System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting fan behavior data; means for pre-processing the collected data; means for analyzing the pre-processed data with an artificial intelligence model; means for generating insights based on the analysis; and means for displaying the generated insights.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The challenge is to effectively collect and analyze data on fan interests and behavior at race events and provide personalized fan experiences to improve the engagement and loyalty of event participants. Conventional methods have made it difficult to efficiently collect and analyze this data, resulting in a lack of services tailored to fan preferences. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for collecting fan behavior data, a means for preprocessing the collected data, a means for analyzing the preprocessed data using an artificial intelligence model, a means for generating insights based on the analysis results, and a means for displaying the generated insights. Specifically, the system collects fan location information and behavior data in real time, ensures data quality through preprocessing, and then analyzes the data in detail using artificial intelligence to generate personalized insights and provide them to event organizers and teams. This enables customized services and promotions based on the interests and behavior of individual fans, thereby improving fan engagement.

[0006] "Fan behavior data" refers to the actions taken by fans at the event venue and various data collected during that process, including location information, length of stay, places visited, purchase history, etc.

[0007] "Preprocessing" refers to the process of organizing collected raw data into an analyzable format, and specifically includes filling in missing values, correcting outliers, and standardizing data.

[0008] "Artificial intelligence model" refers to machine learning algorithms and data analysis methods used to analyze collected data, find patterns, and generate insights.

[0009] "Insights" refers to the insights and findings obtained as a result of data analysis, and is information that provides event organizers and teams with the basis for developing fan engagement strategies.

[0010] "Display means" refers to devices or software for visually displaying analysis results and generated insights, specifically systems and screen display methods including dashboards, graphs, charts, etc. [Brief explanation of the drawings]

[0011] [Figure 1]1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0031] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0032] The present invention is a system that collects and analyzes fan behavior data and provides customized insights to event organizers and teams based on the results. This system is realized through the collaboration of a server, terminals, and users.

[0033] Data collection

[0034] The server collects data in real time from sensors placed at the event venue and from mobile apps used by fans. Specifically, this data includes location information, places visited, length of stay, and purchase history. The devices, such as fans' smartphones and tablets, automatically record location information and behavioral data and send it to the server. Users (fans) grant permission for data collection through the app as they move around the event venue.

[0035] Data Preprocessing

[0036] The server preprocesses the collected raw data, including imputing missing values, correcting outliers, and standardizing the data to ensure data quality and convert it into a format suitable for analysis.

[0037] Data analysis

[0038] The server then feeds the pre-processed data into an artificial intelligence model, which uses machine learning algorithms to analyze the data and identify fan behavior patterns and preferences. For example, it determines that fans who spend a lot of time in a particular area are likely to be interested in services and promotions related to that area.

[0039] Insight generation

[0040] Based on the analysis, the server generates customized insights, including recommended actions and marketing strategies for specific fan segments. For example, an insight could be, "This fan segment is interested in food stands, so we'll offer special food promotions at our next event."

[0041] Visualizing and presenting results

[0042] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams. The terminal displays these visualizations so that users can easily understand them. Users (event organizers and teams) can use these insights to optimize their event operations and marketing strategies.

[0043] Specific examples

[0044] For example, suppose the following data is collected at a race event:

[0045] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[0046] Based on this data, the server generates insights such as:

[0047] Fans around Stand B are very interested in the food stands.

[0048] At your next event, it would be beneficial to run a special food promotion around Stand B.

[0049] This allows event organizers and teams to improve fan engagement by providing personalized services based on fan preferences and behavior.

[0050] The processing flow will be explained below.

[0051] Step 1:

[0052] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically via HTTP requests and APIs to obtain real-time data such as location information, visited locations, and duration of stay.

[0053] Step 2:

[0054] The device collects data from fans' smartphones or tablets through an app and sends it to a server. Users consent to location sharing within the app, and the collection is applied.

[0055] Step 3:

[0056] The server preprocesses the collected raw data by imputing missing values, correcting outliers, and standardizing the data to convert it into a format suitable for analysis. Specifically, it applies preprocessing techniques including data cleansing, filtering, and scaling.

[0057] Step 4:

[0058] The server then feeds the pre-processed data into an artificial intelligence model for analysis. Machine learning algorithms are used to analyze the data and identify fan behavior patterns and preferences, often using clustering and classification techniques.

[0059] Step 5:

[0060] The server generates insights based on the analysis, which include recommended actions and marketing strategies based on fan interests, such as suggesting campaigns targeted to fan groups interested in specific locations.

[0061] Step 6:

[0062] The server visualizes the generated insights in the form of graphs and charts, and uses data visualization tools to display the insights in an intuitive and easy-to-understand way.

[0063] Step 7:

[0064] The device displays visualized insights that can be viewed by event organizers and teams, who can then use these insights to optimize their event operations and marketing strategies.

[0065] Specific examples

[0066] For example, the following data is collected at a race event:

[0067] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[0068] After going through steps 1 to 7, the server generates the following insight and displays it on the device:

[0069] Fans around Stand B are very interested in the food stands.

[0070] At your next event, it would be beneficial to run a special food promotion around Stand B.

[0071] This allows event organizers and teams to offer personalized services based on fan preferences and behavior, improving fan engagement.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] In conventional event management, there were few ways to effectively collect visitor behavior data and gain customized insights based on that data. As a result, it was difficult to accurately understand visitor needs and implement effective marketing strategies and services based on those needs. This led to issues such as insufficient improvement of event satisfaction and participant engagement.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for collecting visitor behavior data at an event, means for preprocessing the collected data, means for analyzing the preprocessed data using a machine learning algorithm, means for generating customized insights based on the analysis results, and means for displaying the generated insights as graphs or charts. This makes it possible to effectively collect and analyze visitor behavior data and provide customized insights based on the results. This allows event organizers to accurately understand visitor needs and implement effective marketing strategies and service provision based on those needs, significantly improving event satisfaction and participant engagement.

