smartphone application

[0216] Output: User-adjusted pricing

[0217] Specific operation: The user checks the pricing settings through the interface and adjusts them using sliders or numerical input.

[0218] Step 9:

[0219] The user finalizes the pricing, and the server saves it.

[0220] Input: User-adjusted pricing

[0221] Output: Final pricing settings stored in the database

[0222] Specific operation: After the user presses the "Confirm" button, the server saves the pricing settings to the database.

[0223] Step 10:

[0224] The server reflects the final pricing in the ticket sales system.

[0225] Input: Final pricing saved in the database

[0226] Output: Pricing reflected in the ticket sales system

[0227] Specific action: The server uses the API to update the pricing settings of the ticket sales system.

[0228] 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.

[0229] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and ultimately provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, this invention provides interaction tailored to the user's emotional state by incorporating an emotion engine that recognizes the user's emotions.

[0230] Data acquisition methods

[0231] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[0232] Data preprocessing means

[0233] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[0234] Feature transformation means

[0235] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[0236] Machine learning model creation methods

[0237] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[0238] Means for verifying analysis results

[0239] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[0240] Ticket price prediction method

[0241] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[0242] Price setting output method

[0243] The server outputs the predicted pricing to the user's terminal. The user can review this pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[0244] Pricing confirmation method

[0245] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[0246] Embedding an emotion engine

[0247] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions. As the user interacts with the device, the emotion engine monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display more detailed explanations and provide support to help the user feel at ease.

[0248] Specific example

[0249] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict ticket prices for the new event. The pricing is output to the device, and the user adjusts it as needed to finalize the pricing. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's feelings.

[0250] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[0251] The following describes the processing flow.

[0252] Step 1:

[0253] Users input past event data into their devices. Specifically, they input information such as the type of event, date and time, weather, seating layout, and sales performance.

[0254] Step 2:

[0255] The server collects past event data entered by users from the database. It issues SQL queries to retrieve the necessary data.

[0256] Step 3:

[0257] The server preprocesses the collected data. This preprocessing includes imputing missing values, removing duplicate data, and normalizing the data. For example, it uses the Pandas library to execute a function that imputes missing values.

[0258] Step 4:

[0259] The server converts pre-processed data into features. Categorical data such as weather is converted into numerical data and made into an analyzable format. Specifically, one-hot encoding and label encoding are applied.

[0260] Step 5:

[0261] The server creates a machine learning model based on the data converted into features. The Scikit-learn library is used to train regression models and random forests. The dataset is split into training and test data for model training.

[0262] Step 6:

[0263] The server validates the accuracy of the machine learning model using cross-validation. It calculates model performance metrics (RMSE, R^2, etc.) to confirm the model's effectiveness. Furthermore, it tunes hyperparameters as needed.

[0264] Step 7:

[0265] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (scheduled date and time, expected weather, seating layout, etc.).

[0266] Step 8:

[0267] The server uses a machine learning model to predict the optimal ticket price based on newly entered event information. It also considers past event data and analyzes the balance of supply and demand to calculate the price.

[0268] Step 9:

[0269] The server outputs the predicted charges to the terminal. The user can review these charges and manually adjust them through the interface provided by the server.

[0270] Step 10:

[0271] The emotion engine monitors the user's emotions. When a user checks the pricing, the emotion engine analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions.

[0272] Step 11:

[0273] The emotion engine dynamically adjusts the interface based on the user's emotional state. For example, if the user is feeling anxious, it will display additional explanations or support messages.

[0274] Step 12:

[0275] The user confirms the final pricing on their device. If the pricing is adjusted by the user, that information is also sent to the server.

[0276] Step 13:

[0277] The server saves confirmed pricing information to the database. New pricing information is recorded and used for subsequent event analysis and management.

[0278] Step 14:

[0279] The server collaborates with the ticket sales system to reflect the published fare settings. Utilizing the API, it transfers the new fare setting information to the ticket sales system and automatically applies it.

[0280] The above is the specific processing flow of the system combined with the emotion engine. With this system, while recognizing the user's emotions in real time, by setting the optimal seat fares for small and medium-sized events, it is expected to maximize revenue and improve the user experience.

[0281] (Example 2)

[0282] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0283] In optimizing seat fare settings using past event data, it is required to improve the accuracy of data analysis while providing interactions according to the user's emotions. However, in conventional systems, it was difficult to meet these requirements while performing multi-dimensional analysis of data and real-time emotion analysis of users.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into feature quantities, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket fares based on new event information, means for outputting the predicted fare settings and adjusting them as necessary, means for determining the final fare settings and storing them in the system, and means for recognizing the user's emotions and dynamically adjusting the user interface. Thereby, it becomes possible to set fares with high accuracy based on past data and dynamically adjust the interface according to the user's emotions.

[0285] "Data of past events" refers to all information related to events previously carried out, including elements such as weather conditions, seat arrangements, sales history, etc.

[0286] "Data preprocessing" refers to a series of operations to organize the collected data into a form suitable for analysis, including processes such as missing value imputation, duplicate data removal, normalization, etc.

[0287] "Converting to feature quantities" refers to the step of changing raw data into an analyzable form, such as operations like converting weather into numerical data.

[0288] "Machine learning model" refers to an algorithm that finds patterns from data and enables future predictions and classifications, including regression algorithms and decision tree algorithms.

[0289] "Verification of analysis results" refers to the process of evaluating how accurate the generated machine learning model is, and methods such as cross-validation are used.

[0290] "Predicting ticket prices" refers to the process of calculating the optimal price based on new event information, making use of past data and machine learning models.

[0291] "Outputting and adjusting price settings" refers to the function of displaying the predicted price on the user interface and allowing the user to change the price as needed.

[0292] "Finalizing and saving price settings" refers to the process of recording the finally determined ticket price in the system's database.

[0293] "Recognizing emotions" refers to the function of reading the emotional state from the user's facial expressions, voice tones, gestures, etc. and analyzing it in real time.

[0294] "Dynamically adjusting the user interface" refers to the process of adapting the system's display and operation methods in real time according to the user's emotional state.

[0295] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, the invention provides interaction tailored to the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[0296] Data acquisition methods

[0297] The server collects data from past events. This data includes weather conditions, seating arrangements, and sales history. Users access the database through their terminals, retrieve the necessary information from the database, and send it to the server. The server integrates this data and stores it as a dataset for analysis.

[0298] Data preprocessing means

[0299] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. For example, if weather data is missing, it is imputed using historical mean values.

[0300] Feature transformation means

[0301] The server converts the preprocessed data into analyzable features. For example, it converts weather data into a format that is easy to apply to machine learning models, such as quantifying "sunny = 1" and "rainy = 0". This conversion allows for the integration and analysis of multiple factors.

[0302] Machine learning model creation methods

[0303] The server generates a machine learning model based on the data converted into feature quantities. For creating this model, Scikit-learn is used to train regression algorithms and decision tree algorithms. This model learns patterns from past data and makes predictions by applying them to data of new events.

[0304] Analysis result verification means

[0305] The server confirms the effectiveness of the model using cross-validation and other verification methods. The data is split to confirm the reliability of the analysis results and used as test data. Hyperparameter tuning is performed as necessary to improve the accuracy of the model.

[0306] Ticket price prediction means

[0307] The server predicts the optimal ticket price based on new event information. The user inputs new event information such as "Winter Music Festival" through the terminal, and the server calculates the price based on that information. In this process, past event data and the generated AI model are utilized to make highly accurate predictions.

[0308] Price setting output means

[0309] The server outputs the predicted price setting to the user's terminal. The user checks this price setting using the terminal and adjusts the price as necessary. For example, set the standing area price for the "Winter Music Festival" to 5500 yen and the seating area price to 4500 yen.

[0310] Price setting confirmation means

[0311] The user finalizes the price setting, and the server saves that information in the database. After that, the server utilizes the API to cooperate with the ticket sales system and reflects the announced price setting.

[0312] Embedding an emotion engine

[0313] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body movements to recognize emotions. As the user interacts with the device, the server monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display a detailed explanation and an encouraging message to support the user.

[0314] Specific example

[0315] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a generative AI model and predicts the ticket price for the new event based on that model. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's emotions.

[0316] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[0317] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0318] Step 1: Data Collection

[0319] The server collects historical event data. The user, via their terminal, instructs the server to retrieve this data from the database. The server executes SQL queries to the database, retrieving information such as weather conditions, seating arrangements, and sales history. This data is then sent to the server for integration.

[0320] Input: Event name submitted by the user (e.g., "Summer Festival", "Spring Carnival")

[0321] Output: Integrated data on weather conditions, seating arrangements, and sales history.

[0322] Specific actions:

[0323] The user enters the event name, such as "Summer Festival" or "Spring Carnival," from their device.

[0324] The server uses SQL queries to retrieve relevant information from the database.

[0325] The server integrates the acquired information and saves it as a dataset for analysis.

[0326] Step 2: Data Preprocessing

[0327] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The collected data is then converted into a format suitable for analysis.

[0328] Input: Integrated event data

[0329] Output: Preprocessed data

[0330] Specific actions:

[0331] The server creates a dataframe using the Pandas library.

[0332] Missing data is imputed with historical averages.

[0333] Remove duplicate data and maintain consistent data.

[0334] The data is normalized to a range of 0 to 1 and converted into an analyzable format.

[0335] Step 3: Feature transformation

[0336] The server converts the preprocessed data into analyzable features. This feature conversion includes processes such as converting categorical data into numerical data. For example, weather data is converted to "sunny = 1" and "rainy = 0".

[0337] Input: Preprocessed data

[0338] Output: Data converted into features

[0339] Specific actions:

[0340] Convert categorical data such as weather data into numerical data.

[0341] The server uses Pandas to generate multiple features.

[0342] Step 4: Create a machine learning model

[0343] The server generates machine learning models using the data converted into features. It uses Scikit-learn to train regression and decision tree algorithms. The models learn patterns from past data and make predictions with new event data.

[0344] Input: Data converted into features

[0345] Output: Trained machine learning model

[0346] Specific actions:

[0347] Splitting data into training and test phases using the scikit-learn library

[0348] Train random forest and regression models and evaluate their prediction accuracy.

[0349] Hyperparameter tuning as needed

[0350] Step 5: Verification of analysis results

[0351] The server uses cross-validation and other verification methods to verify the effectiveness of the generated model. The reliability of the analysis results is evaluated, and the model is re-evaluated using test data to confirm its accuracy.

[0352] Input: Trained machine learning model

[0353] Output: Validated models and their accuracy evaluation

[0354] Specific actions:

[0355] The server divides the data into k subsets and performs cross-validation.

[0356] Train the model on each subset and test it on the remaining subsets.

[0357] The model's accuracy and reliability are verified on average, and tuning is performed if necessary.

[0358] Step 6: Predicting Ticket Prices

[0359] The server uses a generative AI model to predict the optimal ticket price based on new event information. When a user enters new event information from their device, the server calculates the price based on that information.

[0360] Input: New event information (e.g., "Winter Music Festival")

[0361] Output: Predicted ticket price

[0362] Specific actions:

[0363] Users enter new event information via their devices.

[0364] The server inputs new information into an AI model to predict the cost.

[0365] We predict the standing area ticket price will be 5500 yen and the seated area ticket price will be 4500 yen.

[0366] Step 7: Output pricing settings

[0367] The server outputs the predicted charges to the user's terminal. The user reviews these charges and adjusts them as needed.

[0368] Input: Predicted ticket price

[0369] Output: Adjustable pricing

[0370] Specific actions:

[0371] The server sends the predicted charges information to the user's terminal.

[0372] The user checks the price and adjusts the standing area price, for example, from 5500 yen to 5000 yen.

[0373] Step 8: Confirm pricing

[0374] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the pricing changes.

[0375] Input: Final adjusted pricing

[0376] Output: Finalized pricing and the database reflecting it.

[0377] Specific actions:

[0378] The user finalizes the pricing.

[0379] The server stores pricing information in the database.

[0380] The server uses an API to connect with the ticket sales system.

[0381] Step 9: Integrating the Emotion Engine

[0382] The server uses an emotion engine to analyze sensor information that recognizes the user's emotions. As the user operates the device, it monitors their emotions in real time and dynamically adjusts the interface based on that information.

[0383] Input: User's facial expressions, voice tone, and body movements

[0384] Output: Dynamic adjustment of the user interface

[0385] Specific actions:

[0386] The server analyzes the user's facial expressions and voice tone using sensors.

[0387] When a user feels anxious, detailed help information and encouraging messages are displayed.

[0388] This enables highly accurate pricing based on historical data and dynamic adjustments to the interface in response to user emotions.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0391] For small to medium-sized events, it is difficult to determine optimal seating rates by utilizing past event data. Furthermore, the pricing process often lacks support that considers user emotions, leading to user anxiety and questions. Therefore, a system is needed that allows for efficient and reassuring pricing.

[0392] 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. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted price setting and adjusting it as necessary, means for determining the final price setting and saving it to the system, means for recognizing the user's emotions in real time, and means for dynamically adjusting the interface according to the user's emotions. This enables optimal seat pricing using past event data, as well as support that responds to the user's emotions.

[0393] "Past event data" refers to a collection of information about events held in the past, specifically including data such as weather conditions, seating layout, and sales performance.

[0394] "Data preprocessing" is the process of converting collected data into a format suitable for analysis, and includes tasks such as imputing missing values, removing duplicate data, and normalizing the data.

[0395] "Features" are attributes or properties of data used to apply to machine learning models, and are used to predict new information.

[0396] A "machine learning model" is a type of algorithm that learns data trends and patterns from large amounts of data and uses that learning to make predictions and classifications on new data.

[0397] A "ticket price prediction method" is a method for calculating the optimal seat price based on new event information, and it uses a machine learning model to make predictions.

[0398] "User emotion recognition means" refers to technology that analyzes the user's facial expressions, voice tone, body gestures, etc., to recognize the user's emotional state in real time.

[0399] "Dynamic interface adjustment" means changing the system's interface and display content in real time according to the user's emotional state.

[0400] "Verification of analysis results" refers to evaluating the analysis results using test data in order to confirm the performance and effectiveness of a machine learning model.

[0401] "Finalizing pricing" refers to the process of determining the final pricing and saving that information in the system.

[0402] This invention is a system that optimizes seat pricing for small and medium-sized events by utilizing past event data, and further recognizes user emotions in real time to dynamically adjust the interface. This system is implemented using specific hardware and software.

[0403] 1. System Configuration

[0404] The server includes means that have the following functions:

[0405] Data collection method: Collect past event data. This includes weather conditions, seating layout, sales performance, etc.

[0406] Data preprocessing means: The collected data is preprocessed to impute missing values, remove duplicate data, and normalize the data.

[0407] Feature transformation means: Converts preprocessed data into analyzable features.

[0408] Machine learning model creation method: Create a machine learning model based on features and use a regression model or random forest.

[0409] Method for verifying analysis results: The accuracy of the analysis results is verified using cross-validation.

[0410] Ticket price prediction method: Predicts the optimal ticket price based on new event information.

[0411] Pricing output method: Predicts the pricing and allows the user to adjust it.

[0412] Pricing confirmation method: Confirm the final pricing and save it in the system.

[0413] Emotion recognition means: Recognizes the user's emotions in real time using a camera or voice input device.

[0414] Dynamic interface adjustment means: The interface is dynamically adjusted based on information obtained by the emotion recognition means.

[0415] 2. Hardware and software required for implementation

[0416] Specific examples of the hardware and software used are as follows:

[0417] Hardware: Server, camera, microphone, user terminal (smartphone or PC)

[0418] Software: Python, Pandas, Scikit-learn, EmotionEngine (a virtual emotion recognition module)

[0419] 3. Data processing and data calculation

[0420] The server processes the data in the following order:

[0421] Data collection: Retrieve past event data from the database.

[0422] Data preprocessing: Use the Pandas library to impute missing values ​​and normalize the collected data.

[0423] Feature transformation: Converts data such as weather and seating layout into numerical data.

[0424] Machine learning model creation: Create a machine learning model using Scikit-learn.

[0425] Model validation: Evaluate the accuracy of the model using cross-validation.

[0426] Price Prediction: Input new event information and use a machine learning model to predict the optimal price.

[0427] Emotion Recognition: EmotionEngine is used to analyze user emotions using data obtained from the camera and microphone.

[0428] Dynamic interface adjustment: The interface changes according to the user's emotional state.