[0077] "Behavioral data" refers to data such as a visitor's location, the places they visited, the length of their stay, and their purchase history.

[0078] "Data preprocessing" refers to the process of imputing missing values, correcting outliers, and standardizing collected raw data.

[0079] A "machine learning algorithm" is an algorithm that learns patterns based on past data and makes predictions and classifications for future data.

[0080] "Customized insights" are specific suggestions based on analysis results, such as recommended actions and marketing strategies for specific visitor groups.

[0081] "Graphs and charts" are shapes that visually represent collected and analyzed data and generated insights.

[0082] "Event Organizer" means the person or entity responsible for planning, conducting and managing an Event.

[0083] This invention is a system that collects and analyzes visitor behavior data and provides customized insights based on the results, and is realized through the collaboration of servers, terminals, and users.

[0084] Data collection

[0085] The server collects real-time data from multiple sensors placed around the event venue. These sensors include Bluetooth beacons and Wi-Fi access points. These sensors communicate with visitors' smartphones to obtain location information. Mobile apps used by visitors also send data to the server. This data includes location information, locations visited, length of stay, and purchase history.

[0086] The devices are the visitors' smartphones or tablets, which use location services in the background to collect the visitor's location data. For example, when a visitor enters a certain area, the location information is automatically updated and sent to the server.

[0087] When users (visitors) arrive at the event venue, they open the mobile app and grant permission for data collection, specifically by turning on location sharing and in-app notifications.

[0088] Data Preprocessing

[0089] The server pre-processes the collected raw data, including imputing missing values, correcting outliers, and standardizing the data. Specifically, it performs the following processes:

[0090] 1. Data imputation: If some location information is missing, it is imputed using data from adjacent time intervals.

[0091] 2. Anomaly correction: If a visitor suddenly moves beyond the range of the sensor, the data will be deleted or corrected as an anomaly.

[0092] 3. Data standardization: To process collected data on a unified scale, convert coordinate data and other data into a standard format. Use a Python numerical processing library (e.g., Pandas, NumPy).

[0093] Data analysis

[0094] The server then feeds the preprocessed data into an artificial intelligence model, for example using a machine learning library such as Scikit-learn or TensorFlow, to build a model that performs the following analyses:

[0095] 1. Behavioral pattern analysis: Analyze the behavioral patterns of visitors who stay in a specific area for a long time.

[0096] 2. Preference analysis: Identify which foods visitors are interested in based on the number of times they visit the food stand and the time of day.

[0097] Insight generation

[0098] The server generates customized insights based on the data analysis results, including, for example:

[0099] 1. Generate recommended actions: Generate recommended actions for specific visitor demographics.

[0100] Example: An insight that says, "Visitors gathering around Stand G are interested in a particular beverage, so we should promote beverages in that area."

[0101] 2. Marketing strategy proposal: Propose effective measures for the next event.

[0102] Example: "At our next event, we'll be running a special food promotion around Stand B."

[0103] Visualizing and presenting results

[0104] The server visualizes the generated insights as graphs and charts, using the following tools:

[0105] 1. Tableau or Power BI: Generate graphs to visually represent behavioral patterns and preferences.

[0106] 2. Dashboard: Organize insights and present them in an easily accessible format for event organizers and teams.

[0107] The device displays these visualizations, and event organizers and teams can check various graphs and charts on the device to plan on-site measures.

[0108] Users (event organizers and teams) can use the insights provided by the server to optimize their event management and marketing strategies, specifically adjusting the placement and promotional content of their next event.

[0109] Prompt Sentence Examples

[0110] Suggest a marketing strategy for your next event based on the following behavioral data:

[0111] Fan A stayed in Stand B for 15 minutes and then went to the food stand. Use this data to provide insights into services and promotions relevant to that specific area.

[0112] The above is an embodiment of the present invention.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1: Data collection

[0115] The server collects data from sensors placed at the event venue and from mobile apps used by visitors. Input includes location information from Bluetooth beacons and Wi-Fi access points, visited locations, length of stay, and purchase history. Specifically, when a visitor enters a specific area, the sensor communicates with the smartphone and sends the location information to the server. The output is streaming location information and behavioral data.

[0116] Step 2: Data Preprocessing

[0117] The server preprocesses the collected data. The input is raw data (location information, visited locations, duration of stay, etc.). If there are missing values ​​in the data at this stage, they are filled in using data from adjacent time intervals. Outliers are removed or corrected. For example, if a visitor moves out of the sensor range at high speed, it is considered an outlier. The server also converts the collected data into a standard format. This process improves the quality of the data and makes it consistent. The output is preprocessed, clean data.

[0118] Step 3: Data analysis

[0119] The server analyzes the preprocessed data using machine learning algorithms. The input is the preprocessed dataset. Specifically, Scikit-learn and TensorFlow are used to analyze and model visitor behavior patterns. Behavior pattern analysis identifies, for example, patterns where visitors spend a long time in a particular area. Preference analysis identifies groups of visitors who may be interested in specific promotions or services. The output is the identified patterns and preference information as the analysis results.

[0120] Step 4: Insight generation

[0121] The server generates customized insights based on the analysis results. The input is the results of data analysis. Specifically, based on the analysis results, it automatically generates recommended actions and marketing strategies tailored to the visitor demographic. For example, it generates an insight that "Since many visitors gather around Stand G, we should implement a beverage promotion in this area." The output is customized insights.

[0122] Step 5: Visualize and deliver results

[0123] The server visualizes the generated insights as graphs and charts. The input is the generated customized insights. Specifically, a data visualization tool (e.g., Tableau or Power BI) is used to visually represent the analysis results, which clearly visualizes visitor behavior patterns and preferences. The terminal displays these visualizations and provides them to the user (event organizer or team) in a format that is easy to understand. The output is visualized insights based on attendee behavior patterns.

[0124] The above is a detailed description of each processing step of the system.

[0125] (Application example 1)

[0126] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0127] Conventional systems do not fully utilize behavioral data of fans and customers at event venues and brick-and-mortar stores, making it difficult to optimize personalized promotion strategies based on customer behavior patterns and preferences. Furthermore, there is a lack of means to clearly visualize the analysis results and make them specifically useful for store management.

[0128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0129] In this invention, the server includes means for collecting fan behavior data, means for preprocessing the collected data, means for analyzing the preprocessed data using an artificial intelligence model, means for generating insights based on the analysis results, and means for displaying the generated insights and providing promotion strategies, thereby enabling the development of effective promotion strategies based on customer behavior patterns and preferences and the specific visualization of the results.

[0130] "Fan behavior data" refers to data such as the location information of customers (fans) at event venues and physical stores, the places they visit, the length of their stay, and their purchase history.

[0131] "Means for preprocessing collected data" refers to means for executing processes to ensure data quality and convert the data into a format suitable for analysis, such as completing missing values ​​in the data, correcting outliers, and standardizing the data.

[0132] An "artificial intelligence model" is a model that uses machine learning algorithms and other techniques to analyze pre-processed data and identify fan behavior patterns and preferences.

[0133] "Means for generating insights" are means that have the ability to propose recommended actions and promotional strategies for specific fan groups based on the analysis results.

[0134] "Means for displaying the generated insights and providing promotion strategies" refers to means for visualizing the insights obtained through analysis in the form of graphs and charts, displaying them in a way that is easy for operators of event venues and physical stores to understand, and providing specific promotion strategies based on them.

[0135] This invention is a system that collects and analyzes behavioral data of fans and customers at event venues and brick-and-mortar stores, and provides customized promotional strategies based on that data. This system is realized primarily through the collaboration of a server, terminals, and users.

[0136] Data collection

[0137] The server collects data in real time from sensors placed at event venues and brick-and-mortar stores, as well as from mobile apps used by customers. Specifically, data such as location information, places visited, length of stay, and purchase history is collected. The devices are smartphones and tablets held by customers, which automatically record behavioral data and send it to the server. Users (customers) give permission for data collection through the app.

[0138] Data Preprocessing

[0139] The server preprocesses the collected raw data using data processing libraries such as Pandas to impute missing values, correct outliers, and standardize the data, thereby ensuring data quality and converting it into a format suitable for analysis.

[0140] Data analysis

[0141] The server then feeds the preprocessed data into an artificial intelligence model, which uses machine learning algorithms such as Scikit-learn to analyze the data and identify customer behavioral patterns and preferences. For example, if a customer spends a long time in a particular area, it can determine that they are likely interested in products and services related to that area.

[0142] Insight generation

[0143] Based on the analysis results, the server generates customized insights, including recommended actions and promotion strategies for specific customer segments. For example, an insight might be, "This customer segment is interested in the snack area, so we'll offer a special snack promotion at the next event." The insights can also be visualized using Matplotlib and displayed in graphs and charts.

[0144] Providing results

[0145] The generated insights are visualized in graphs and charts by the server and provided to event and store managers. The terminal displays these visualizations so that users can easily understand them. Users (managers) can use these insights to optimize their event and store operations and further marketing strategies.

[0146] Specific examples

[0147] For example, suppose a store collects the following data:

[0148] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[0149] Customer B stayed in the beverage area for 15 minutes.

[0150] Based on this data, the server generates insights such as:

[0151] Customers around the general goods area are very interested in snacks.

[0152] For your next store promotion, it would be effective to run a special snack promotion around the general merchandise area.

[0153] This allows event organizers and store operators to provide personalized services based on customer preferences and behavior, improving fan engagement.

[0154] Example prompts to be input to the generative AI model

[0155] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[0156] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[0157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0158] Step 1: Data collection

[0159] The server collects data in real time from sensors placed at event venues and physical stores, as well as from smartphone apps used by customers. Specifically, the data collected includes location information, visited locations, length of stay, and purchase history. The device (customer's smartphone) automatically records this data and sends it to the server. The user (customer) gives permission for data collection through the app, which then initiates data collection.

[0160] Input: Raw data from sensors and smartphone apps (location information, visit locations, stay times, purchase history)

[0161] Output: Raw behavioral data aggregated on the server

[0162] Step 2: Data Preprocessing

[0163] The server preprocesses the collected raw data by using Pandas to impute missing values, correct outliers, and standardize the collected data, thereby ensuring data quality and converting it into a format suitable for analysis.

[0164] Input: Collected raw behavioral data

[0165] Output: Preprocessed data with missing value imputation, outlier correction, and standardization

[0166] Step 3: Data analysis

[0167] The preprocessed data is fed into an artificial intelligence model by the server, which then uses machine learning algorithms such as Scikit-learn's KMeans to cluster the data and identify customer behavior patterns and preferences. The server then determines which cluster each customer's behavior data belongs to and analyzes the characteristics of each cluster.

[0168] Input: Preprocessed behavioral data

[0169] Output: Clustering results for each customer and cluster feature data

[0170] Step 4: Insight generation

[0171] The server generates customized insights based on the results of the clustering analysis. Specifically, it generates data for each cluster to suggest the level of interest in specific product areas and promotion strategies. In this process, marketing strategies are proposed based on the average values ​​and behavioral patterns of each cluster.

[0172] Input: Clustering results and cluster feature data

[0173] Output: Insights for specific customer segments (e.g., promotional strategy suggestions)

[0174] Step 5: Visualize and deliver results

[0175] The server visualizes the generated insights in the form of graphs and charts, using visualization libraries such as Matplotlib to display the insights in an easy-to-understand format. The terminal displays these visualizations so that users (event organizers and store operators) can easily understand them.

[0176] Input: Generated insights

[0177] Output: Visualized insights in the form of graphs and charts, displayed visualizations

[0178] As a concrete example, consider the following data collected at a store:

[0179] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[0180] Customer B stayed in the beverage area for 15 minutes.