[0429] 4. Specific examples and prompt statements

[0430] For example, when a user plans a "winter music festival," they input data from past events such as "summer festivals" into the system. The server then predicts the optimal seating price for the new event through processes such as data collection, data preprocessing, feature transformation, and machine learning model creation. The predicted pricing is then presented to the user, allowing them to confidently set prices based on sentiment recognition.

[0431] Example of a prompt:

[0432] Based on past event data, please determine the optimal seating price for a winter music festival. Please provide detailed information, including weather, seating layout, and sales performance. Also, please explain how you can address any concerns users may have.

[0433] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0434] Step 1:

[0435] The server collects historical event data from the database. Specifically, it queries data such as weather conditions, seating layout, and sales performance, and retrieves the results. The input is the query conditions for the event data, and the output is the collected historical event data.

[0436] Step 2:

[0437] The server-collected data is preprocessed using the Pandas library. Specifically, missing value imputation, duplicate data removal, and normalization are performed. The input is the collected event data, and the output is the preprocessed data.

[0438] Step 3:

[0439] The server converts pre-processed data into features. Specifically, it converts data such as weather and seating layout into numerical data. The input is pre-processed data, and the output is data converted into features.

[0440] Step 4:

[0441] The server uses Scikit-learn to create machine learning models. Specifically, it trains them using regression models or random forests. The input is data transformed into features and their corresponding labels, and the output is the trained machine learning model.

[0442] Step 5:

[0443] The server uses cross-validation to validate the model. Specifically, it evaluates the accuracy of the trained model and confirms that the model works correctly. The input is the trained machine learning model and test data, and the output is the model's accuracy evaluation result.

[0444] Step 6:

[0445] The user enters new event information from a terminal. Specifically, the user enters details of the new event (e.g., weather conditions, seating layout, expected sales figures, etc.) into the terminal. The input is the new event information, and the output is the display of the entered event information on the terminal screen.

[0446] Step 7:

[0447] The server predicts ticket prices based on new event information. Specifically, it uses a trained machine learning model to calculate the optimal seat price. The input is the new event information and the trained model, and the output is the predicted ticket price.

[0448] Step 8:

[0449] The server outputs the predicted price to the user's terminal. The input is the predicted ticket price, and the output is the price displayed on the user's terminal.

[0450] Step 9:

[0451] The user reviews the predicted price displayed on their device and makes adjustments as needed. Specifically, the user views the predicted price and changes or modifies it. The input is the predicted price, and the output is the price adjusted by the user.

[0452] Step 10:

[0453] The server saves the final pricing to the system. Specifically, it saves the confirmed pricing to the database and prepares it for integration with the ticket sales system. The input is the final pricing adjusted by the user, and the output is the pricing information stored in the database.

[0454] Step 11:

[0455] The server uses EmotionEngine to recognize the user's emotions in real time. Specifically, it analyzes data acquired from cameras and microphones to determine the user's emotional state. The input is data obtained from cameras and microphones, and the output is the real-time emotion recognition result.

[0456] Step 12:

[0457] The server dynamically adjusts the interface based on the user's emotional state. Specifically, if the user is feeling anxious or confused, the system provides detailed explanations or additional support information. The input is real-time emotion recognition results, and the output is a dynamically adjusted interface.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Second Embodiment]

[0462] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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".

[0474] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing.

[0475] Data acquisition methods

[0476] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[0477] Data preprocessing means

[0478] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[0479] Feature transformation means

[0480] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[0481] Machine learning model creation methods

[0482] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[0483] Means for verifying analysis results

[0484] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[0485] Ticket price prediction method

[0486] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[0487] Price setting output method

[0488] The server outputs the predicted pricing to the user's terminal. The user can review the displayed pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[0489] Pricing confirmation method

[0490] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[0491] Specific example

[0492] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as "Summer Festivals," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[0493] This system allows for the use of historical data even for small and medium-sized events, enabling optimal seat pricing to maximize revenue.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] Users input past event data into their terminals. Specifically, they input information such as the type of event, weather, seating layout, and sales performance.

[0497] Step 2:

[0498] The server collects the input data and extracts relevant historical event information from the database. It then issues SQL queries to the database to retrieve the necessary data.

[0499] Step 3:

[0500] The server preprocesses the collected data. Specifically, this involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity.

[0501] Step 4:

[0502] The server converts pre-processed data into features. Categorical data such as weather and seating layout is converted into numerical data, making it a format that can be applied to machine learning models.

[0503] Step 5:

[0504] The server uses the data, which has been converted into features, to create machine learning models. Here, the Scikit-learn library is used to train regression models and random forests.

[0505] Step 6:

[0506] The server validates the accuracy of the machine learning model. During this process, cross-validation is used to check the model's effectiveness, and hyperparameter tuning is performed as needed.

[0507] Step 7:

[0508] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (date, time, location, expected weather, etc.).

[0509] Step 8:

[0510] The server uses a machine learning model to predict seat prices based on newly entered event information. It calculates the optimal price while considering its relevance to past data.

[0511] Step 9:

[0512] The server outputs the predicted price to the terminal. The user can review this price setting and adjust it manually if necessary. The displayed price is, for example, 5500 yen for the standing area and 4500 yen for the seated area.

[0513] Step 10:

[0514] The user confirms the final pricing on their device. The adjusted price is finalized at this point.

[0515] Step 11:

[0516] The server saves the finalized pricing information to a database. This data is recorded for future event management and analysis.

[0517] Step 12:

[0518] The server integrates with the ticket sales system and reflects the published pricing. It uses an API to automatically transfer pricing information to the ticket sales system.

[0519] The above is a detailed explanation of the 12 steps in the program's processing flow. This system enables optimal seat pricing that maximizes revenue, even for small to medium-sized events, by utilizing past data.

[0520] (Example 1)

[0521] 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."

[0522] For small and medium-sized events, there is a need for a way to effectively utilize past event data and automate and optimize seat pricing to maximize revenue. However, current methods often rely heavily on manual settings, making efficient and accurate pricing difficult. Therefore, a system is needed that uses data analysis and prediction based on past event data to optimize pricing for new events.

[0523] 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.

[0524] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting the settings as necessary, means for finalizing the pricing and saving it in the system, and means for coordinating with the ticket sales system to reflect the settings. This makes it possible to effectively utilize past data and accurately and efficiently set optimal seat prices.

[0525] "Past event data" refers to information about past events, including weather conditions, seating arrangements, and sales figures.

[0526] "Means of collecting data" refers to methods for obtaining information about past events from databases, etc., and these are executed via a server.

[0527] "Preprocessing methods" refer to techniques used to maintain the integrity of collected data and convert it into a format that is easy to analyze, such as imputing missing values, removing duplicate data, and normalizing the data.

[0528] "Means of converting to features" refers to means of converting preprocessed data into a format that can be processed by a machine learning model, and includes, for example, converting it into numerical data.

[0529] "Means for creating machine learning models" refers to methods for training and creating machine learning models such as predictive models and decision trees using preprocessed data and features.

[0530] "Means for verifying analysis results" refer to methods such as cross-validation and hyperparameter tuning to confirm the accuracy and reliability of the created machine learning model.

[0531] "A method for predicting ticket prices based on new event information" refers to a method for inputting information about new events into a machine learning model to calculate the optimal ticket price.

[0532] "A means of outputting predicted pricing and allowing users to adjust the settings as needed" refers to a means of displaying predicted pricing on the user's device and allowing the user to adjust the pricing as needed.

[0533] "Means for finalizing and saving the final pricing" refers to the means by which the user's finalized pricing is saved in a database.

[0534] "Methods for linking with the ticket sales system to reflect settings" refers to methods of linking with the ticket sales system using APIs or similar means to reflect the finalized pricing settings in the ticket sales system.

[0535] This invention relates to a system for optimizing seat pricing for small and medium-sized events. This system collects, preprocesses, and features-transforms historical event data, creates a machine learning model based on it, verifies the analysis results, predicts seat pricing for new events, and provides a series of processes for users to confirm, adjust, and finalize the predicted pricing.

[0536] Data acquisition methods

[0537] The server collects past event data. Specifically, the server connects to a database and retrieves past event information (weather conditions, seating arrangements, sales performance, etc.). Users grant permission to access the database through their terminals and enter the necessary information.

[0538] Specific example

[0539] When a user plans a new event called "Winter Music Festival," they access the database from their device and input data from past "Summer Festivals" and "Autumn Music Festivals." The server collects this data and stores it in the database.

[0540] Data preprocessing means

[0541] The data collected by the server is preprocessed. The Pandas library is used to impute missing values, remove duplicate data, and normalize the data.

[0542] Specific example

[0543] The server uses the Pandas library to impute missing weather data, for example, by using the mean. It also removes duplicate event data and performs normalization to maintain data consistency.

[0544] Feature transformation means

[0545] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it a format that is easy to apply to the model.

[0546] Specific example

[0547] The server quantifies weather information, assigning values ​​such as 1 for "sunny" and 0 for "rainy," and combines this with other sales performance data to generate features.

[0548] Machine learning model creation methods

[0549] The server uses the transformed features to create a machine learning model. It then trains regression models and decision trees using the Scikit-learn library.

[0550] Specific example

[0551] The server uses the Scikit-learn library to train a regression model based on past event data and create a sales forecast model for new events.

[0552] Means for verifying analysis results

[0553] The server verifies the model's effectiveness using methods such as cross-validation. If the accuracy is insufficient, hyperparameter tuning is performed to improve the model's accuracy.

[0554] Specific example

[0555] The server splits the model into training and test data and verifies the prediction accuracy through cross-validation. If the accuracy is less than 80%, the hyperparameters are adjusted and training is performed again.

[0556] Ticket price prediction method

[0557] The server uses a machine learning model to predict the optimal ticket price based on the new event information. The user enters the new event information from their device.

[0558] Specific example

[0559] Users input information about the "Winter Music Festival" from their terminals, and the server inputs that information into a machine learning model to calculate the optimal seating price. For example, it might predict that the standing area price is 5,500 yen and the seated area price is 4,500 yen.

[0560] Price setting output method

[0561] The server outputs the predicted charges to the user's terminal. The user reviews the displayed charges and adjusts them as needed.

[0562] Specific example

[0563] The user checks the pricing displayed on their device and sets the standing area to 5500 yen and the seated area to 4500 yen.

[0564] Pricing confirmation method

[0565] The user finalizes the pricing, and the server saves that information to a database. The server then integrates with the ticket sales system to reflect the published pricing.

[0566] Specific example

[0567] The user confirms the final settings, and the server saves those settings to the database. Next, the server uses an API to connect with the ticket sales system and publish the set price.

[0568] Examples of prompts to input into a generative AI model

[0569] "Please enter the data needed to predict pricing for the new event. For example, past event names, weather conditions, sales performance, etc."

[0570] This system allows even small and medium-sized events to effectively utilize past data and accurately and efficiently set optimal seating rates.

[0571] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0572] Step 1: Data Collection

[0573] The server collects past event data. Specifically, the server connects to a database and retrieves event information such as weather conditions, seating arrangements, and sales performance. Users grant permission to access the database through their terminals and enter the necessary information. The input data includes event name, location, date and time, weather, seating layout, and sales performance. The server then saves the collected data to the database.

[0574] Step 2: Data Preprocessing

[0575] The server preprocesses the collected data. Specifically, it uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The input data is the raw data collected in step 1, and the output data is the preprocessed, clean data. The server imputes missing values ​​with the mean and removes duplicate data. Normalization maintains data consistency.

[0576] Step 3: Feature transformation

[0577] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it easier to apply to the model. The input data is preprocessed clean data, and the output data is numerical or encoded feature data. For example, weather information is converted to "sunny → 1" and "rainy → 0".

[0578] Step 4: Create a machine learning model

[0579] The server creates a machine learning model using the transformed features. Specifically, it trains regression models and decision trees using the Scikit-learn library. The input data is data that has been transformed into features, and the output data is the trained machine learning model. The server uses the regression model to create a sales forecast model based on past event data.

[0580] Step 5: Verification of analysis results

[0581] The server validates the model's effectiveness using methods such as cross-validation. Specifically, it splits the data, checks the prediction accuracy on test data, and improves the model's accuracy through hyperparameter tuning. The input data is a trained machine learning model, and the output data is the evaluation result of the prediction accuracy. The server performs cross-validation, and adjusts the hyperparameters if the prediction accuracy is less than 80%.

[0582] Step 6: Predicting Ticket Prices

[0583] The server uses a machine learning model to predict the optimal ticket price based on new event information. The user inputs new event information from their terminal. The input data is the new event information and the trained model, and the output data is the predicted pricing. The user inputs information about the "Winter Music Festival," and the server calculates the ticket price based on that. For example, it predicts a standing area price of 5500 yen and a seated area price of 4500 yen.

[0584] Step 7: Output pricing settings

[0585] The server outputs the predicted pricing to the user's terminal. Specifically, it displays the predicted pricing on the user's terminal, allowing the user to review and adjust it. The input data is the predicted pricing, and the output data is the adjustable pricing displayed to the user. The user reviews the pricing displayed on their terminal and sets the standing area to 5500 yen and the seated area to 4500 yen.

[0586] Step 8: Confirm pricing

[0587] The user finalizes the pricing, and the server saves this information to the database. The server then integrates with the ticket sales system to reflect the published pricing. The input data is the finalized pricing, while the output data is the pricing saved in the database and its reflection in the sales system. The user finalizes the settings on their terminal, and the server saves these settings to the database. The server then uses an API to integrate with the ticket sales system and publishes the set prices.

[0588] (Application Example 1)

[0589] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0590] For small to medium-sized events, setting efficient and optimal seating rates is a crucial challenge for organizers. To maximize revenue, it is necessary to accurately predict pricing based on past event data, and furthermore, to smoothly present this information to users at physical locations and allow them to make appropriate adjustments.

[0591] 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.

[0592] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for finalizing the pricing and saving it to the system, and means for displaying the collected data and predicted pricing using a smartphone application used in physical stores, allowing the user to make adjustments and final settings. This makes it possible to set optimal seat prices to maximize revenue by utilizing past event data.

[0593] "Past event data" refers to information about events that were actually held in the past, including data such as weather, seating layout, and sales performance.

[0594] "Means of data collection" refers to the processes and technical means for accumulating information about past events on a server.

[0595] "Methods for preprocessing data and converting it into features" refer to the process of preparing collected data into an analyzable format by imputing missing values, removing duplicate data, performing numerical conversions, etc.

[0596] A "machine learning model" is an algorithm and computational model used to make predictions about future events based on historically collected data.

[0597] "Means for verifying analysis results" refer to methods and processes for evaluating the accuracy and effectiveness of results generated by machine learning models.

[0598] "Methods for predicting ticket prices" refer to the processes and technical means for predicting optimal seat prices based on new event information.

[0599] "Means for outputting pricing and adjusting it as needed" refers to an interface and technical means for displaying predicted pricing to the user and allowing manual adjustments as necessary.

[0600] "Means for finalizing pricing and saving it to the system" refers to the technical means for saving the final pricing information confirmed by the user to a database.

[0601] A "smartphone application" is software that runs on a smartphone and allows users to input past event data, check price prediction results, and adjust and finalize price settings.

[0602] A "physical store" refers to a store that exists in a physical location and is a place where events are held.

[0603] This invention relates to a smartphone application and its backend structure for streamlining event management at physical stores. The system includes a series of processes: collecting historical event data, performing data preprocessing and feature transformation, creating machine learning models, and predicting ticket prices for new events. The results of this process are presented to the user through the smartphone application, allowing the user to adjust and finalize the pricing.

[0604] The server accesses a database to retrieve past event information as a means of collecting historical event data. This information includes weather, seating layout, and sales performance. Users complete data collection by entering the necessary data through a smartphone application and sending it to the server.

[0605] Since the collected data is not suitable for analysis in its raw form, the server uses data preprocessing to impute missing values, remove duplicate data, and normalize the data. This preprocessing uses data preprocessing libraries such as Pandas and NumPy. Subsequently, feature transformation is used to convert categorical data, such as weather, into numerical data.

[0606] Based on the preprocessed and feature-transformed data, the server creates a machine learning model. This model uses Scikit-learn's regression model or random forest. The accuracy of the analysis results of the created model is checked using validation methods such as cross-validation.

[0607] When new event information is entered, the server uses a machine learning model to predict ticket prices. These predictions are presented to the user via a smartphone application, allowing them to review the pricing and make adjustments as needed. These adjustments can be made through the user interface.