[0181] Based on this data, the server generates a prompt like this:

[0182] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[0183] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[0184] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0185] The present invention is a system that collects and analyzes fan behavior data to generate insights, and combines this with an emotion engine that recognizes user emotions to provide a more accurate and customized fan experience. This system is composed of a server, terminals, and users working together.

[0186] Data collection

[0187] The server collects fan behavior data from sensors installed at the event venue and from mobile apps. Specifically, it obtains data such as location information, visited locations, and length of stay in real time. The device collects data from fans' smartphones or tablets and sends it to the server. Users (fans) give consent to share their location information and collect behavioral data through the app.

[0188] Emotional Data Collection

[0189] The server also uses an emotion engine to collect emotional data from fans. This emotional data includes emotional information obtained through voice analysis and facial expression analysis. The device transmits the data acquired through the camera and microphone to the server.

[0190] Data Preprocessing

[0191] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by imputing missing values, correcting outliers, and standardizing the data. For emotion data, it also categorizes and scores emotions.

[0192] Data analysis

[0193] The server then inputs the pre-processed data into an artificial intelligence model. The server then uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. For example, if fans who spend a long time in a particular area have positive emotions, the server determines that they are likely to be interested in services and promotions related to that area.

[0194] Insight generation

[0195] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This fan base is interested in food stands and has positive emotions, so we'll offer special food promotions at our next event."

[0196] Visualizing and presenting results

[0197] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizer or team. The device displays these visualizations, allowing the event organizer or team to easily understand the information. The user (event organizer or team) can then use these insights to optimize their event operations and marketing strategies.

[0198] Specific examples

[0199] For example, the following data is collected at a race event:

[0200] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0201] Based on this data, the server generates insights such as:

[0202] Since fans around Stand B are more interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[0203] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[0204] The processing flow will be explained below.

[0205] Step 1:

[0206] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically, data such as location information, visited locations, and length of stay in real time, and receives the data via HTTP requests and APIs.

[0207] Step 2:

[0208] The device collects location information and behavioral data from fans' smartphones or tablets and sends it to a server in real time. Users consent to the sharing of location information and the collection of behavioral data through the app.

[0209] Step 3:

[0210] The server uses an emotion engine to collect emotional data from fans. Specifically, it analyzes voice data and facial expression data from fans as they move around the venue to obtain emotional information.

[0211] Step 4:

[0212] The device captures audio and video data via the fan's smartphone or tablet and transmits this data to a server in real time.

[0213] Step 5:

[0214] The server preprocesses the collected behavioral and emotional data. Specifically, it complements missing values, corrects outliers, and standardizes the data. For emotional data, it also categorizes and scores emotions.

[0215] Step 6:

[0216] The server then feeds the pre-processed data into an artificial intelligence model for analysis, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions.

[0217] Step 7:

[0218] The server generates insights based on the analysis results, including recommended actions for specific fan groups and marketing strategies that take sentiment information into account.

[0219] Step 8:

[0220] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, while the terminal displays these visualized insights for the event organizers and teams to view and understand.

[0221] Specific examples

[0222] For example, suppose the following data is collected at a racing event:

[0223] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0224] Based on this data, the server generates insights like the following and displays them on the device:

[0225] Since fans around Stand B are highly interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[0226] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[0227] Example 2

[0228] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0229] Conventional fan experience delivery systems provide services based solely on fan behavioral data, and are unable to accurately capture fans' emotions and preferences. This has resulted in low accuracy in customizing the services and promotions provided, making it difficult to improve fan engagement. Furthermore, there is no system for centrally collecting and analyzing emotional and behavioral data, making integrated analysis of the data difficult. Given these circumstances, there is a need for an integrated collection and analysis of diverse data, including fans' emotional information, to provide highly accurate, customized fan experiences.

[0230] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting behavioral data of fans, a means for preprocessing the collected behavioral data and emotion data, and a means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to accurately grasp the behavioral patterns and emotions of fans and provide customized services to users.

[0231] "Behavioral data" refers to data that indicates how fans behaved within the event venue, such as their location, the places they visited, and the length of their stay.

[0232] "Emotional data" is data that indicates the emotional state of fans, obtained through voice analysis and facial expression analysis.

[0233] "Preprocessing" refers to the process of converting the collected raw data and emotion data into a format suitable for analysis by complementing missing values, correcting outliers, and standardizing them.

[0234] An "artificial intelligence model" is a model that uses algorithms such as machine learning and deep learning to analyze input data and extract patterns and features.

[0235] "Insights" are insights and recommended actions related to fan behavior and sentiment generated based on the analysis results.

[0236] "Sensors" are devices installed at event venues to collect fan behavior data. Examples include Wi-Fi beacons and GPS.

[0237] A "mobile app" is application software that fans install and use on their smartphones or tablets, and collects behavioral and emotional data.

[0238] "Terminal" refers to a mobile information terminal such as a smartphone or tablet held by a fan, which collects data and transmits it to the server.

[0239] "Data analysis" is the process of feeding pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions.

[0240] "Visualization" is a technique that makes information easier to understand visually by displaying the generated insights in the form of graphs and charts.

[0241] The present invention is a system for generating insights by collecting and analyzing behavioral data and emotional data of fans. This system is mainly composed of a server, terminals, and users working together. Specific embodiments of the system are described below.

[0242] Data collection

[0243] The server collects real-time behavioral data, such as location, visit locations, and duration of stay, from sensors installed at the event venue and mobile apps. Sensors such as Wi-Fi beacons and GPS can be used to determine which areas fans were in and how long they stayed there. For example, the server receives Wi-Fi beacon signals and updates the fan's location information.

[0244] The device sends data acquired from sensors and apps via the fan's smartphone or tablet to a server. The mobile app collects location and behavioral data at regular intervals and sends it to the server using the HTTPS protocol. When the user (fan) launches the app for the first time, they give consent to share their location information and collect behavioral data.

[0245] Emotional Data Collection

[0246] The server uses an emotion engine to analyze data collected from the device's camera and microphone to obtain emotional information about the fan. The camera captures facial expressions, and the microphone collects audio data. For example, the device's camera captures the user's facial expressions at regular intervals, while simultaneously collecting and sending audio data to the server.

[0247] The device sends this data to a server, which then uses voice and facial expression analysis to estimate emotions. Voice analysis extracts features such as pitch, tempo, and volume from the voice data, while facial expression analysis detects facial features to classify emotions.

[0248] Data Preprocessing

[0249] The server complements missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data. For example, if part of the location data is missing, it is complemented using an interpolation algorithm based on the preceding and following data. Furthermore, if an extremely high emotion score is obtained, it is clipped at an upper threshold.

[0250] The server also converts the preprocessed data into a format suitable for analysis, for example by scaling the sentiment scores to a range from 0 to 1.

[0251] Data analysis

[0252] The server then inputs the pre-processed data into an AI model to analyze fan behavior patterns, preferences, and emotions. Machine learning algorithms are used to analyze the data and identify common fan preferences and behavior patterns. For example, it can identify groups of fans who spend a long time in the same area and exhibit positive emotions.

[0253] Insight generation

[0254] The server generates customized insights based on the analysis results, such as "This fan base is interested in food stands and has positive sentiment," which provides useful recommended actions and marketing strategies for event organizers and teams.

[0255] Visualizing and presenting results

[0256] The server visualizes the generated insights in the form of graphs and charts and provides them to event organizers and teams using libraries such as Matplotlib and D3.js. The terminal displays these visualizations, allowing event organizers and teams to easily understand the information.

[0257] Specific examples

[0258] For example, the following data is collected at a race event:

[0259] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0260] Based on this data, the server generates insights such as:

[0261] Fans around Stand B are more interested in food stands and have positive feelings about them, so it would be effective to run a special food promotion at the next event.

[0262] Examples of prompt statements

[0263] Examples of prompts for a generative AI model might include:

[0264] "Based on the data collected during the event, could you please tell us the results of your analysis of the relationship between the amount of time fans spent in a specific area and their emotional scores?"

[0265] This allows the AI ​​model to generate specific insights.

[0266] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0267] Step 1:

[0268] Data collection

[0269] The server collects real-time behavioral data such as location, visited locations, and length of stay from sensors installed at the event venue and mobile apps.

[0270] Input: Location information from sensors, behavioral data from mobile apps.

[0271] Data processing: Receives Wi-Fi beacon and GPS data and records fans' location information and time spent there.

[0272] Output: Recorded behavioral data.

[0273] How it works: The server periodically receives signals from sensors and stores the data in a database. For example, when a fan enters a specific area, it logs their location based on information received from Wi-Fi beacons.

[0274] Step 2:

[0275] Data transmission via fan terminals

[0276] The device transmits data obtained from sensors and apps to a server via the fan's smartphone or tablet.

[0277] Input: Location and behavioral data collected on the device.

[0278] Data processing: Data is batch processed at regular intervals and sent to the server using the HTTPS protocol.

[0279] Output: Behavioral data sent to the server.

[0280] Specific operation: The app sets the collection timing to every minute and sends behavioral data to the server each time, allowing data to be accumulated on the server in real time.

[0281] Step 3:

[0282] Obtaining User Consent

[0283] Users (fans) use the mobile app to give consent to share location information and collect behavioral data.

[0284] Input: The consent screen that appears when the app is first launched.

[0285] Data processing: Data collection will only begin once consent has been obtained.

[0286] Output: Data collection settings based on consent.

[0287] Specific behavior: When the app is launched for the first time, a pop-up regarding location usage and data collection will be displayed, and data collection will not begin until the user presses the consent button.

[0288] Step 4:

[0289] Emotional Data Collection

[0290] The server analyzes emotional information using data collected from the device's camera and microphone.

[0291] Input: Audio and image data sent from the device.

[0292] Data processing: Conduct voice analysis and facial expression analysis to estimate emotions.

[0293] Output: Sentiment score.

[0294] How it works: The device camera captures the user's face and the microphone collects their voice. These data are sent to the server in real time or in batches, and the emotion engine calculates an emotion score.

[0295] Step 5:

[0296] Data Preprocessing

[0297] The server imputes missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data.

[0298] Input: location data, behavioral data, emotion data.

[0299] Data processing: imputation of missing values, correction of outliers, standardization processing.

[0300] Output: Preprocessed data.

[0301] Specific operation: If there are gaps in the location information data, it will be interpolated based on the previous and following data. If an abnormally high value is found in the emotion score, it will be corrected by an upper threshold. This prepares the data in a state suitable for analysis.

[0302] Step 6:

[0303] Data analysis

[0304] The server then feeds the pre-processed data into an AI model to identify fan behavior patterns, preferences, and emotions.

[0305] Input: Preprocessed behavioral and emotional data.

[0306] Data processing: Analysis using machine learning algorithms.

[0307] Output: Analysis results (behavioral patterns, preferences, emotions).

[0308] Specific behavior: Using clustering techniques, we identify groups of fans with similar behavioral patterns, such as fans who spend a long time in the same area and show positive emotions.

[0309] Step 7:

[0310] Insight generation

[0311] The server generates customized insights based on the analysis results.

[0312] Input: Analysis results.

[0313] Data processing: Generating insights.

[0314] Output: Insights (recommended actions, marketing strategies).

[0315] What happens: Based on the analysis results, we can generate insights such as "This fan base is interested in food stands and has positive sentiments," which can then be used to plan special promotions for the next event.

[0316] Step 8:

[0317] Visualizing and presenting results

[0318] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, and the terminals display these visualizations.

[0319] Input: Generated insights.

[0320] Data processing: Visual content generation.

[0321] Output: The displayed graphs and charts.

[0322] Specific operation: Using libraries such as Matplotlib and D3.js, insights are displayed as timelines, heat maps, bar graphs, etc. In the mobile app on the device, this data is displayed on a dashboard and can be manipulated interactively.