[0608] The finalized pricing is saved to a database by the server and reflected in the ticket sales system. This saving and updating of information is automated using an API.

[0609] For example, if a user plans a new event called "Winter Music Festival," the process would proceed as follows: The user inputs data from a past event, such as "Summer Festival," from their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[0610] Example of a prompt:

[0611] To predict the optimal ticket price for the new event "Winter Music Festival 2023," please use data from the past "Summer Festival 2022" (weather: sunny, seating layout: standing, sales: 5000 tickets) to determine the price.

[0612] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0613] Step 1:

[0614] The user enters information about a new event into a smartphone application.

[0615] Input: Basic information for the new event (e.g., event name, date, venue, seating layout, etc.)

[0616] Output: The input event information is sent to the server.

[0617] Specific operation: When a user enters event details into an input form on their smartphone and presses the "Submit" button, the data is sent to the server.

[0618] Step 2:

[0619] The server collects past event data from the database.

[0620] Input: Conditions of past events (e.g., dates of similar events, weather, seating layout, etc.)

[0621] Output: Historical event dataset

[0622] Specific operation: The server queries the database and retrieves past event data that matches the specified conditions.

[0623] Step 3:

[0624] The server preprocesses the data it collects.

[0625] Input: Collected historical event data

[0626] Output: A normalized dataset with missing values ​​imputed and duplicate data removed.

[0627] Specific operation: Using the Pandas and Numpy libraries, the system performs mean imputation of missing values, removes duplicate data, and normalizes the data using MinMaxScaler.

[0628] Step 4:

[0629] The server converts the pre-processed data into features.

[0630] Input: Preprocessed dataset

[0631] Output: Feature data converted to a format applicable to machine learning models.

[0632] Specific operation: One-hot encoding is performed to convert categorical data (e.g., weather) into numerical data.

[0633] Step 5:

[0634] The server creates a machine learning model and verifies the analysis results.

[0635] Input: Dataset converted into features

[0636] Output: Trained machine learning model and validation results

[0637] Specific operation: Use Scikit-learn to train a regression model or a random forest model, and then evaluate the accuracy using cross-validation.

[0638] Step 6:

[0639] The server predicts ticket prices based on new event information.

[0640] Input: New event information and a trained machine learning model

[0641] Output: Predicted ticket price

[0642] Specific operation: Input the features of the new event into the model and calculate the predicted price.

[0643] Step 7:

[0644] The server outputs the predicted pricing to the smartphone application.

[0645] Input: Predicted ticket price

[0646] Output: Pricing displayed on the smartphone application

[0647] Specific operation: The server sends pricing data to the application via the API and displays it in the user interface.

[0648] Step 8:

[0649] Users can check the pricing settings through the application and make adjustments as needed.

[0650] Input: Pricing displayed on the smartphone application

[0651] Output: User-adjusted pricing

[0652] Specific operation: The user checks the pricing settings through the interface and adjusts them using sliders or numerical input.

[0653] Step 9:

[0654] The user finalizes the pricing, and the server saves it.

[0655] Input: User-adjusted pricing

[0656] Output: Final pricing settings stored in the database

[0657] Specific operation: After the user presses the "Confirm" button, the server saves the pricing settings to the database.

[0658] Step 10:

[0659] The server reflects the final pricing in the ticket sales system.

[0660] Input: Final pricing saved in the database

[0661] Output: Pricing reflected in the ticket sales system

[0662] Specific action: The server uses the API to update the pricing settings of the ticket sales system.

[0663] 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.

[0664] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and ultimately provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, this invention provides interaction tailored to the user's emotional state by incorporating an emotion engine that recognizes the user's emotions.

[0665] Data acquisition methods

[0666] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[0667] Data preprocessing means

[0668] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[0669] Feature transformation means

[0670] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[0671] Machine learning model creation methods

[0672] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[0673] Means for verifying analysis results

[0674] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[0675] Ticket price prediction method

[0676] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[0677] Price setting output method

[0678] The server outputs the predicted pricing to the user's terminal. The user can review this pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[0679] Pricing confirmation method

[0680] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[0681] Embedding an emotion engine

[0682] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions. As the user interacts with the device, the emotion engine monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display more detailed explanations and provide support to help the user feel at ease.

[0683] Specific example

[0684] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict ticket prices for the new event. The pricing is output to the device, and the user adjusts it as needed to finalize the pricing. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's feelings.

[0685] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[0686] The following describes the processing flow.

[0687] Step 1:

[0688] Users input past event data into their devices. Specifically, they input information such as the type of event, date and time, weather, seating layout, and sales performance.

[0689] Step 2:

[0690] The server collects past event data entered by users from the database. It issues SQL queries to retrieve the necessary data.

[0691] Step 3:

[0692] The server preprocesses the collected data. This preprocessing includes imputing missing values, removing duplicate data, and normalizing the data. For example, it uses the Pandas library to execute a function that imputes missing values.

[0693] Step 4:

[0694] The server converts pre-processed data into features. Categorical data such as weather is converted into numerical data and made into an analyzable format. Specifically, one-hot encoding and label encoding are applied.

[0695] Step 5:

[0696] The server creates a machine learning model based on the data converted into features. The Scikit-learn library is used to train regression models and random forests. The dataset is split into training and test data for model training.

[0697] Step 6:

[0698] The server validates the accuracy of the machine learning model using cross-validation. It calculates model performance metrics (RMSE, R^2, etc.) to confirm the model's effectiveness. Furthermore, it tunes hyperparameters as needed.

[0699] Step 7:

[0700] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (scheduled date and time, expected weather, seating layout, etc.).

[0701] Step 8:

[0702] The server uses a machine learning model to predict the optimal ticket price based on newly entered event information. It also considers past event data and analyzes the balance of supply and demand to calculate the price.

[0703] Step 9:

[0704] The server outputs the predicted charges to the terminal. The user can review these charges and manually adjust them through the interface provided by the server.

[0705] Step 10:

[0706] The emotion engine monitors the user's emotions. When a user checks the pricing, the emotion engine analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions.

[0707] Step 11:

[0708] The emotion engine dynamically adjusts the interface based on the user's emotional state. For example, if the user is feeling anxious, it will display additional explanations or support messages.

[0709] Step 12:

[0710] The user confirms the final pricing on their device. If the pricing is adjusted by the user, that information is also sent to the server.

[0711] Step 13:

[0712] The server saves confirmed pricing information to the database. New pricing information is recorded and used for subsequent event analysis and management.

[0713] Step 14:

[0714] The server integrates with the ticket sales system to reflect the published pricing. Using an API, new pricing information is automatically transferred to the ticket sales system and applied.

[0715] The above is the specific processing flow of the system that combines the emotion engine. This system is expected to maximize revenue and improve the user experience by recognizing user emotions in real time and setting optimal seating rates for small to medium-sized events.

[0716] (Example 2)

[0717] 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".

[0718] In optimizing seat pricing using past event data, there is a need to improve the accuracy of data analysis while providing user-responsive interactions. However, conventional systems have struggled to meet these requirements while simultaneously performing multidimensional data analysis and real-time user sentiment analysis.

[0719] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for determining the final pricing and saving it to the system, and means for recognizing user emotions and dynamically adjusting the user interface. This enables highly accurate pricing based on past data and dynamic adjustment of the interface in response to user emotions.

[0720] "Past event data" refers to all information about events that have been held in the past, including elements such as weather conditions, seating arrangements, and sales history.

[0721] "Data preprocessing" refers to a series of operations to prepare collected data into a format suitable for analysis, and includes processes such as imputation of missing values, removal of duplicate data, and normalization.

[0722] "Converting to features" refers to the step of changing raw data into an analyzable format, such as converting weather data into numerical data.

[0723] A "machine learning model" refers to an algorithm that finds patterns in data and enables future predictions and classifications, and includes regression algorithms and decision tree algorithms.

[0724] "Verification of analysis results" refers to the process of evaluating how accurate the generated machine learning model is, and methods such as cross-validation are used.

[0725] "Predicting ticket prices" refers to the process of calculating the optimal price based on new event information, utilizing historical data and machine learning models.

[0726] "Outputting and adjusting pricing" refers to a function that displays predicted prices in the user interface, allowing users to change prices as needed.

[0727] "Confirming and saving pricing" refers to the process of recording the final determined ticket price in the system's database.

[0728] "Emotional recognition" refers to a function that reads the user's emotional state from their facial expressions, voice tone, gestures, etc., and analyzes it in real time.

[0729] "Dynamically adjusting the user interface" refers to the process of adapting the system's display and operation methods in real time according to the user's emotional state.

[0730] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, the invention provides interaction tailored to the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[0731] Data acquisition methods

[0732] The server collects data from past events. This data includes weather conditions, seating arrangements, and sales history. Users access the database through their terminals, retrieve the necessary information from the database, and send it to the server. The server integrates this data and stores it as a dataset for analysis.

[0733] Data preprocessing means

[0734] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. For example, if weather data is missing, it is imputed using historical mean values.

[0735] Feature transformation means

[0736] The server converts the preprocessed data into analyzable features. For example, it converts weather data into a format that is easy to apply to machine learning models, such as quantifying "sunny = 1" and "rainy = 0". This conversion allows for the integration and analysis of multiple factors.

[0737] Machine learning model creation methods

[0738] The server generates a machine learning model based on the data converted into features. This model is created using Scikit-learn, training regression and decision tree algorithms. The model learns patterns from past data and applies them to new event data to make predictions.

[0739] Means for verifying analysis results

[0740] The server verifies the model's effectiveness using cross-validation and other validation techniques. The data is split to verify the reliability of the analysis results and used as test data. Hyperparameter tuning is performed as needed to improve the model's accuracy.

[0741] Ticket price prediction method

[0742] The server predicts the optimal ticket price based on new event information. Users input new event information, such as "Winter Music Festival," through their terminals, and the server calculates the price based on that information. In this process, historical event data and generative AI models are utilized to make highly accurate predictions.

[0743] Price setting output method

[0744] The server outputs the predicted pricing to the user's terminal. The user uses the terminal to check this pricing and adjust the prices as needed. For example, the standing area price for the "Winter Music Festival" is set at 5500 yen and the seating area price at 4500 yen.

[0745] Pricing confirmation method

[0746] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the published pricing.

[0747] Embedding an emotion engine

[0748] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body movements to recognize emotions. As the user interacts with the device, the server monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display a detailed explanation and an encouraging message to support the user.

[0749] Specific example

[0750] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a generative AI model and predicts the ticket price for the new event based on that model. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's emotions.

[0751] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1: Data Collection

[0754] The server collects historical event data. The user, via their terminal, instructs the server to retrieve this data from the database. The server executes SQL queries to the database, retrieving information such as weather conditions, seating arrangements, and sales history. This data is then sent to the server for integration.

[0755] Input: Event name submitted by the user (e.g., "Summer Festival", "Spring Carnival")

[0756] Output: Integrated data on weather conditions, seating arrangements, and sales history.

[0757] Specific actions:

[0758] The user enters the event name, such as "Summer Festival" or "Spring Carnival," from their device.

[0759] The server uses SQL queries to retrieve relevant information from the database.

[0760] The server integrates the acquired information and saves it as a dataset for analysis.

[0761] Step 2: Data Preprocessing

[0762] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The collected data is then converted into a format suitable for analysis.

[0763] Input: Integrated event data

[0764] Output: Preprocessed data

[0765] Specific actions:

[0766] The server creates a dataframe using the Pandas library.

[0767] Missing data is imputed with historical averages.

[0768] Remove duplicate data and maintain consistent data.

[0769] The data is normalized to a range of 0 to 1 and converted into an analyzable format.

[0770] Step 3: Feature transformation

[0771] The server converts the preprocessed data into analyzable features. This feature conversion includes processes such as converting categorical data into numerical data. For example, weather data is converted to "sunny = 1" and "rainy = 0".

[0772] Input: Preprocessed data

[0773] Output: Data converted into features

[0774] Specific actions:

[0775] Convert categorical data such as weather data into numerical data.

[0776] The server uses Pandas to generate multiple features.

[0777] Step 4: Create a machine learning model

[0778] The server generates machine learning models using the data converted into features. It uses Scikit-learn to train regression and decision tree algorithms. The models learn patterns from past data and make predictions with new event data.

[0779] Input: Data converted into features

[0780] Output: Trained machine learning model

[0781] Specific actions:

[0782] Splitting data into training and test phases using the scikit-learn library

[0783] Train random forest and regression models and evaluate their prediction accuracy.

[0784] Hyperparameter tuning as needed

[0785] Step 5: Verification of analysis results

[0786] The server uses cross-validation and other verification methods to verify the effectiveness of the generated model. The reliability of the analysis results is evaluated, and the model is re-evaluated using test data to confirm its accuracy.

[0787] Input: Trained machine learning model

[0788] Output: Validated models and their accuracy evaluation

[0789] Specific actions:

[0790] The server divides the data into k subsets and performs cross-validation.

[0791] Train the model on each subset and test it on the remaining subsets.

[0792] The model's accuracy and reliability are verified on average, and tuning is performed if necessary.

[0793] Step 6: Predicting Ticket Prices

[0794] The server uses a generative AI model to predict the optimal ticket price based on new event information. When a user enters new event information from their device, the server calculates the price based on that information.

[0795] Input: New event information (e.g., "Winter Music Festival")

[0796] Output: Predicted ticket price

[0797] Specific actions:

[0798] Users enter new event information via their devices.

[0799] The server inputs new information into an AI model to predict the cost.

[0800] We predict the standing area ticket price will be 5500 yen and the seated area ticket price will be 4500 yen.

[0801] Step 7: Output pricing settings

[0802] The server outputs the predicted charges to the user's terminal. The user reviews these charges and adjusts them as needed.

[0803] Input: Predicted ticket price

[0804] Output: Adjustable pricing

[0805] Specific actions:

[0806] The server sends the predicted charges information to the user's terminal.

[0807] The user checks the price and adjusts the standing area price, for example, from 5500 yen to 5000 yen.

[0808] Step 8: Confirm pricing

[0809] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the pricing changes.

[0810] Input: Final adjusted pricing

[0811] Output: Finalized pricing and the database reflecting it.

[0812] Specific actions:

[0813] The user finalizes the pricing.

[0814] The server stores pricing information in the database.

[0815] The server uses an API to connect with the ticket sales system.

[0816] Step 9: Integrating the Emotion Engine

[0817] The server uses an emotion engine to analyze sensor information that recognizes the user's emotions. As the user operates the device, it monitors their emotions in real time and dynamically adjusts the interface based on that information.

[0818] Input: User's facial expressions, voice tone, and body movements

[0819] Output: Dynamic adjustment of the user interface

[0820] Specific actions:

[0821] The server analyzes the user's facial expressions and voice tone using sensors.

[0822] When a user feels anxious, detailed help information and encouraging messages are displayed.

[0823] This enables highly accurate pricing based on historical data and dynamic adjustments to the interface in response to user emotions.

[0824] (Application Example 2)

[0825] 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."

[0826] For small to medium-sized events, it is difficult to determine optimal seating rates by utilizing past event data. Furthermore, the pricing process often lacks support that considers user emotions, leading to user anxiety and questions. Therefore, a system is needed that allows for efficient and reassuring pricing.

[0827] 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. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted price setting and adjusting it as necessary, means for determining the final price setting and saving it to the system, means for recognizing the user's emotions in real time, and means for dynamically adjusting the interface according to the user's emotions. This enables optimal seat pricing using past event data, as well as support that responds to the user's emotions.

[0828] "Past event data" refers to a collection of information about events held in the past, specifically including data such as weather conditions, seating layout, and sales performance.

[0829] "Data preprocessing" is the process of converting collected data into a format suitable for analysis, and includes tasks such as imputing missing values, removing duplicate data, and normalizing the data.

[0830] "Features" are attributes or properties of data used to apply to machine learning models, and are used to predict new information.

[0831] A "machine learning model" is a type of algorithm that learns data trends and patterns from large amounts of data and uses that learning to make predictions and classifications on new data.

[0832] A "ticket price prediction method" is a method for calculating the optimal seat price based on new event information, and it uses a machine learning model to make predictions.

[0833] "User emotion recognition means" refers to technology that analyzes the user's facial expressions, voice tone, body gestures, etc., to recognize the user's emotional state in real time.

[0834] "Dynamic interface adjustment" means changing the system's interface and display content in real time according to the user's emotional state.

[0835] "Verification of analysis results" refers to evaluating the analysis results using test data in order to confirm the performance and effectiveness of a machine learning model.