[0323] (Application example 2)

[0324] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0325] Traditional fan engagement systems rely solely on behavioral data and are unable to grasp fan sentiment in real time, making it difficult to provide personalized fan experiences. Furthermore, the insights gained from analyzing the collected data are limited and lacking in accuracy. This makes them lack the ability to provide customized services based on fans' interests and emotions.

[0326] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting behavioral data and emotional data of fans, means for preprocessing the collected data, and means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to comprehensively analyze the behavior and emotions of fans and provide users with personalized recommended actions and marketing strategies based on the obtained insights.

[0327] "Behavioral Data" refers to data related to the behavior of fans or users, such as their physical location, visited pages, and duration of stay.

[0328] "Emotional data" is emotional information obtained through voice analysis and facial expression analysis of fans and users, and is data that indicates their emotional state, such as positive or negative.

[0329] "Preprocessing" refers to a series of processes such as data imputation, outlier correction, and standardization to convert collected raw data into a format suitable for analysis.

[0330] An "artificial intelligence model" is a model that uses machine learning and data analysis algorithms to analyze data and derive specific patterns and insights.

[0331] "Insights" are useful knowledge and discoveries obtained based on analyzed data, and are information that can be used to recommend actions and guide marketing strategies that are valuable to users.

[0332] "Personalized recommendations" are customized suggestions for services and promotions based on the individual behavioral patterns and emotional data of fans and users.

[0333] A "marketing strategy" refers to plans and actions designed to increase sales and customer satisfaction, taking into account the preferences and emotions of fans and users.

[0334] "Visualization" is the process of displaying analyzed data and insights in visual formats such as graphs and charts to make them easier to understand.

[0335] This invention is a system that collects and analyzes fan behavioral and emotional data to provide users with a customized fan experience. This system is realized primarily through collaboration between a server, terminals, and users.

[0336] Data collection

[0337] The server collects behavioral and emotional data from fans via sensors and mobile applications installed at event venues and virtual stores. Specifically, in addition to behavioral data such as fans' location, visited pages, and length of stay, it also uses smartphone cameras and microphones to analyze facial expressions and voices to obtain emotional data.

[0338] The terminal (e.g., a smartphone) is a device carried by the fan through which data is collected. An application on the terminal accesses the camera and microphone and transmits the data in real time to a server.

[0339] By using the application, users (fans) agree to the sharing of their location information and the collection of behavioral data, and enjoy the experience within the application.

[0340] Data Preprocessing

[0341] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by interpolating missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[0342] Data analysis

[0343] The pre-processed data is then fed into an artificial intelligence model by a server, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. The server then uses a machine learning platform such as Google Cloud AI Platform to perform the analysis.

[0344] Insight generation

[0345] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This user is interested in electronics and has positive emotions, so we recommend related accessories."

[0346] Visualizing and presenting results

[0347] The generated insights are visualized by the server in the form of graphs and charts and displayed within the user's smartphone application, allowing the user to easily understand the personalized recommended actions and enjoy the experience.

[0348] Specific examples

[0349] For example, if a user spends 15 minutes in the "electronics" section of a virtual store and displays positive emotions, the "related accessories" section will be recommended next.

[0350] Example prompt sentence:

[0351] Thanks for your attention! We understand you're interested in electronics. Why not take a look at some related accessories next?

[0352] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0353] Step 1:

[0354] Data collection

[0355] The device collects behavioral and emotional data from fans. Specifically, the smartphone application accesses the camera and microphone to capture location information, visited pages, time spent on the device, voice and facial expressions.

[0356] Inputs include location information from the smartphone's sensors, video data from the camera, and audio data from the microphone.

[0357] The output is the raw behavioral and emotional data collected.

[0358] Step 2:

[0359] Data transmission

[0360] The device sends the collected raw data to a server, where an application encrypts the data and sends it to the server over the Internet.

[0361] The input is raw behavioral and emotional data collected on the device.

[0362] The output is raw behavioral and emotional data sent to a server.

[0363] Step 3:

[0364] Data Preprocessing

[0365] The server preprocesses the collected raw data, including filling in missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[0366] The input is raw behavioral and emotional data sent from the device.

[0367] The output is the pre-processed data.

[0368] Step 4:

[0369] Data analysis

[0370] The server then feeds the pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions. Specifically, the data is analyzed using machine learning platforms such as Google Cloud AI Platform.

[0371] The input is preprocessed data.

[0372] The output is analysis results such as behavioral patterns, preferences, and emotional data.

[0373] Step 5:

[0374] Insight generation

[0375] The server generates customized insights based on the analysis results, specifically recommended actions and marketing strategies based on specific patterns and sentiments.

[0376] The input is behavioral patterns, preferences, and emotional data obtained from data analysis.

[0377] The output is the insight generated.

[0378] Step 6:

[0379] Visualizing and presenting results

[0380] The server visualizes the generated insights in the form of graphs and charts and sends them to the device, which displays the visualized insights in a smartphone application and provides the user with personalized recommended actions and marketing strategies.

[0381] The input is the generated insight.

[0382] The output is a recommended action or marketing strategy that is displayed within the smartphone application.

[0383] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0384] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0385] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0386] [Second embodiment]

[0387] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0388] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0389] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0390] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0391] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0392] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0393] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0394] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0395] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0396] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0397] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0398] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0399] The present invention is a system that collects and analyzes fan behavior data and provides customized insights to event organizers and teams based on the results. This system is realized through the collaboration of a server, terminals, and users.

[0400] Data collection

[0401] The server collects data in real time from sensors placed at the event venue and from mobile apps used by fans. Specifically, this data includes location information, places visited, length of stay, and purchase history. The devices, such as fans' smartphones and tablets, automatically record location information and behavioral data and send it to the server. Users (fans) grant permission for data collection through the app as they move around the event venue.

[0402] Data Preprocessing

[0403] The server preprocesses the collected raw data, including imputing missing values, correcting outliers, and standardizing the data to ensure data quality and convert it into a format suitable for analysis.

[0404] Data analysis

[0405] The server then feeds the pre-processed data into an artificial intelligence model, which uses machine learning algorithms to analyze the data and identify fan behavior patterns and preferences. For example, it determines that fans who spend a lot of time in a particular area are likely to be interested in services and promotions related to that area.

[0406] Insight generation

[0407] Based on the analysis, the server generates customized insights, including recommended actions and marketing strategies for specific fan segments. For example, an insight could be, "This fan segment is interested in food stands, so we'll offer special food promotions at our next event."

[0408] Visualizing and presenting results

[0409] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams. The terminal displays these visualizations so that users can easily understand them. Users (event organizers and teams) can use these insights to optimize their event operations and marketing strategies.

[0410] Specific examples

[0411] For example, suppose the following data is collected at a race event:

[0412] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[0413] Based on this data, the server generates insights such as:

[0414] Fans around Stand B are very interested in the food stands.

[0415] At your next event, it would be beneficial to run a special food promotion around Stand B.

[0416] This allows event organizers and teams to improve fan engagement by providing personalized services based on fan preferences and behavior.

[0417] The processing flow will be explained below.

[0418] Step 1:

[0419] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically via HTTP requests and APIs to obtain real-time data such as location information, visited locations, and duration of stay.

[0420] Step 2:

[0421] The device collects data from fans' smartphones or tablets through an app and sends it to a server. Users consent to location sharing within the app, and the collection is applied.

[0422] Step 3:

[0423] The server preprocesses the collected raw data by imputing missing values, correcting outliers, and standardizing the data to convert it into a format suitable for analysis. Specifically, it applies preprocessing techniques including data cleansing, filtering, and scaling.

[0424] Step 4:

[0425] The server then feeds the pre-processed data into an artificial intelligence model for analysis. Machine learning algorithms are used to analyze the data and identify fan behavior patterns and preferences, often using clustering and classification techniques.

[0426] Step 5:

[0427] The server generates insights based on the analysis, which include recommended actions and marketing strategies based on fan interests, such as suggesting campaigns targeted to fan groups interested in specific locations.

[0428] Step 6:

[0429] The server visualizes the generated insights in the form of graphs and charts, and uses data visualization tools to display the insights in an intuitive and easy-to-understand way.

[0430] Step 7:

[0431] The device displays visualized insights that can be viewed by event organizers and teams, who can then use these insights to optimize their event operations and marketing strategies.

[0432] Specific examples

[0433] For example, the following data is collected at a race event:

[0434] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[0435] After going through steps 1 to 7, the server generates the following insight and displays it on the device:

[0436] Fans around Stand B are very interested in the food stands.

[0437] At your next event, it would be beneficial to run a special food promotion around Stand B.

[0438] This allows event organizers and teams to offer personalized services based on fan preferences and behavior, improving fan engagement.

[0439] Example 1

[0440] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0441] In conventional event management, there were few ways to effectively collect visitor behavior data and gain customized insights based on that data. As a result, it was difficult to accurately understand visitor needs and implement effective marketing strategies and services based on those needs. This led to issues such as insufficient improvement of event satisfaction and participant engagement.

[0442] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0443] In this invention, the server includes means for collecting visitor behavior data at an event, means for preprocessing the collected data, means for analyzing the preprocessed data using a machine learning algorithm, means for generating customized insights based on the analysis results, and means for displaying the generated insights as graphs or charts. This makes it possible to effectively collect and analyze visitor behavior data and provide customized insights based on the results. This allows event organizers to accurately understand visitor needs and implement effective marketing strategies and service provision based on those needs, significantly improving event satisfaction and participant engagement.

[0444] "Behavioral data" refers to data such as a visitor's location, the places they visited, the length of their stay, and their purchase history.

[0445] "Data preprocessing" refers to the process of imputing missing values, correcting outliers, and standardizing collected raw data.

[0446] A "machine learning algorithm" is an algorithm that learns patterns based on past data and makes predictions and classifications for future data.

[0447] "Customized insights" are specific suggestions based on analysis results, such as recommended actions and marketing strategies for specific visitor groups.

[0448] "Graphs and charts" are shapes that visually represent collected and analyzed data and generated insights.

[0449] "Event Organizer" means the person or entity responsible for planning, conducting and managing an Event.

[0450] This invention is a system that collects and analyzes visitor behavior data and provides customized insights based on the results, and is realized through the collaboration of servers, terminals, and users.

[0451] Data collection

[0452] The server collects real-time data from multiple sensors placed around the event venue. These sensors include Bluetooth beacons and Wi-Fi access points. These sensors communicate with visitors' smartphones to obtain location information. Mobile apps used by visitors also send data to the server. This data includes location information, locations visited, length of stay, and purchase history.

[0453] The devices are the visitors' smartphones or tablets, which use location services in the background to collect the visitor's location data. For example, when a visitor enters a certain area, the location information is automatically updated and sent to the server.

[0454] When users (visitors) arrive at the event venue, they open the mobile app and grant permission for data collection, specifically by turning on location sharing and in-app notifications.

[0455] Data Preprocessing

[0456] The server pre-processes the collected raw data, including imputing missing values, correcting outliers, and standardizing the data. Specifically, it performs the following processes:

[0457] 1. Data imputation: If some location information is missing, it is imputed using data from adjacent time intervals.

[0458] 2. Anomaly correction: If a visitor suddenly moves beyond the range of the sensor, the data will be deleted or corrected as an anomaly.

[0459] 3. Data standardization: To process collected data on a unified scale, convert coordinate data and other data into a standard format. Use a Python numerical processing library (e.g., Pandas, NumPy).