[0836] "Finalizing pricing" refers to the process of determining the final pricing and saving that information in the system.

[0837] This invention is a system that optimizes seat pricing for small and medium-sized events by utilizing past event data, and further recognizes user emotions in real time to dynamically adjust the interface. This system is implemented using specific hardware and software.

[0838] 1. System Configuration

[0839] The server includes means that have the following functions:

[0840] Data collection method: Collect past event data. This includes weather conditions, seating layout, sales performance, etc.

[0841] Data preprocessing means: The collected data is preprocessed to impute missing values, remove duplicate data, and normalize the data.

[0842] Feature transformation means: Converts preprocessed data into analyzable features.

[0843] Machine learning model creation method: Create a machine learning model based on features and use a regression model or random forest.

[0844] Method for verifying analysis results: The accuracy of the analysis results is verified using cross-validation.

[0845] Ticket price prediction method: Predicts the optimal ticket price based on new event information.

[0846] Pricing output method: Predicts the pricing and allows the user to adjust it.

[0847] Pricing confirmation method: Confirm the final pricing and save it in the system.

[0848] Emotion recognition means: Recognizes the user's emotions in real time using a camera or voice input device.

[0849] Dynamic interface adjustment means: The interface is dynamically adjusted based on information obtained by the emotion recognition means.

[0850] 2. Hardware and software required for implementation

[0851] Specific examples of the hardware and software used are as follows:

[0852] Hardware: Server, camera, microphone, user terminal (smartphone or PC)

[0853] Software: Python, Pandas, Scikit-learn, EmotionEngine (a virtual emotion recognition module)

[0854] 3. Data processing and data calculation

[0855] The server processes the data in the following order:

[0856] Data collection: Retrieve past event data from the database.

[0857] Data preprocessing: Use the Pandas library to impute missing values ​​and normalize the collected data.

[0858] Feature transformation: Converts data such as weather and seating layout into numerical data.

[0859] Machine learning model creation: Create a machine learning model using Scikit-learn.

[0860] Model validation: Evaluate the accuracy of the model using cross-validation.

[0861] Price Prediction: Input new event information and use a machine learning model to predict the optimal price.

[0862] Emotion Recognition: EmotionEngine is used to analyze user emotions using data obtained from the camera and microphone.

[0863] Dynamic interface adjustment: The interface changes according to the user's emotional state.

[0864] 4. Specific examples and prompt statements

[0865] For example, when a user plans a "winter music festival," they input data from past events such as "summer festivals" into the system. The server then predicts the optimal seating price for the new event through processes such as data collection, data preprocessing, feature transformation, and machine learning model creation. The predicted pricing is then presented to the user, allowing them to confidently set prices based on sentiment recognition.

[0866] Example of a prompt:

[0867] Based on past event data, please determine the optimal seating price for a winter music festival. Please provide detailed information, including weather, seating layout, and sales performance. Also, please explain how you can address any concerns users may have.

[0868] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0869] Step 1:

[0870] The server collects historical event data from the database. Specifically, it queries data such as weather conditions, seating layout, and sales performance, and retrieves the results. The input is the query conditions for the event data, and the output is the collected historical event data.

[0871] Step 2:

[0872] The server-collected data is preprocessed using the Pandas library. Specifically, missing value imputation, duplicate data removal, and normalization are performed. The input is the collected event data, and the output is the preprocessed data.

[0873] Step 3:

[0874] The server converts pre-processed data into features. Specifically, it converts data such as weather and seating layout into numerical data. The input is pre-processed data, and the output is data converted into features.

[0875] Step 4:

[0876] The server uses Scikit-learn to create machine learning models. Specifically, it trains them using regression models or random forests. The input is data transformed into features and their corresponding labels, and the output is the trained machine learning model.

[0877] Step 5:

[0878] The server uses cross-validation to validate the model. Specifically, it evaluates the accuracy of the trained model and confirms that the model works correctly. The input is the trained machine learning model and test data, and the output is the model's accuracy evaluation result.

[0879] Step 6:

[0880] The user enters new event information from a terminal. Specifically, the user enters details of the new event (e.g., weather conditions, seating layout, expected sales figures, etc.) into the terminal. The input is the new event information, and the output is the display of the entered event information on the terminal screen.

[0881] Step 7:

[0882] The server predicts ticket prices based on new event information. Specifically, it uses a trained machine learning model to calculate the optimal seat price. The input is the new event information and the trained model, and the output is the predicted ticket price.

[0883] Step 8:

[0884] The server outputs the predicted price to the user's terminal. The input is the predicted ticket price, and the output is the price displayed on the user's terminal.

[0885] Step 9:

[0886] The user reviews the predicted price displayed on their device and makes adjustments as needed. Specifically, the user views the predicted price and changes or modifies it. The input is the predicted price, and the output is the price adjusted by the user.

[0887] Step 10:

[0888] The server saves the final pricing to the system. Specifically, it saves the confirmed pricing to the database and prepares it for integration with the ticket sales system. The input is the final pricing adjusted by the user, and the output is the pricing information stored in the database.

[0889] Step 11:

[0890] The server uses EmotionEngine to recognize the user's emotions in real time. Specifically, it analyzes data acquired from cameras and microphones to determine the user's emotional state. The input is data obtained from cameras and microphones, and the output is the real-time emotion recognition result.

[0891] Step 12:

[0892] The server dynamically adjusts the interface based on the user's emotional state. Specifically, if the user is feeling anxious or confused, the system provides detailed explanations or additional support information. The input is real-time emotion recognition results, and the output is a dynamically adjusted interface.

[0893] 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.

[0894] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0895] 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.

[0896] [Third Embodiment]

[0897] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0898] 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.

[0899] 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).

[0900] 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.

[0901] 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.

[0902] 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).

[0903] 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.

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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".

[0909] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing.

[0910] Data acquisition methods

[0911] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[0912] Data preprocessing means

[0913] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[0914] Feature transformation means

[0915] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[0916] Machine learning model creation methods

[0917] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[0918] Means for verifying analysis results

[0919] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[0920] Ticket price prediction method

[0921] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[0922] Price setting output method

[0923] The server outputs the predicted pricing to the user's terminal. The user can review the displayed pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[0924] Pricing confirmation method

[0925] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[0926] Specific example

[0927] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as "Summer Festivals," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[0928] This system allows for the use of historical data even for small and medium-sized events, enabling optimal seat pricing to maximize revenue.

[0929] The following describes the processing flow.

[0930] Step 1:

[0931] Users input past event data into their terminals. Specifically, they input information such as the type of event, weather, seating layout, and sales performance.

[0932] Step 2:

[0933] The server collects the input data and extracts relevant historical event information from the database. It then issues SQL queries to the database to retrieve the necessary data.

[0934] Step 3:

[0935] The server preprocesses the collected data. Specifically, this involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity.

[0936] Step 4:

[0937] The server converts pre-processed data into features. Categorical data such as weather and seating layout is converted into numerical data, making it a format that can be applied to machine learning models.

[0938] Step 5:

[0939] The server uses the data, which has been converted into features, to create machine learning models. Here, the Scikit-learn library is used to train regression models and random forests.

[0940] Step 6:

[0941] The server validates the accuracy of the machine learning model. During this process, cross-validation is used to check the model's effectiveness, and hyperparameter tuning is performed as needed.

[0942] Step 7:

[0943] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (date, time, location, expected weather, etc.).

[0944] Step 8:

[0945] The server uses a machine learning model to predict seat prices based on newly entered event information. It calculates the optimal price while considering its relevance to past data.

[0946] Step 9:

[0947] The server outputs the predicted price to the terminal. The user can review this price setting and adjust it manually if necessary. The displayed price is, for example, 5500 yen for the standing area and 4500 yen for the seated area.

[0948] Step 10:

[0949] The user confirms the final pricing on their device. The adjusted price is finalized at this point.

[0950] Step 11:

[0951] The server saves the finalized pricing information to a database. This data is recorded for future event management and analysis.

[0952] Step 12:

[0953] The server integrates with the ticket sales system and reflects the published pricing. It uses an API to automatically transfer pricing information to the ticket sales system.

[0954] The above is a detailed explanation of the 12 steps in the program's processing flow. This system enables optimal seat pricing that maximizes revenue, even for small to medium-sized events, by utilizing past data.

[0955] (Example 1)

[0956] 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."

[0957] For small and medium-sized events, there is a need for a way to effectively utilize past event data and automate and optimize seat pricing to maximize revenue. However, current methods often rely heavily on manual settings, making efficient and accurate pricing difficult. Therefore, a system is needed that uses data analysis and prediction based on past event data to optimize pricing for new events.

[0958] 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.

[0959] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting the settings as necessary, means for finalizing the pricing and saving it in the system, and means for coordinating with the ticket sales system to reflect the settings. This makes it possible to effectively utilize past data and accurately and efficiently set optimal seat prices.

[0960] "Past event data" refers to information about past events, including weather conditions, seating arrangements, and sales figures.

[0961] "Means of collecting data" refers to methods for obtaining information about past events from databases, etc., and these are executed via a server.

[0962] "Preprocessing methods" refer to techniques used to maintain the integrity of collected data and convert it into a format that is easy to analyze, such as imputing missing values, removing duplicate data, and normalizing the data.

[0963] "Means of converting to features" refers to means of converting preprocessed data into a format that can be processed by a machine learning model, and includes, for example, converting it into numerical data.

[0964] "Means for creating machine learning models" refers to methods for training and creating machine learning models such as predictive models and decision trees using preprocessed data and features.

[0965] "Means for verifying analysis results" refer to methods such as cross-validation and hyperparameter tuning to confirm the accuracy and reliability of the created machine learning model.

[0966] "A method for predicting ticket prices based on new event information" refers to a method for inputting information about new events into a machine learning model to calculate the optimal ticket price.

[0967] "A means of outputting predicted pricing and allowing users to adjust the settings as needed" refers to a means of displaying predicted pricing on the user's device and allowing the user to adjust the pricing as needed.

[0968] "Means for finalizing and saving the final pricing" refers to the means by which the user's finalized pricing is saved in a database.

[0969] "Methods for linking with the ticket sales system to reflect settings" refers to methods of linking with the ticket sales system using APIs or similar means to reflect the finalized pricing settings in the ticket sales system.

[0970] This invention relates to a system for optimizing seat pricing for small and medium-sized events. This system collects, preprocesses, and features-transforms historical event data, creates a machine learning model based on it, verifies the analysis results, predicts seat pricing for new events, and provides a series of processes for users to confirm, adjust, and finalize the predicted pricing.

[0971] Data acquisition methods

[0972] The server collects past event data. Specifically, the server connects to a database and retrieves past event information (weather conditions, seating arrangements, sales performance, etc.). Users grant permission to access the database through their terminals and enter the necessary information.

[0973] Specific example

[0974] When a user plans a new event called "Winter Music Festival," they access the database from their device and input data from past "Summer Festivals" and "Autumn Music Festivals." The server collects this data and stores it in the database.

[0975] Data preprocessing means

[0976] The data collected by the server is preprocessed. The Pandas library is used to impute missing values, remove duplicate data, and normalize the data.

[0977] Specific example

[0978] The server uses the Pandas library to impute missing weather data, for example, by using the mean. It also removes duplicate event data and performs normalization to maintain data consistency.

[0979] Feature transformation means

[0980] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it a format that is easy to apply to the model.

[0981] Specific example

[0982] The server quantifies weather information, assigning values ​​such as 1 for "sunny" and 0 for "rainy," and combines this with other sales performance data to generate features.

[0983] Machine learning model creation methods

[0984] The server uses the transformed features to create a machine learning model. It then trains regression models and decision trees using the Scikit-learn library.

[0985] Specific example

[0986] The server uses the Scikit-learn library to train a regression model based on past event data and create a sales forecast model for new events.

[0987] Means for verifying analysis results

[0988] The server verifies the model's effectiveness using methods such as cross-validation. If the accuracy is insufficient, hyperparameter tuning is performed to improve the model's accuracy.

[0989] Specific example

[0990] The server splits the model into training and test data and verifies the prediction accuracy through cross-validation. If the accuracy is less than 80%, the hyperparameters are adjusted and training is performed again.

[0991] Ticket price prediction method

[0992] The server uses a machine learning model to predict the optimal ticket price based on the new event information. The user enters the new event information from their device.

[0993] Specific example

[0994] Users input information about the "Winter Music Festival" from their terminals, and the server inputs that information into a machine learning model to calculate the optimal seating price. For example, it might predict that the standing area price is 5,500 yen and the seated area price is 4,500 yen.

[0995] Price setting output method

[0996] The server outputs the predicted charges to the user's terminal. The user reviews the displayed charges and adjusts them as needed.

[0997] Specific example

[0998] The user checks the pricing displayed on their device and sets the standing area to 5500 yen and the seated area to 4500 yen.

[0999] Pricing confirmation method

[1000] The user finalizes the pricing, and the server saves that information to a database. The server then integrates with the ticket sales system to reflect the published pricing.

[1001] Specific example

[1002] The user confirms the final settings, and the server saves those settings to the database. Next, the server uses an API to connect with the ticket sales system and publish the set price.

[1003] Examples of prompts to input into a generative AI model

[1004] "Please enter the data needed to predict pricing for the new event. For example, past event names, weather conditions, sales performance, etc."

[1005] This system allows even small and medium-sized events to effectively utilize past data and accurately and efficiently set optimal seating rates.

[1006] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1007] Step 1: Data Collection

[1008] The server collects past event data. Specifically, the server connects to a database and retrieves event information such as weather conditions, seating arrangements, and sales performance. Users grant permission to access the database through their terminals and enter the necessary information. The input data includes event name, location, date and time, weather, seating layout, and sales performance. The server then saves the collected data to the database.

[1009] Step 2: Data Preprocessing

[1010] The server preprocesses the collected data. Specifically, it uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The input data is the raw data collected in step 1, and the output data is the preprocessed, clean data. The server imputes missing values ​​with the mean and removes duplicate data. Normalization maintains data consistency.

[1011] Step 3: Feature transformation

[1012] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it easier to apply to the model. The input data is preprocessed clean data, and the output data is numerical or encoded feature data. For example, weather information is converted to "sunny → 1" and "rainy → 0".

[1013] Step 4: Create a machine learning model

[1014] The server creates a machine learning model using the transformed features. Specifically, it trains regression models and decision trees using the Scikit-learn library. The input data is data that has been transformed into features, and the output data is the trained machine learning model. The server uses the regression model to create a sales forecast model based on past event data.

[1015] Step 5: Verification of analysis results

[1016] The server validates the model's effectiveness using methods such as cross-validation. Specifically, it splits the data, checks the prediction accuracy on test data, and improves the model's accuracy through hyperparameter tuning. The input data is a trained machine learning model, and the output data is the evaluation result of the prediction accuracy. The server performs cross-validation, and adjusts the hyperparameters if the prediction accuracy is less than 80%.

[1017] Step 6: Predicting Ticket Prices

[1018] The server uses a machine learning model to predict the optimal ticket price based on new event information. The user inputs new event information from their terminal. The input data is the new event information and the trained model, and the output data is the predicted pricing. The user inputs information about the "Winter Music Festival," and the server calculates the ticket price based on that. For example, it predicts a standing area price of 5500 yen and a seated area price of 4500 yen.

[1019] Step 7: Output pricing settings

[1020] The server outputs the predicted pricing to the user's terminal. Specifically, it displays the predicted pricing on the user's terminal, allowing the user to review and adjust it. The input data is the predicted pricing, and the output data is the adjustable pricing displayed to the user. The user reviews the pricing displayed on their terminal and sets the standing area to 5500 yen and the seated area to 4500 yen.

[1021] Step 8: Confirm pricing

[1022] The user finalizes the pricing, and the server saves this information to the database. The server then integrates with the ticket sales system to reflect the published pricing. The input data is the finalized pricing, while the output data is the pricing saved in the database and its reflection in the sales system. The user finalizes the settings on their terminal, and the server saves these settings to the database. The server then uses an API to integrate with the ticket sales system and publishes the set prices.

[1023] (Application Example 1)

[1024] 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."

[1025] For small to medium-sized events, setting efficient and optimal seating rates is a crucial challenge for organizers. To maximize revenue, it is necessary to accurately predict pricing based on past event data, and furthermore, to smoothly present this information to users at physical locations and allow them to make appropriate adjustments.

[1026] 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.

[1027] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for finalizing the pricing and saving it to the system, and means for displaying the collected data and predicted pricing using a smartphone application used in physical stores, allowing the user to make adjustments and final settings. This makes it possible to set optimal seat prices to maximize revenue by utilizing past event data.

[1028] "Past event data" refers to information about events that were actually held in the past, including data such as weather, seating layout, and sales performance.

[1029] "Means of data collection" refers to the processes and technical means for accumulating information about past events on a server.

[1030] "Methods for preprocessing data and converting it into features" refer to the process of preparing collected data into an analyzable format by imputing missing values, removing duplicate data, performing numerical conversions, etc.

[1031] A "machine learning model" is an algorithm and computational model used to make predictions about future events based on historically collected data.

[1032] "Means for verifying analysis results" refer to methods and processes for evaluating the accuracy and effectiveness of results generated by machine learning models.

[1033] "Methods for predicting ticket prices" refer to the processes and technical means for predicting optimal seat prices based on new event information.

[1034] "Means for outputting pricing and adjusting it as needed" refers to an interface and technical means for displaying predicted pricing to the user and allowing manual adjustments as necessary.

[1035] "Means for finalizing pricing and saving it to the system" refers to the technical means for saving the final pricing information confirmed by the user to a database.

[1036] A "smartphone application" is software that runs on a smartphone and allows users to input past event data, check price prediction results, and adjust and finalize price settings.

[1037] A "physical store" refers to a store that exists in a physical location and is a place where events are held.

[1038] This invention relates to a smartphone application and its backend structure for streamlining event management at physical stores. The system includes a series of processes: collecting historical event data, performing data preprocessing and feature transformation, creating machine learning models, and predicting ticket prices for new events. The results of this process are presented to the user through the smartphone application, allowing the user to adjust and finalize the pricing.

[1039] The server accesses a database to retrieve past event information as a means of collecting historical event data. This information includes weather, seating layout, and sales performance. Users complete data collection by entering the necessary data through a smartphone application and sending it to the server.

[1040] Since the collected data is not suitable for analysis in its raw form, the server uses data preprocessing to impute missing values, remove duplicate data, and normalize the data. This preprocessing uses data preprocessing libraries such as Pandas and NumPy. Subsequently, feature transformation is used to convert categorical data, such as weather, into numerical data.

[1041] Based on the preprocessed and feature-transformed data, the server creates a machine learning model. This model uses Scikit-learn's regression model or random forest. The accuracy of the analysis results of the created model is checked using validation methods such as cross-validation.

[1042] When new event information is entered, the server uses a machine learning model to predict ticket prices. These predictions are presented to the user via a smartphone application, allowing them to review the pricing and make adjustments as needed. These adjustments can be made through the user interface.

[1043] The finalized pricing is saved to a database by the server and reflected in the ticket sales system. This saving and updating of information is automated using an API.

[1044] For example, if a user plans a new event called "Winter Music Festival," the process would proceed as follows: The user inputs data from a past event, such as "Summer Festival," from their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[1045] Example of a prompt:

[1046] To predict the optimal ticket price for the new event "Winter Music Festival 2023," please use data from the past "Summer Festival 2022" (weather: sunny, seating layout: standing, sales: 5000 tickets) to determine the price.

[1047] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1048] Step 1:

[1049] The user enters information about a new event into a smartphone application.

[1050] Input: Basic information for the new event (e.g., event name, date, venue, seating layout, etc.)

[1051] Output: The input event information is sent to the server.

[1052] Specific operation: When a user enters event details into an input form on their smartphone and presses the "Submit" button, the data is sent to the server.

[1053] Step 2:

[1054] The server collects past event data from the database.

[1055] Input: Conditions of past events (e.g., dates of similar events, weather, seating layout, etc.)

[1056] Output: Historical event dataset

[1057] Specific operation: The server queries the database and retrieves past event data that matches the specified conditions.

[1058] Step 3:

[1059] The server preprocesses the data it collects.

[1060] Input: Collected historical event data

[1061] Output: A normalized dataset with missing values ​​imputed and duplicate data removed.

[1062] Specific operation: Using the Pandas and Numpy libraries, the system performs mean imputation of missing values, removes duplicate data, and normalizes the data using MinMaxScaler.

[1063] Step 4:

[1064] The server converts the pre-processed data into features.

[1065] Input: Preprocessed dataset

[1066] Output: Feature data converted to a format applicable to machine learning models.

[1067] Specific operation: One-hot encoding is performed to convert categorical data (e.g., weather) into numerical data.

[1068] Step 5:

[1069] The server creates a machine learning model and verifies the analysis results.

[1070] Input: Dataset converted into features

[1071] Output: Trained machine learning model and validation results

[1072] Specific operation: Use Scikit-learn to train a regression model or a random forest model, and then evaluate the accuracy using cross-validation.

[1073] Step 6:

[1074] The server predicts ticket prices based on new event information.

[1075] Input: New event information and a trained machine learning model

[1076] Output: Predicted ticket price

[1077] Specific operation: Input the features of the new event into the model and calculate the predicted price.

[1078] Step 7:

[1079] The server outputs the predicted pricing to the smartphone application.

[1080] Input: Predicted ticket price

[1081] Output: Pricing displayed on the smartphone application

[1082] Specific operation: The server sends pricing data to the application via the API and displays it in the user interface.

[1083] Step 8:

[1084] Users can check the pricing settings through the application and make adjustments as needed.

[1085] Input: Pricing displayed on the smartphone application

[1086] Output: User-adjusted pricing

[1087] Specific operation: The user checks the pricing settings through the interface and adjusts them using sliders or numerical input.

[1088] Step 9:

[1089] The user finalizes the pricing, and the server saves it.

[1090] Input: User-adjusted pricing

[1091] Output: Final pricing settings stored in the database

[1092] Specific operation: After the user presses the "Confirm" button, the server saves the pricing settings to the database.

[1093] Step 10:

[1094] The server reflects the final pricing in the ticket sales system.

[1095] Input: Final pricing saved in the database

[1096] Output: Pricing reflected in the ticket sales system

[1097] Specific action: The server uses the API to update the pricing settings of the ticket sales system.

[1098] 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.

[1099] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and ultimately provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, this invention provides interaction tailored to the user's emotional state by incorporating an emotion engine that recognizes the user's emotions.

[1100] Data acquisition methods

[1101] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[1102] Data preprocessing means

[1103] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[1104] Feature transformation means

[1105] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[1106] Machine learning model creation methods

[1107] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[1108] Means for verifying analysis results

[1109] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[1110] Ticket price prediction method

[1111] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[1112] Price setting output method

[1113] The server outputs the predicted pricing to the user's terminal. The user can review this pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[1114] Pricing confirmation method

[1115] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[1116] Embedding an emotion engine

[1117] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions. As the user interacts with the device, the emotion engine monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display more detailed explanations and provide support to help the user feel at ease.

[1118] Specific example

[1119] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict ticket prices for the new event. The pricing is output to the device, and the user adjusts it as needed to finalize the pricing. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's feelings.

[1120] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[1121] The following describes the processing flow.

[1122] Step 1:

[1123] Users input past event data into their devices. Specifically, they input information such as the type of event, date and time, weather, seating layout, and sales performance.

[1124] Step 2:

[1125] The server collects past event data entered by users from the database. It issues SQL queries to retrieve the necessary data.

[1126] Step 3:

[1127] The server preprocesses the collected data. This preprocessing includes imputing missing values, removing duplicate data, and normalizing the data. For example, it uses the Pandas library to execute a function that imputes missing values.

[1128] Step 4:

[1129] The server converts pre-processed data into features. Categorical data such as weather is converted into numerical data and made into an analyzable format. Specifically, one-hot encoding and label encoding are applied.

[1130] Step 5:

[1131] The server creates a machine learning model based on the data converted into features. The Scikit-learn library is used to train regression models and random forests. The dataset is split into training and test data for model training.

[1132] Step 6:

[1133] The server validates the accuracy of the machine learning model using cross-validation. It calculates model performance metrics (RMSE, R^2, etc.) to confirm the model's effectiveness. Furthermore, it tunes hyperparameters as needed.

[1134] Step 7:

[1135] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (scheduled date and time, expected weather, seating layout, etc.).

[1136] Step 8:

[1137] The server uses a machine learning model to predict the optimal ticket price based on newly entered event information. It also considers past event data and analyzes the balance of supply and demand to calculate the price.

[1138] Step 9:

[1139] The server outputs the predicted charges to the terminal. The user can review these charges and manually adjust them through the interface provided by the server.

[1140] Step 10:

[1141] The emotion engine monitors the user's emotions. When a user checks the pricing, the emotion engine analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions.

[1142] Step 11:

[1143] The emotion engine dynamically adjusts the interface based on the user's emotional state. For example, if the user is feeling anxious, it will display additional explanations or support messages.

[1144] Step 12:

[1145] The user confirms the final pricing on their device. If the pricing is adjusted by the user, that information is also sent to the server.

[1146] Step 13:

[1147] The server saves confirmed pricing information to the database. New pricing information is recorded and used for subsequent event analysis and management.

[1148] Step 14:

[1149] The server integrates with the ticket sales system to reflect the published pricing. Using an API, new pricing information is automatically transferred to the ticket sales system and applied.

[1150] The above is the specific processing flow of the system that combines the emotion engine. This system is expected to maximize revenue and improve the user experience by recognizing user emotions in real time and setting optimal seating rates for small to medium-sized events.

[1151] (Example 2)

[1152] 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."

[1153] In optimizing seat pricing using past event data, there is a need to improve the accuracy of data analysis while providing user-responsive interactions. However, conventional systems have struggled to meet these requirements while simultaneously performing multidimensional data analysis and real-time user sentiment analysis.

[1154] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for determining the final pricing and saving it to the system, and means for recognizing user emotions and dynamically adjusting the user interface. This enables highly accurate pricing based on past data and dynamic adjustment of the interface in response to user emotions.

[1155] "Past event data" refers to all information about events that have been held in the past, including elements such as weather conditions, seating arrangements, and sales history.

[1156] "Data preprocessing" refers to a series of operations to prepare collected data into a format suitable for analysis, and includes processes such as imputation of missing values, removal of duplicate data, and normalization.

[1157] "Converting to features" refers to the step of changing raw data into an analyzable format, such as converting weather data into numerical data.

[1158] A "machine learning model" refers to an algorithm that finds patterns in data and enables future predictions and classifications, and includes regression algorithms and decision tree algorithms.

[1159] "Verification of analysis results" refers to the process of evaluating how accurate the generated machine learning model is, and methods such as cross-validation are used.

[1160] "Predicting ticket prices" refers to the process of calculating the optimal price based on new event information, utilizing historical data and machine learning models.

[1161] "Outputting and adjusting pricing" refers to a function that displays predicted prices in the user interface, allowing users to change prices as needed.

[1162] "Confirming and saving pricing" refers to the process of recording the final determined ticket price in the system's database.

[1163] "Emotional recognition" refers to a function that reads the user's emotional state from their facial expressions, voice tone, gestures, etc., and analyzes it in real time.

[1164] "Dynamically adjusting the user interface" refers to the process of adapting the system's display and operation methods in real time according to the user's emotional state.

[1165] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, the invention provides interaction tailored to the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[1166] Data acquisition methods

[1167] The server collects data from past events. This data includes weather conditions, seating arrangements, and sales history. Users access the database through their terminals, retrieve the necessary information from the database, and send it to the server. The server integrates this data and stores it as a dataset for analysis.

[1168] Data preprocessing means

[1169] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. For example, if weather data is missing, it is imputed using historical mean values.

[1170] Feature transformation means

[1171] The server converts the preprocessed data into analyzable features. For example, it converts weather data into a format that is easy to apply to machine learning models, such as quantifying "sunny = 1" and "rainy = 0". This conversion allows for the integration and analysis of multiple factors.

[1172] Machine learning model creation methods

[1173] The server generates a machine learning model based on the data converted into features. This model is created using Scikit-learn, training regression and decision tree algorithms. The model learns patterns from past data and applies them to new event data to make predictions.

[1174] Means for verifying analysis results

[1175] The server verifies the model's effectiveness using cross-validation and other validation techniques. The data is split to verify the reliability of the analysis results and used as test data. Hyperparameter tuning is performed as needed to improve the model's accuracy.

[1176] Ticket price prediction method

[1177] The server predicts the optimal ticket price based on new event information. Users input new event information, such as "Winter Music Festival," through their terminals, and the server calculates the price based on that information. In this process, historical event data and generative AI models are utilized to make highly accurate predictions.

[1178] Price setting output method

[1179] The server outputs the predicted pricing to the user's terminal. The user uses the terminal to check this pricing and adjust the prices as needed. For example, the standing area price for the "Winter Music Festival" is set at 5500 yen and the seating area price at 4500 yen.

[1180] Pricing confirmation method

[1181] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the published pricing.

[1182] Embedding an emotion engine

[1183] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body movements to recognize emotions. As the user interacts with the device, the server monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display a detailed explanation and an encouraging message to support the user.

[1184] Specific example

[1185] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a generative AI model and predicts the ticket price for the new event based on that model. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's emotions.

[1186] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[1187] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1188] Step 1: Data Collection

[1189] The server collects historical event data. The user, via their terminal, instructs the server to retrieve this data from the database. The server executes SQL queries to the database, retrieving information such as weather conditions, seating arrangements, and sales history. This data is then sent to the server for integration.

[1190] Input: Event name submitted by the user (e.g., "Summer Festival", "Spring Carnival")

[1191] Output: Integrated data on weather conditions, seating arrangements, and sales history.

[1192] Specific actions:

[1193] The user enters the event name, such as "Summer Festival" or "Spring Carnival," from their device.

[1194] The server uses SQL queries to retrieve relevant information from the database.

[1195] The server integrates the acquired information and saves it as a dataset for analysis.

[1196] Step 2: Data Preprocessing

[1197] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The collected data is then converted into a format suitable for analysis.

[1198] Input: Integrated event data

[1199] Output: Preprocessed data

[1200] Specific actions:

[1201] The server creates a dataframe using the Pandas library.

[1202] Missing data is imputed with historical averages.

[1203] Remove duplicate data and maintain consistent data.

[1204] The data is normalized to a range of 0 to 1 and converted into an analyzable format.

[1205] Step 3: Feature transformation

[1206] The server converts the preprocessed data into analyzable features. This feature conversion includes processes such as converting categorical data into numerical data. For example, weather data is converted to "sunny = 1" and "rainy = 0".

[1207] Input: Preprocessed data

[1208] Output: Data converted into features

[1209] Specific actions:

[1210] Convert categorical data such as weather data into numerical data.

[1211] The server uses Pandas to generate multiple features.

[1212] Step 4: Create a machine learning model

[1213] The server generates machine learning models using the data converted into features. It uses Scikit-learn to train regression and decision tree algorithms. The models learn patterns from past data and make predictions with new event data.

[1214] Input: Data converted into features

[1215] Output: Trained machine learning model

[1216] Specific actions:

[1217] Splitting data into training and test phases using the scikit-learn library

[1218] Train random forest and regression models and evaluate their prediction accuracy.

[1219] Hyperparameter tuning as needed

[1220] Step 5: Verification of analysis results

[1221] The server uses cross-validation and other verification methods to verify the effectiveness of the generated model. The reliability of the analysis results is evaluated, and the model is re-evaluated using test data to confirm its accuracy.

[1222] Input: Trained machine learning model

[1223] Output: Validated models and their accuracy evaluation

[1224] Specific actions:

[1225] The server divides the data into k subsets and performs cross-validation.

[1226] Train the model on each subset and test it on the remaining subsets.

[1227] The model's accuracy and reliability are verified on average, and tuning is performed if necessary.

[1228] Step 6: Predicting Ticket Prices

[1229] The server uses a generative AI model to predict the optimal ticket price based on new event information. When a user enters new event information from their device, the server calculates the price based on that information.

[1230] Input: New event information (e.g., "Winter Music Festival")

[1231] Output: Predicted ticket price

[1232] Specific actions:

[1233] Users enter new event information via their devices.

[1234] The server inputs new information into an AI model to predict the cost.

[1235] We predict the standing area ticket price will be 5500 yen and the seated area ticket price will be 4500 yen.

[1236] Step 7: Output pricing settings

[1237] The server outputs the predicted charges to the user's terminal. The user reviews these charges and adjusts them as needed.

[1238] Input: Predicted ticket price

[1239] Output: Adjustable pricing

[1240] Specific actions:

[1241] The server sends the predicted charges information to the user's terminal.

[1242] The user checks the price and adjusts the standing area price, for example, from 5500 yen to 5000 yen.

[1243] Step 8: Confirm pricing

[1244] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the pricing changes.

[1245] Input: Final adjusted pricing

[1246] Output: Finalized pricing and the database reflecting it.

[1247] Specific actions:

[1248] The user finalizes the pricing.

[1249] The server stores pricing information in the database.

[1250] The server uses an API to connect with the ticket sales system.

[1251] Step 9: Integrating the Emotion Engine

[1252] The server uses an emotion engine to analyze sensor information that recognizes the user's emotions. As the user operates the device, it monitors their emotions in real time and dynamically adjusts the interface based on that information.

[1253] Input: User's facial expressions, voice tone, and body movements

[1254] Output: Dynamic adjustment of the user interface

[1255] Specific actions:

[1256] The server analyzes the user's facial expressions and voice tone using sensors.

[1257] When a user feels anxious, detailed help information and encouraging messages are displayed.

[1258] This enables highly accurate pricing based on historical data and dynamic adjustments to the interface in response to user emotions.

[1259] (Application Example 2)

[1260] 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."

[1261] For small to medium-sized events, it is difficult to determine optimal seating rates by utilizing past event data. Furthermore, the pricing process often lacks support that considers user emotions, leading to user anxiety and questions. Therefore, a system is needed that allows for efficient and reassuring pricing.

[1262] 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. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted price setting and adjusting it as necessary, means for determining the final price setting and saving it to the system, means for recognizing the user's emotions in real time, and means for dynamically adjusting the interface according to the user's emotions. This enables optimal seat pricing using past event data, as well as support that responds to the user's emotions.

[1263] "Past event data" refers to a collection of information about events held in the past, specifically including data such as weather conditions, seating layout, and sales performance.

[1264] "Data preprocessing" is the process of converting collected data into a format suitable for analysis, and includes tasks such as imputing missing values, removing duplicate data, and normalizing the data.

[1265] "Features" are attributes or properties of data used to apply to machine learning models, and are used to predict new information.

[1266] A "machine learning model" is a type of algorithm that learns data trends and patterns from large amounts of data and uses that learning to make predictions and classifications on new data.

[1267] A "ticket price prediction method" is a method for calculating the optimal seat price based on new event information, and it uses a machine learning model to make predictions.

[1268] "User emotion recognition means" refers to technology that analyzes the user's facial expressions, voice tone, body gestures, etc., to recognize the user's emotional state in real time.

[1269] "Dynamic interface adjustment" means changing the system's interface and display content in real time according to the user's emotional state.

[1270] "Verification of analysis results" refers to evaluating the analysis results using test data in order to confirm the performance and effectiveness of a machine learning model.

[1271] "Finalizing pricing" refers to the process of determining the final pricing and saving that information in the system.

[1272] This invention is a system that optimizes seat pricing for small and medium-sized events by utilizing past event data, and further recognizes user emotions in real time to dynamically adjust the interface. This system is implemented using specific hardware and software.

[1273] 1. System Configuration

[1274] The server includes means that have the following functions:

[1275] Data collection method: Collect past event data. This includes weather conditions, seating layout, sales performance, etc.

[1276] Data preprocessing means: The collected data is preprocessed to impute missing values, remove duplicate data, and normalize the data.

[1277] Feature transformation means: Converts preprocessed data into analyzable features.

[1278] Machine learning model creation method: Create a machine learning model based on features and use a regression model or random forest.

[1279] Method for verifying analysis results: The accuracy of the analysis results is verified using cross-validation.

[1280] Ticket price prediction method: Predicts the optimal ticket price based on new event information.

[1281] Pricing output method: Predicts the pricing and allows the user to adjust it.

[1282] Pricing confirmation method: Confirm the final pricing and save it in the system.

[1283] Emotion recognition means: Recognizes the user's emotions in real time using a camera or voice input device.

[1284] Dynamic interface adjustment means: The interface is dynamically adjusted based on information obtained by the emotion recognition means.

[1285] 2. Hardware and software required for implementation

[1286] Specific examples of the hardware and software used are as follows:

[1287] Hardware: Server, camera, microphone, user terminal (smartphone or PC)

[1288] Software: Python, Pandas, Scikit-learn, EmotionEngine (a virtual emotion recognition module)

[1289] 3. Data processing and data calculation

[1290] The server processes the data in the following order:

[1291] Data collection: Retrieve past event data from the database.

[1292] Data preprocessing: Use the Pandas library to impute missing values ​​and normalize the collected data.

[1293] Feature transformation: Converts data such as weather and seating layout into numerical data.

[1294] Machine learning model creation: Create a machine learning model using Scikit-learn.

[1295] Model validation: Evaluate the accuracy of the model using cross-validation.

[1296] Price Prediction: Input new event information and use a machine learning model to predict the optimal price.

[1297] Emotion Recognition: EmotionEngine is used to analyze user emotions using data obtained from the camera and microphone.

[1298] Dynamic interface adjustment: The interface changes according to the user's emotional state.

[1299] 4. Specific examples and prompt statements

[1300] For example, when a user plans a "winter music festival," they input data from past events such as "summer festivals" into the system. The server then predicts the optimal seating price for the new event through processes such as data collection, data preprocessing, feature transformation, and machine learning model creation. The predicted pricing is then presented to the user, allowing them to confidently set prices based on sentiment recognition.

[1301] Example of a prompt:

[1302] Based on past event data, please determine the optimal seating price for a winter music festival. Please provide detailed information, including weather, seating layout, and sales performance. Also, please explain how you can address any concerns users may have.

[1303] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1304] Step 1:

[1305] The server collects historical event data from the database. Specifically, it queries data such as weather conditions, seating layout, and sales performance, and retrieves the results. The input is the query conditions for the event data, and the output is the collected historical event data.

[1306] Step 2:

[1307] The server-collected data is preprocessed using the Pandas library. Specifically, missing value imputation, duplicate data removal, and normalization are performed. The input is the collected event data, and the output is the preprocessed data.

[1308] Step 3:

[1309] The server converts pre-processed data into features. Specifically, it converts data such as weather and seating layout into numerical data. The input is pre-processed data, and the output is data converted into features.

[1310] Step 4:

[1311] The server uses Scikit-learn to create machine learning models. Specifically, it trains them using regression models or random forests. The input is data transformed into features and their corresponding labels, and the output is the trained machine learning model.

[1312] Step 5:

[1313] The server uses cross-validation to validate the model. Specifically, it evaluates the accuracy of the trained model and confirms that the model works correctly. The input is the trained machine learning model and test data, and the output is the model's accuracy evaluation result.

[1314] Step 6:

[1315] The user enters new event information from a terminal. Specifically, the user enters details of the new event (e.g., weather conditions, seating layout, expected sales figures, etc.) into the terminal. The input is the new event information, and the output is the display of the entered event information on the terminal screen.

[1316] Step 7:

[1317] The server predicts ticket prices based on new event information. Specifically, it uses a trained machine learning model to calculate the optimal seat price. The input is the new event information and the trained model, and the output is the predicted ticket price.

[1318] Step 8:

[1319] The server outputs the predicted price to the user's terminal. The input is the predicted ticket price, and the output is the price displayed on the user's terminal.

[1320] Step 9:

[1321] The user reviews the predicted price displayed on their device and makes adjustments as needed. Specifically, the user views the predicted price and changes or modifies it. The input is the predicted price, and the output is the price adjusted by the user.

[1322] Step 10:

[1323] The server saves the final pricing to the system. Specifically, it saves the confirmed pricing to the database and prepares it for integration with the ticket sales system. The input is the final pricing adjusted by the user, and the output is the pricing information stored in the database.

[1324] Step 11:

[1325] The server uses EmotionEngine to recognize the user's emotions in real time. Specifically, it analyzes data acquired from cameras and microphones to determine the user's emotional state. The input is data obtained from cameras and microphones, and the output is the real-time emotion recognition result.

[1326] Step 12:

[1327] The server dynamically adjusts the interface based on the user's emotional state. Specifically, if the user is feeling anxious or confused, the system provides detailed explanations or additional support information. The input is real-time emotion recognition results, and the output is a dynamically adjusted interface.

[1328] 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.

[1329] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1330] 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.

[1331] [Fourth Embodiment]

[1332] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1333] 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.

[1334] 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).

[1335] 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.

[1336] 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.

[1337] 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).

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] 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.

[1344] 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".

[1345] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing.

[1346] Data acquisition methods

[1347] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[1348] Data preprocessing means

[1349] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[1350] Feature transformation means

[1351] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[1352] Machine learning model creation methods

[1353] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[1354] Means for verifying analysis results

[1355] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[1356] Ticket price prediction method

[1357] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[1358] Price setting output method

[1359] The server outputs the predicted pricing to the user's terminal. The user can review the displayed pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[1360] Pricing confirmation method

[1361] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[1362] Specific example

[1363] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as "Summer Festivals," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[1364] This system allows for the use of historical data even for small and medium-sized events, enabling optimal seat pricing to maximize revenue.

[1365] The following describes the processing flow.

[1366] Step 1:

[1367] Users input past event data into their terminals. Specifically, they input information such as the type of event, weather, seating layout, and sales performance.

[1368] Step 2:

[1369] The server collects the input data and extracts relevant historical event information from the database. It then issues SQL queries to the database to retrieve the necessary data.

[1370] Step 3:

[1371] The server preprocesses the collected data. Specifically, this involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity.

[1372] Step 4:

[1373] The server converts pre-processed data into features. Categorical data such as weather and seating layout is converted into numerical data, making it a format that can be applied to machine learning models.

[1374] Step 5:

[1375] The server uses the data, which has been converted into features, to create machine learning models. Here, the Scikit-learn library is used to train regression models and random forests.

[1376] Step 6:

[1377] The server validates the accuracy of the machine learning model. During this process, cross-validation is used to check the model's effectiveness, and hyperparameter tuning is performed as needed.

[1378] Step 7:

[1379] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (date, time, location, expected weather, etc.).

[1380] Step 8:

[1381] The server uses a machine learning model to predict seat prices based on newly entered event information. It calculates the optimal price while considering its relevance to past data.

[1382] Step 9:

[1383] The server outputs the predicted price to the terminal. The user can review this price setting and adjust it manually if necessary. The displayed price is, for example, 5500 yen for the standing area and 4500 yen for the seated area.

[1384] Step 10:

[1385] The user confirms the final pricing on their device. The adjusted price is finalized at this point.

[1386] Step 11:

[1387] The server saves the finalized pricing information to a database. This data is recorded for future event management and analysis.

[1388] Step 12:

[1389] The server integrates with the ticket sales system and reflects the published pricing. It uses an API to automatically transfer pricing information to the ticket sales system.

[1390] The above is a detailed explanation of the 12 steps in the program's processing flow. This system enables optimal seat pricing that maximizes revenue, even for small to medium-sized events, by utilizing past data.

[1391] (Example 1)

[1392] 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".

[1393] For small and medium-sized events, there is a need for a way to effectively utilize past event data and automate and optimize seat pricing to maximize revenue. However, current methods often rely heavily on manual settings, making efficient and accurate pricing difficult. Therefore, a system is needed that uses data analysis and prediction based on past event data to optimize pricing for new events.

[1394] 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.

[1395] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting the settings as necessary, means for finalizing the pricing and saving it in the system, and means for coordinating with the ticket sales system to reflect the settings. This makes it possible to effectively utilize past data and accurately and efficiently set optimal seat prices.

[1396] "Past event data" refers to information about past events, including weather conditions, seating arrangements, and sales figures.

[1397] "Means of collecting data" refers to methods for obtaining information about past events from databases, etc., and these are executed via a server.

[1398] "Preprocessing methods" refer to techniques used to maintain the integrity of collected data and convert it into a format that is easy to analyze, such as imputing missing values, removing duplicate data, and normalizing the data.

[1399] "Means of converting to features" refers to means of converting preprocessed data into a format that can be processed by a machine learning model, and includes, for example, converting it into numerical data.

[1400] "Means for creating machine learning models" refers to methods for training and creating machine learning models such as predictive models and decision trees using preprocessed data and features.

[1401] "Means for verifying analysis results" refer to methods such as cross-validation and hyperparameter tuning to confirm the accuracy and reliability of the created machine learning model.

[1402] "A method for predicting ticket prices based on new event information" refers to a method for inputting information about new events into a machine learning model to calculate the optimal ticket price.

[1403] "A means of outputting predicted pricing and allowing users to adjust the settings as needed" refers to a means of displaying predicted pricing on the user's device and allowing the user to adjust the pricing as needed.

[1404] "Means for finalizing and saving the final pricing" refers to the means by which the user's finalized pricing is saved in a database.

[1405] "Methods for linking with the ticket sales system to reflect settings" refers to methods of linking with the ticket sales system using APIs or similar means to reflect the finalized pricing settings in the ticket sales system.

[1406] This invention relates to a system for optimizing seat pricing for small and medium-sized events. This system collects, preprocesses, and features-transforms historical event data, creates a machine learning model based on it, verifies the analysis results, predicts seat pricing for new events, and provides a series of processes for users to confirm, adjust, and finalize the predicted pricing.

[1407] Data acquisition methods

[1408] The server collects past event data. Specifically, the server connects to a database and retrieves past event information (weather conditions, seating arrangements, sales performance, etc.). Users grant permission to access the database through their terminals and enter the necessary information.

[1409] Specific example

[1410] When a user plans a new event called "Winter Music Festival," they access the database from their device and input data from past "Summer Festivals" and "Autumn Music Festivals." The server collects this data and stores it in the database.

[1411] Data preprocessing means

[1412] The data collected by the server is preprocessed. The Pandas library is used to impute missing values, remove duplicate data, and normalize the data.

[1413] Specific example

[1414] The server uses the Pandas library to impute missing weather data, for example, by using the mean. It also removes duplicate event data and performs normalization to maintain data consistency.

[1415] Feature transformation means

[1416] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it a format that is easy to apply to the model.

[1417] Specific example

[1418] The server quantifies weather information, assigning values ​​such as 1 for "sunny" and 0 for "rainy," and combines this with other sales performance data to generate features.

[1419] Machine learning model creation methods

[1420] The server uses the transformed features to create a machine learning model. It then trains regression models and decision trees using the Scikit-learn library.

[1421] Specific example

[1422] The server uses the Scikit-learn library to train a regression model based on past event data and create a sales forecast model for new events.

[1423] Means for verifying analysis results

[1424] The server verifies the model's effectiveness using methods such as cross-validation. If the accuracy is insufficient, hyperparameter tuning is performed to improve the model's accuracy.

[1425] Specific example

[1426] The server splits the model into training and test data and verifies the prediction accuracy through cross-validation. If the accuracy is less than 80%, the hyperparameters are adjusted and training is performed again.

[1427] Ticket price prediction method

[1428] The server uses a machine learning model to predict the optimal ticket price based on the new event information. The user enters the new event information from their device.

[1429] Specific example

[1430] Users input information about the "Winter Music Festival" from their terminals, and the server inputs that information into a machine learning model to calculate the optimal seating price. For example, it might predict that the standing area price is 5,500 yen and the seated area price is 4,500 yen.

[1431] Price setting output method

[1432] The server outputs the predicted charges to the user's terminal. The user reviews the displayed charges and adjusts them as needed.

[1433] Specific example

[1434] The user checks the pricing displayed on their device and sets the standing area to 5500 yen and the seated area to 4500 yen.

[1435] Pricing confirmation method

[1436] The user finalizes the pricing, and the server saves that information to a database. The server then integrates with the ticket sales system to reflect the published pricing.

[1437] Specific example

[1438] The user confirms the final settings, and the server saves those settings to the database. Next, the server uses an API to connect with the ticket sales system and publish the set price.

[1439] Examples of prompts to input into a generative AI model

[1440] "Please enter the data needed to predict pricing for the new event. For example, past event names, weather conditions, sales performance, etc."

[1441] This system allows even small and medium-sized events to effectively utilize past data and accurately and efficiently set optimal seating rates.

[1442] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1443] Step 1: Data Collection

[1444] The server collects past event data. Specifically, the server connects to a database and retrieves event information such as weather conditions, seating arrangements, and sales performance. Users grant permission to access the database through their terminals and enter the necessary information. The input data includes event name, location, date and time, weather, seating layout, and sales performance. The server then saves the collected data to the database.

[1445] Step 2: Data Preprocessing

[1446] The server preprocesses the collected data. Specifically, it uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The input data is the raw data collected in step 1, and the output data is the preprocessed, clean data. The server imputes missing values ​​with the mean and removes duplicate data. Normalization maintains data consistency.

[1447] Step 3: Feature transformation

[1448] The server converts the preprocessed data into analyzable features. Specifically, it converts weather information into numerical data, for example, to make it easier to apply to the model. The input data is preprocessed clean data, and the output data is numerical or encoded feature data. For example, weather information is converted to "sunny → 1" and "rainy → 0".

[1449] Step 4: Create a machine learning model

[1450] The server creates a machine learning model using the transformed features. Specifically, it trains regression models and decision trees using the Scikit-learn library. The input data is data that has been transformed into features, and the output data is the trained machine learning model. The server uses the regression model to create a sales forecast model based on past event data.

[1451] Step 5: Verification of analysis results

[1452] The server validates the model's effectiveness using methods such as cross-validation. Specifically, it splits the data, checks the prediction accuracy on test data, and improves the model's accuracy through hyperparameter tuning. The input data is a trained machine learning model, and the output data is the evaluation result of the prediction accuracy. The server performs cross-validation, and adjusts the hyperparameters if the prediction accuracy is less than 80%.

[1453] Step 6: Predicting Ticket Prices

[1454] The server uses a machine learning model to predict the optimal ticket price based on new event information. The user inputs new event information from their terminal. The input data is the new event information and the trained model, and the output data is the predicted pricing. The user inputs information about the "Winter Music Festival," and the server calculates the ticket price based on that. For example, it predicts a standing area price of 5500 yen and a seated area price of 4500 yen.

[1455] Step 7: Output pricing settings

[1456] The server outputs the predicted pricing to the user's terminal. Specifically, it displays the predicted pricing on the user's terminal, allowing the user to review and adjust it. The input data is the predicted pricing, and the output data is the adjustable pricing displayed to the user. The user reviews the pricing displayed on their terminal and sets the standing area to 5500 yen and the seated area to 4500 yen.

[1457] Step 8: Confirm pricing

[1458] The user finalizes the pricing, and the server saves this information to the database. The server then integrates with the ticket sales system to reflect the published pricing. The input data is the finalized pricing, while the output data is the pricing saved in the database and its reflection in the sales system. The user finalizes the settings on their terminal, and the server saves these settings to the database. The server then uses an API to integrate with the ticket sales system and publishes the set prices.

[1459] (Application Example 1)

[1460] 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".

[1461] For small to medium-sized events, setting efficient and optimal seating rates is a crucial challenge for organizers. To maximize revenue, it is necessary to accurately predict pricing based on past event data, and furthermore, to smoothly present this information to users at physical locations and allow them to make appropriate adjustments.

[1462] 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.

[1463] In this invention, the server includes means for collecting data from past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for finalizing the pricing and saving it to the system, and means for displaying the collected data and predicted pricing using a smartphone application used in physical stores, allowing the user to make adjustments and final settings. This makes it possible to set optimal seat prices to maximize revenue by utilizing past event data.

[1464] "Past event data" refers to information about events that were actually held in the past, including data such as weather, seating layout, and sales performance.

[1465] "Means of data collection" refers to the processes and technical means for accumulating information about past events on a server.

[1466] "Methods for preprocessing data and converting it into features" refer to the process of preparing collected data into an analyzable format by imputing missing values, removing duplicate data, performing numerical conversions, etc.

[1467] A "machine learning model" is an algorithm and computational model used to make predictions about future events based on historically collected data.

[1468] "Means for verifying analysis results" refer to methods and processes for evaluating the accuracy and effectiveness of results generated by machine learning models.

[1469] "Methods for predicting ticket prices" refer to the processes and technical means for predicting optimal seat prices based on new event information.

[1470] "Means for outputting pricing and adjusting it as needed" refers to an interface and technical means for displaying predicted pricing to the user and allowing manual adjustments as necessary.

[1471] "Means for finalizing pricing and saving it to the system" refers to the technical means for saving the final pricing information confirmed by the user to a database.

[1472] A "smartphone application" is software that runs on a smartphone and allows users to input past event data, check price prediction results, and adjust and finalize price settings.

[1473] A "physical store" refers to a store that exists in a physical location and is a place where events are held.

[1474] This invention relates to a smartphone application and its backend structure for streamlining event management at physical stores. The system includes a series of processes: collecting historical event data, performing data preprocessing and feature transformation, creating machine learning models, and predicting ticket prices for new events. The results of this process are presented to the user through the smartphone application, allowing the user to adjust and finalize the pricing.

[1475] The server accesses a database to retrieve past event information as a means of collecting historical event data. This information includes weather, seating layout, and sales performance. Users complete data collection by entering the necessary data through a smartphone application and sending it to the server.

[1476] Since the collected data is not suitable for analysis in its raw form, the server uses data preprocessing to impute missing values, remove duplicate data, and normalize the data. This preprocessing uses data preprocessing libraries such as Pandas and NumPy. Subsequently, feature transformation is used to convert categorical data, such as weather, into numerical data.

[1477] Based on the preprocessed and feature-transformed data, the server creates a machine learning model. This model uses Scikit-learn's regression model or random forest. The accuracy of the analysis results of the created model is checked using validation methods such as cross-validation.

[1478] When new event information is entered, the server uses a machine learning model to predict ticket prices. These predictions are presented to the user via a smartphone application, allowing them to review the pricing and make adjustments as needed. These adjustments can be made through the user interface.

[1479] The finalized pricing is saved to a database by the server and reflected in the ticket sales system. This saving and updating of information is automated using an API.

[1480] For example, if a user plans a new event called "Winter Music Festival," the process would proceed as follows: The user inputs data from a past event, such as "Summer Festival," from their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict the ticket price for the new event. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system.

[1481] Example of a prompt:

[1482] To predict the optimal ticket price for the new event "Winter Music Festival 2023," please use data from the past "Summer Festival 2022" (weather: sunny, seating layout: standing, sales: 5000 tickets) to determine the price.

[1483] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1484] Step 1:

[1485] The user enters information about a new event into a smartphone application.

[1486] Input: Basic information for the new event (e.g., event name, date, venue, seating layout, etc.)

[1487] Output: The input event information is sent to the server.

[1488] Specific operation: When a user enters event details into an input form on their smartphone and presses the "Submit" button, the data is sent to the server.

[1489] Step 2:

[1490] The server collects past event data from the database.

[1491] Input: Conditions of past events (e.g., dates of similar events, weather, seating layout, etc.)

[1492] Output: Historical event dataset

[1493] Specific operation: The server queries the database and retrieves past event data that matches the specified conditions.

[1494] Step 3:

[1495] The server preprocesses the data it collects.

[1496] Input: Collected historical event data

[1497] Output: A normalized dataset with missing values ​​imputed and duplicate data removed.

[1498] Specific operation: Using the Pandas and Numpy libraries, the system performs mean imputation of missing values, removes duplicate data, and normalizes the data using MinMaxScaler.

[1499] Step 4:

[1500] The server converts the pre-processed data into features.

[1501] Input: Preprocessed dataset

[1502] Output: Feature data converted to a format applicable to machine learning models.

[1503] Specific operation: One-hot encoding is performed to convert categorical data (e.g., weather) into numerical data.

[1504] Step 5:

[1505] The server creates a machine learning model and verifies the analysis results.

[1506] Input: Dataset converted into features

[1507] Output: Trained machine learning model and validation results

[1508] Specific operation: Use Scikit-learn to train a regression model or a random forest model, and then evaluate the accuracy using cross-validation.

[1509] Step 6:

[1510] The server predicts ticket prices based on new event information.

[1511] Input: New event information and a trained machine learning model

[1512] Output: Predicted ticket price

[1513] Specific operation: Input the features of the new event into the model and calculate the predicted price.

[1514] Step 7:

[1515] The server outputs the predicted pricing to the smartphone application.

[1516] Input: Predicted ticket price

[1517] Output: Pricing displayed on the smartphone application

[1518] Specific operation: The server sends pricing data to the application via the API and displays it in the user interface.

[1519] Step 8:

[1520] Users can check the pricing settings through the application and make adjustments as needed.

[1521] Input: Pricing displayed on the smartphone application

[1522] Output: User-adjusted pricing

[1523] Specific operation: The user checks the pricing settings through the interface and adjusts them using sliders or numerical input.

[1524] Step 9:

[1525] The user finalizes the pricing, and the server saves it.

[1526] Input: User-adjusted pricing

[1527] Output: Final pricing settings stored in the database

[1528] Specific operation: After the user presses the "Confirm" button, the server saves the pricing settings to the database.

[1529] Step 10:

[1530] The server reflects the final pricing in the ticket sales system.

[1531] Input: Final pricing saved in the database

[1532] Output: Pricing reflected in the ticket sales system

[1533] Specific action: The server uses the API to update the pricing settings of the ticket sales system.

[1534] 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.

[1535] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and ultimately provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, this invention provides interaction tailored to the user's emotional state by incorporating an emotion engine that recognizes the user's emotions.

[1536] Data acquisition methods

[1537] Historical event data is collected using a server. This server connects to a database and retrieves information about past events (weather, seating layout, sales figures, etc.). Users grant access to this database via their terminals and input the necessary information. This data collection allows the system to handle a variety of events.

[1538] Data preprocessing means

[1539] Since the collected data is not suitable for analysis in its raw state, the server preprocesses the data. This preprocessing step involves imputing missing values, removing duplicate data, and normalizing the data. For example, the Pandas library is used to maintain data integrity and convert it into a format suitable for analysis.

[1540] Feature transformation means

[1541] The preprocessed data is converted into analyzable features by the server. This process involves converting weather data, for example, into numerical data, making it suitable for application to machine learning models. This allows the system to consider multiple factors and make more accurate predictions.

[1542] Machine learning model creation methods

[1543] Using the data converted into features, the server creates a machine learning model. For example, it uses regression models or random forests to perform analysis based on historical data. The server uses Scikit-learn to train the model and improve the accuracy of the analysis results.

[1544] Means for verifying analysis results

[1545] The server verifies the model's effectiveness using methods such as cross-validation. In this step, the data is split to confirm the reliability of the analysis results, and verification is performed using test data. If the model's accuracy is insufficient, hyperparameter tuning is performed to improve accuracy.

[1546] Ticket price prediction method

[1547] Based on new event information, the server uses a machine learning model to predict the optimal ticket price. Users input new event information into their terminals, and the server calculates the price based on that information. In this process, past event data is considered, and the impact of differences in weather conditions and seating layout is also evaluated.

[1548] Price setting output method

[1549] The server outputs the predicted pricing to the user's terminal. The user can review this pricing and adjust it as needed through the interface provided by the system. For example, the price for the standing area might be set at 5500 yen and the price for the seated area at 4500 yen.

[1550] Pricing confirmation method

[1551] The user finalizes the pricing, and the server saves this information to a database. The server then integrates with the ticket sales system to reflect the published pricing. This process can be automated using an API.

[1552] Embedding an emotion engine

[1553] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions. As the user interacts with the device, the emotion engine monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display more detailed explanations and provide support to help the user feel at ease.

[1554] Specific example

[1555] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a machine learning model and uses that model to predict ticket prices for the new event. The pricing is output to the device, and the user adjusts it as needed to finalize the pricing. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's feelings.

[1556] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[1557] The following describes the processing flow.

[1558] Step 1:

[1559] Users input past event data into their devices. Specifically, they input information such as the type of event, date and time, weather, seating layout, and sales performance.

[1560] Step 2:

[1561] The server collects past event data entered by users from the database. It issues SQL queries to retrieve the necessary data.

[1562] Step 3:

[1563] The server preprocesses the collected data. This preprocessing includes imputing missing values, removing duplicate data, and normalizing the data. For example, it uses the Pandas library to execute a function that imputes missing values.

[1564] Step 4:

[1565] The server converts pre-processed data into features. Categorical data such as weather is converted into numerical data and made into an analyzable format. Specifically, one-hot encoding and label encoding are applied.

[1566] Step 5:

[1567] The server creates a machine learning model based on the data converted into features. The Scikit-learn library is used to train regression models and random forests. The dataset is split into training and test data for model training.

[1568] Step 6:

[1569] The server validates the accuracy of the machine learning model using cross-validation. It calculates model performance metrics (RMSE, R^2, etc.) to confirm the model's effectiveness. Furthermore, it tunes hyperparameters as needed.

[1570] Step 7:

[1571] The user enters new event information into the terminal. For example, they enter details about a "Winter Music Festival" (scheduled date and time, expected weather, seating layout, etc.).

[1572] Step 8:

[1573] The server uses a machine learning model to predict the optimal ticket price based on newly entered event information. It also considers past event data and analyzes the balance of supply and demand to calculate the price.

[1574] Step 9:

[1575] The server outputs the predicted charges to the terminal. The user can review these charges and manually adjust them through the interface provided by the server.

[1576] Step 10:

[1577] The emotion engine monitors the user's emotions. When a user checks the pricing, the emotion engine analyzes the user's facial expressions, voice tone, and body gestures to recognize their emotions.

[1578] Step 11:

[1579] The emotion engine dynamically adjusts the interface based on the user's emotional state. For example, if the user is feeling anxious, it will display additional explanations or support messages.

[1580] Step 12:

[1581] The user confirms the final pricing on their device. If the pricing is adjusted by the user, that information is also sent to the server.

[1582] Step 13:

[1583] The server saves confirmed pricing information to the database. New pricing information is recorded and used for subsequent event analysis and management.

[1584] Step 14:

[1585] The server integrates with the ticket sales system to reflect the published pricing. Using an API, new pricing information is automatically transferred to the ticket sales system and applied.

[1586] The above is the specific processing flow of the system that combines the emotion engine. This system is expected to maximize revenue and improve the user experience by recognizing user emotions in real time and setting optimal seating rates for small to medium-sized events.

[1587] (Example 2)

[1588] 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".

[1589] In optimizing seat pricing using past event data, there is a need to improve the accuracy of data analysis while providing user-responsive interactions. However, conventional systems have struggled to meet these requirements while simultaneously performing multidimensional data analysis and real-time user sentiment analysis.

[1590] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted pricing and adjusting it as necessary, means for determining the final pricing and saving it to the system, and means for recognizing user emotions and dynamically adjusting the user interface. This enables highly accurate pricing based on past data and dynamic adjustment of the interface in response to user emotions.

[1591] "Past event data" refers to all information about events that have been held in the past, including elements such as weather conditions, seating arrangements, and sales history.

[1592] "Data preprocessing" refers to a series of operations to prepare collected data into a format suitable for analysis, and includes processes such as imputation of missing values, removal of duplicate data, and normalization.

[1593] "Converting to features" refers to the step of changing raw data into an analyzable format, such as converting weather data into numerical data.

[1594] A "machine learning model" refers to an algorithm that finds patterns in data and enables future predictions and classifications, and includes regression algorithms and decision tree algorithms.

[1595] "Verification of analysis results" refers to the process of evaluating how accurate the generated machine learning model is, and methods such as cross-validation are used.

[1596] "Predicting ticket prices" refers to the process of calculating the optimal price based on new event information, utilizing historical data and machine learning models.

[1597] "Outputting and adjusting pricing" refers to a function that displays predicted prices in the user interface, allowing users to change prices as needed.

[1598] "Confirming and saving pricing" refers to the process of recording the final determined ticket price in the system's database.

[1599] "Emotional recognition" refers to a function that reads the user's emotional state from their facial expressions, voice tone, gestures, etc., and analyzes it in real time.

[1600] "Dynamically adjusting the user interface" refers to the process of adapting the system's display and operation methods in real time according to the user's emotional state.

[1601] This invention relates to a system that optimizes seat pricing for small and medium-sized events by utilizing past event data. This system collects past event data, creates a machine learning model based on it, predicts seat pricing for new events based on the analysis results, and finally provides a series of processes for the user to confirm, adjust, and finalize pricing. Furthermore, the invention provides interaction tailored to the user's emotional state by combining it with an emotion engine that recognizes the user's emotions.

[1602] Data acquisition methods

[1603] The server collects data from past events. This data includes weather conditions, seating arrangements, and sales history. Users access the database through their terminals, retrieve the necessary information from the database, and send it to the server. The server integrates this data and stores it as a dataset for analysis.

[1604] Data preprocessing means

[1605] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. For example, if weather data is missing, it is imputed using historical mean values.

[1606] Feature transformation means

[1607] The server converts the preprocessed data into analyzable features. For example, it converts weather data into a format that is easy to apply to machine learning models, such as quantifying "sunny = 1" and "rainy = 0". This conversion allows for the integration and analysis of multiple factors.

[1608] Machine learning model creation methods

[1609] The server generates a machine learning model based on the data converted into features. This model is created using Scikit-learn, training regression and decision tree algorithms. The model learns patterns from past data and applies them to new event data to make predictions.

[1610] Means for verifying analysis results

[1611] The server verifies the model's effectiveness using cross-validation and other validation techniques. The data is split to verify the reliability of the analysis results and used as test data. Hyperparameter tuning is performed as needed to improve the model's accuracy.

[1612] Ticket price prediction method

[1613] The server predicts the optimal ticket price based on new event information. Users input new event information, such as "Winter Music Festival," through their terminals, and the server calculates the price based on that information. In this process, historical event data and generative AI models are utilized to make highly accurate predictions.

[1614] Price setting output method

[1615] The server outputs the predicted pricing to the user's terminal. The user uses the terminal to check this pricing and adjust the prices as needed. For example, the standing area price for the "Winter Music Festival" is set at 5500 yen and the seating area price at 4500 yen.

[1616] Pricing confirmation method

[1617] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the published pricing.

[1618] Embedding an emotion engine

[1619] The server incorporates an emotion engine that analyzes the user's facial expressions, voice tone, and body movements to recognize emotions. As the user interacts with the device, the server monitors their emotions in real time and dynamically adjusts the interface based on that information. For example, if the user is feeling anxious, the system will display a detailed explanation and an encouraging message to support the user.

[1620] Specific example

[1621] For example, if a user plans a new event called a "Winter Music Festival," the process would proceed as follows: The user inputs data from past events, such as a "Summer Festival," via their device, and the server collects this data. After data preprocessing and feature transformation, the server creates a generative AI model and predicts the ticket price for the new event based on that model. The price setting is output to the device, and the user adjusts it as needed to finalize the price. The server saves this setting in a database and publishes it in conjunction with the ticket sales system. Furthermore, an emotion engine monitors the user's emotions in real time and provides interactions that respond to the user's emotions.

[1622] This system will not only enable the optimal seat pricing that maximizes revenue by utilizing past data even for small and medium-sized events, but will also allow for the provision of services that respond to user emotions.

[1623] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1624] Step 1: Data Collection

[1625] The server collects historical event data. The user, via their terminal, instructs the server to retrieve this data from the database. The server executes SQL queries to the database, retrieving information such as weather conditions, seating arrangements, and sales history. This data is then sent to the server for integration.

[1626] Input: Event name submitted by the user (e.g., "Summer Festival", "Spring Carnival")

[1627] Output: Integrated data on weather conditions, seating arrangements, and sales history.

[1628] Specific actions:

[1629] The user enters the event name, such as "Summer Festival" or "Spring Carnival," from their device.

[1630] The server uses SQL queries to retrieve relevant information from the database.

[1631] The server integrates the acquired information and saves it as a dataset for analysis.

[1632] Step 2: Data Preprocessing

[1633] The server preprocesses the collected data. This preprocessing step uses the Pandas library to impute missing values, remove duplicate data, and normalize the data. The collected data is then converted into a format suitable for analysis.

[1634] Input: Integrated event data

[1635] Output: Preprocessed data

[1636] Specific actions:

[1637] The server creates a dataframe using the Pandas library.

[1638] Missing data is imputed with historical averages.

[1639] Remove duplicate data and maintain consistent data.

[1640] The data is normalized to a range of 0 to 1 and converted into an analyzable format.

[1641] Step 3: Feature transformation

[1642] The server converts the preprocessed data into analyzable features. This feature conversion includes processes such as converting categorical data into numerical data. For example, weather data is converted to "sunny = 1" and "rainy = 0".

[1643] Input: Preprocessed data

[1644] Output: Data converted into features

[1645] Specific actions:

[1646] Convert categorical data such as weather data into numerical data.

[1647] The server uses Pandas to generate multiple features.

[1648] Step 4: Create a machine learning model

[1649] The server generates machine learning models using the data converted into features. It uses Scikit-learn to train regression and decision tree algorithms. The models learn patterns from past data and make predictions with new event data.

[1650] Input: Data converted into features

[1651] Output: Trained machine learning model

[1652] Specific actions:

[1653] Splitting data into training and test phases using the scikit-learn library

[1654] Train random forest and regression models and evaluate their prediction accuracy.

[1655] Hyperparameter tuning as needed

[1656] Step 5: Verification of analysis results

[1657] The server uses cross-validation and other verification methods to verify the effectiveness of the generated model. The reliability of the analysis results is evaluated, and the model is re-evaluated using test data to confirm its accuracy.

[1658] Input: Trained machine learning model

[1659] Output: Validated models and their accuracy evaluation

[1660] Specific actions:

[1661] The server divides the data into k subsets and performs cross-validation.

[1662] Train the model on each subset and test it on the remaining subsets.

[1663] The model's accuracy and reliability are verified on average, and tuning is performed if necessary.

[1664] Step 6: Predicting Ticket Prices

[1665] The server uses a generative AI model to predict the optimal ticket price based on new event information. When a user enters new event information from their device, the server calculates the price based on that information.

[1666] Input: New event information (e.g., "Winter Music Festival")

[1667] Output: Predicted ticket price

[1668] Specific actions:

[1669] Users enter new event information via their devices.

[1670] The server inputs new information into an AI model to predict the cost.

[1671] We predict the standing area ticket price will be 5500 yen and the seated area ticket price will be 4500 yen.

[1672] Step 7: Output pricing settings

[1673] The server outputs the predicted charges to the user's terminal. The user reviews these charges and adjusts them as needed.

[1674] Input: Predicted ticket price

[1675] Output: Adjustable pricing

[1676] Specific actions:

[1677] The server sends the predicted charges information to the user's terminal.

[1678] The user checks the price and adjusts the standing area price, for example, from 5500 yen to 5000 yen.

[1679] Step 8: Confirm pricing

[1680] The user finalizes the pricing, and the server saves this information to a database. The server then uses an API to connect with the ticket sales system and reflect the pricing changes.

[1681] Input: Final adjusted pricing

[1682] Output: Finalized pricing and the database reflecting it.

[1683] Specific actions:

[1684] The user finalizes the pricing.

[1685] The server stores pricing information in the database.

[1686] The server uses an API to connect with the ticket sales system.

[1687] Step 9: Integrating the Emotion Engine

[1688] The server uses an emotion engine to analyze sensor information that recognizes the user's emotions. As the user operates the device, it monitors their emotions in real time and dynamically adjusts the interface based on that information.

[1689] Input: User's facial expressions, voice tone, and body movements

[1690] Output: Dynamic adjustment of the user interface

[1691] Specific actions:

[1692] The server analyzes the user's facial expressions and voice tone using sensors.

[1693] When a user feels anxious, detailed help information and encouraging messages are displayed.

[1694] This enables highly accurate pricing based on historical data and dynamic adjustments to the interface in response to user emotions.

[1695] (Application Example 2)

[1696] 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".

[1697] For small to medium-sized events, it is difficult to determine optimal seating rates by utilizing past event data. Furthermore, the pricing process often lacks support that considers user emotions, leading to user anxiety and questions. Therefore, a system is needed that allows for efficient and reassuring pricing.

[1698] 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. In this invention, the server includes means for collecting data of past events, means for preprocessing the collected data and converting it into features, means for creating a machine learning model using the preprocessed data and verifying the analysis results, means for predicting ticket prices based on new event information, means for outputting the predicted price setting and adjusting it as necessary, means for determining the final price setting and saving it to the system, means for recognizing the user's emotions in real time, and means for dynamically adjusting the interface according to the user's emotions. This enables optimal seat pricing using past event data, as well as support that responds to the user's emotions.

[1699] "Past event data" refers to a collection of information about events held in the past, specifically including data such as weather conditions, seating layout, and sales performance.

[1700] "Data preprocessing" is the process of converting collected data into a format suitable for analysis, and includes tasks such as imputing missing values, removing duplicate data, and normalizing the data.

[1701] "Features" are attributes or properties of data used to apply to machine learning models, and are used to predict new information.

[1702] A "machine learning model" is a type of algorithm that learns data trends and patterns from large amounts of data and uses that learning to make predictions and classifications on new data.

[1703] A "ticket price prediction method" is a method for calculating the optimal seat price based on new event information, and it uses a machine learning model to make predictions.

[1704] "User emotion recognition means" refers to technology that analyzes the user's facial expressions, voice tone, body gestures, etc., to recognize the user's emotional state in real time.

[1705] "Dynamic interface adjustment" means changing the system's interface and display content in real time according to the user's emotional state.

[1706] "Verification of analysis results" refers to evaluating the analysis results using test data in order to confirm the performance and effectiveness of a machine learning model.

[1707] "Finalizing pricing" refers to the process of determining the final pricing and saving that information in the system.

[1708] This invention is a system that optimizes seat pricing for small and medium-sized events by utilizing past event data, and further recognizes user emotions in real time to dynamically adjust the interface. This system is implemented using specific hardware and software.

[1709] 1. System Configuration

[1710] The server includes means that have the following functions:

[1711] Data collection method: Collect past event data. This includes weather conditions, seating layout, sales performance, etc.

[1712] Data preprocessing means: The collected data is preprocessed to impute missing values, remove duplicate data, and normalize the data.

[1713] Feature transformation means: Converts preprocessed data into analyzable features.

[1714] Machine learning model creation method: Create a machine learning model based on features and use a regression model or random forest.

[1715] Method for verifying analysis results: The accuracy of the analysis results is verified using cross-validation.

[1716] Ticket price prediction method: Predicts the optimal ticket price based on new event information.

[1717] Pricing output method: Predicts the pricing and allows the user to adjust it.

[1718] Pricing confirmation method: Confirm the final pricing and save it in the system.

[1719] Emotion recognition means: Recognizes the user's emotions in real time using a camera or voice input device.

[1720] Dynamic interface adjustment means: The interface is dynamically adjusted based on information obtained by the emotion recognition means.

[1721] 2. Hardware and software required for implementation

[1722] Specific examples of the hardware and software used are as follows:

[1723] Hardware: Server, camera, microphone, user terminal (smartphone or PC)

[1724] Software: Python, Pandas, Scikit-learn, EmotionEngine (a virtual emotion recognition module)

[1725] 3. Data processing and data calculation

[1726] The server processes the data in the following order:

[1727] Data collection: Retrieve past event data from the database.

[1728] Data preprocessing: Use the Pandas library to impute missing values ​​and normalize the collected data.

[1729] Feature transformation: Converts data such as weather and seating layout into numerical data.

[1730] Machine learning model creation: Create a machine learning model using Scikit-learn.

[1731] Model validation: Evaluate the accuracy of the model using cross-validation.

[1732] Price Prediction: Input new event information and use a machine learning model to predict the optimal price.

[1733] Emotion Recognition: EmotionEngine is used to analyze user emotions using data obtained from the camera and microphone.

[1734] Dynamic interface adjustment: The interface changes according to the user's emotional state.

[1735] 4. Specific examples and prompt statements

[1736] For example, when a user plans a "winter music festival," they input data from past events such as "summer festivals" into the system. The server then predicts the optimal seating price for the new event through processes such as data collection, data preprocessing, feature transformation, and machine learning model creation. The predicted pricing is then presented to the user, allowing them to confidently set prices based on sentiment recognition.

[1737] Example of a prompt:

[1738] Based on past event data, please determine the optimal seating price for a winter music festival. Please provide detailed information, including weather, seating layout, and sales performance. Also, please explain how you can address any concerns users may have.

[1739] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1740] Step 1:

[1741] The server collects historical event data from the database. Specifically, it queries data such as weather conditions, seating layout, and sales performance, and retrieves the results. The input is the query conditions for the event data, and the output is the collected historical event data.

[1742] Step 2:

[1743] The server-collected data is preprocessed using the Pandas library. Specifically, missing value imputation, duplicate data removal, and normalization are performed. The input is the collected event data, and the output is the preprocessed data.

[1744] Step 3:

[1745] The server converts pre-processed data into features. Specifically, it converts data such as weather and seating layout into numerical data. The input is pre-processed data, and the output is data converted into features.

[1746] Step 4:

[1747] The server uses Scikit-learn to create machine learning models. Specifically, it trains them using regression models or random forests. The input is data transformed into features and their corresponding labels, and the output is the trained machine learning model.

[1748] Step 5:

[1749] The server uses cross-validation to validate the model. Specifically, it evaluates the accuracy of the trained model and confirms that the model works correctly. The input is the trained machine learning model and test data, and the output is the model's accuracy evaluation result.

[1750] Step 6:

[1751] The user enters new event information from a terminal. Specifically, the user enters details of the new event (e.g., weather conditions, seating layout, expected sales figures, etc.) into the terminal. The input is the new event information, and the output is the display of the entered event information on the terminal screen.

[1752] Step 7:

[1753] The server predicts ticket prices based on new event information. Specifically, it uses a trained machine learning model to calculate the optimal seat price. The input is the new event information and the trained model, and the output is the predicted ticket price.

[1754] Step 8:

[1755] The server outputs the predicted price to the user's terminal. The input is the predicted ticket price, and the output is the price displayed on the user's terminal.

[1756] Step 9:

[1757] The user reviews the predicted price displayed on their device and makes adjustments as needed. Specifically, the user views the predicted price and changes or modifies it. The input is the predicted price, and the output is the price adjusted by the user.

[1758] Step 10:

[1759] The server saves the final pricing to the system. Specifically, it saves the confirmed pricing to the database and prepares it for integration with the ticket sales system. The input is the final pricing adjusted by the user, and the output is the pricing information stored in the database.

[1760] Step 11:

[1761] The server uses EmotionEngine to recognize the user's emotions in real time. Specifically, it analyzes data acquired from cameras and microphones to determine the user's emotional state. The input is data obtained from cameras and microphones, and the output is the real-time emotion recognition result.

[1762] Step 12:

[1763] The server dynamically adjusts the interface based on the user's emotional state. Specifically, if the user is feeling anxious or confused, the system provides detailed explanations or additional support information. The input is real-time emotion recognition results, and the output is a dynamically adjusted interface.

[1764] 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.

[1765] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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."

[1773] 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.

[1774] 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.

[1775] 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.

[1776] 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.

[1777] 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.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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.

[1785] The following is further disclosed regarding the embodiments described above.

[1786] (Claim 1)

[1787] Means of collecting data from past events,

[1788] A means of preprocessing the collected data and converting it into features,

[1789] A means of creating a machine learning model using preprocessed data and verifying the analysis results,

[1790] A method for predicting ticket prices based on new event information,

[1791] A means to output predicted pricing and adjust it as needed,

[1792] A means to finalize the pricing and save it in the system,

[1793] A system that includes this.

[1794] (Claim 2)

[1795] The system according to claim 1, which includes data on past events such as weather, seating layout, and sales performance.

[1796] (Claim 3)

[1797] The system according to claim 1, wherein the machine learning model is a regression model or a random forest.

[1798] "Example 1"

[1799] (Claim 1)

[1800] Means of collecting data from past events,

[1801] A means of preprocessing the collected data and converting it into features,

[1802] A means of creating a machine learning model using preprocessed data and verifying the analysis results,

[1803] A method for predicting ticket prices based on new event information,

[1804] A means of outputting predicted pricing and adjusting the settings as needed,

[1805] A means to finalize the pricing and save it in the system,

[1806] A means of reflecting settings in conjunction with the ticket sales system,

[1807] A system that includes this.

[1808] (Claim 2)

[1809] The system according to claim 1, wherein past event data includes weather conditions, seating arrangements, and sales performance.

[1810] (Claim 3)

[1811] The system according to claim 1, wherein the machine learning model is a predictive model or a decision tree.

[1812] "Application Example 1"

[1813] (Claim 1)

[1814] Means of collecting data from past events,

[1815] A means of preprocessing the collected data and converting it into features,

[1816] A means of creating a machine learning model using preprocessed data and ve...

Claims

1. Means of collecting data from past events, A means of preprocessing the collected data and converting it into features, A means of creating a machine learning model using preprocessed data and verifying the analysis results, A method for predicting ticket prices based on new event information, A means to output predicted pricing and adjust it as needed, A means to finalize the pricing and save it in the system, A system that includes this.

2. The system according to claim 1, wherein past event data includes weather, seating layout, and sales performance.

3. The system according to claim 1, wherein the machine learning model is a regression model or a random forest.

Images