[0460] Data analysis

[0461] The server then feeds the preprocessed data into an artificial intelligence model, for example using a machine learning library such as Scikit-learn or TensorFlow, to build a model that performs the following analyses:

[0462] 1. Behavioral pattern analysis: Analyze the behavioral patterns of visitors who stay in a specific area for a long time.

[0463] 2. Preference analysis: Identify which foods visitors are interested in based on the number of times they visit the food stand and the time of day.

[0464] Insight generation

[0465] The server generates customized insights based on the data analysis results, including, for example:

[0466] 1. Generate recommended actions: Generate recommended actions for specific visitor demographics.

[0467] Example: An insight that says, "Visitors gathering around Stand G are interested in a particular beverage, so we should promote beverages in that area."

[0468] 2. Marketing strategy proposal: Propose effective measures for the next event.

[0469] Example: "At our next event, we'll be running a special food promotion around Stand B."

[0470] Visualizing and presenting results

[0471] The server visualizes the generated insights as graphs and charts, using the following tools:

[0472] 1. Tableau or Power BI: Generate graphs to visually represent behavioral patterns and preferences.

[0473] 2. Dashboard: Organize insights and present them in an easily accessible format for event organizers and teams.

[0474] The device displays these visualizations, and event organizers and teams can check various graphs and charts on the device to plan on-site measures.

[0475] Users (event organizers and teams) can use the insights provided by the server to optimize their event management and marketing strategies, specifically adjusting the placement and promotional content of their next event.

[0476] Prompt Sentence Examples

[0477] Suggest a marketing strategy for your next event based on the following behavioral data:

[0478] Fan A stayed in Stand B for 15 minutes and then went to the food stand. Use this data to provide insights into services and promotions relevant to that specific area.

[0479] The above is an embodiment of the present invention.

[0480] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0481] Step 1: Data collection

[0482] The server collects data from sensors placed at the event venue and from mobile apps used by visitors. Input includes location information from Bluetooth beacons and Wi-Fi access points, visited locations, length of stay, and purchase history. Specifically, when a visitor enters a specific area, the sensor communicates with the smartphone and sends the location information to the server. The output is streaming location information and behavioral data.

[0483] Step 2: Data Preprocessing

[0484] The server preprocesses the collected data. The input is raw data (location information, visited locations, duration of stay, etc.). If there are missing values ​​in the data at this stage, they are filled in using data from adjacent time intervals. Outliers are removed or corrected. For example, if a visitor moves out of the sensor range at high speed, it is considered an outlier. The server also converts the collected data into a standard format. This process improves the quality of the data and makes it consistent. The output is preprocessed, clean data.

[0485] Step 3: Data analysis

[0486] The server analyzes the preprocessed data using machine learning algorithms. The input is the preprocessed dataset. Specifically, Scikit-learn and TensorFlow are used to analyze and model visitor behavior patterns. Behavior pattern analysis identifies, for example, patterns where visitors spend a long time in a particular area. Preference analysis identifies groups of visitors who may be interested in specific promotions or services. The output is the identified patterns and preference information as the analysis results.

[0487] Step 4: Insight generation

[0488] The server generates customized insights based on the analysis results. The input is the results of data analysis. Specifically, based on the analysis results, it automatically generates recommended actions and marketing strategies tailored to the visitor demographic. For example, it generates an insight that "Since many visitors gather around Stand G, we should implement a beverage promotion in this area." The output is customized insights.

[0489] Step 5: Visualize and deliver results

[0490] The server visualizes the generated insights as graphs and charts. The input is the generated customized insights. Specifically, a data visualization tool (e.g., Tableau or Power BI) is used to visually represent the analysis results, which clearly visualizes visitor behavior patterns and preferences. The terminal displays these visualizations and provides them to the user (event organizer or team) in a format that is easy to understand. The output is visualized insights based on attendee behavior patterns.

[0491] The above is a detailed description of each processing step of the system.

[0492] (Application example 1)

[0493] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0494] Conventional systems do not fully utilize behavioral data of fans and customers at event venues and brick-and-mortar stores, making it difficult to optimize personalized promotion strategies based on customer behavior patterns and preferences. Furthermore, there is a lack of means to clearly visualize the analysis results and make them specifically useful for store management.

[0495] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0496] In this invention, the server includes means for collecting fan behavior data, means for preprocessing the collected data, means for analyzing the preprocessed data using an artificial intelligence model, means for generating insights based on the analysis results, and means for displaying the generated insights and providing promotion strategies, thereby enabling the development of effective promotion strategies based on customer behavior patterns and preferences and the specific visualization of the results.

[0497] "Fan behavior data" refers to data such as the location information of customers (fans) at event venues and physical stores, the places they visit, the length of their stay, and their purchase history.

[0498] "Means for preprocessing collected data" refers to means for executing processes to ensure data quality and convert the data into a format suitable for analysis, such as completing missing values ​​in the data, correcting outliers, and standardizing the data.

[0499] An "artificial intelligence model" is a model that uses machine learning algorithms and other techniques to analyze pre-processed data and identify fan behavior patterns and preferences.

[0500] "Means for generating insights" are means that have the ability to propose recommended actions and promotional strategies for specific fan groups based on the analysis results.

[0501] "Means for displaying the generated insights and providing promotion strategies" refers to means for visualizing the insights obtained through analysis in the form of graphs and charts, displaying them in a way that is easy for operators of event venues and physical stores to understand, and providing specific promotion strategies based on them.

[0502] This invention is a system that collects and analyzes behavioral data of fans and customers at event venues and brick-and-mortar stores, and provides customized promotional strategies based on that data. This system is realized primarily through the collaboration of a server, terminals, and users.

[0503] Data collection

[0504] The server collects data in real time from sensors placed at event venues and brick-and-mortar stores, as well as from mobile apps used by customers. Specifically, data such as location information, places visited, length of stay, and purchase history is collected. The devices are smartphones and tablets held by customers, which automatically record behavioral data and send it to the server. Users (customers) give permission for data collection through the app.

[0505] Data Preprocessing

[0506] The server preprocesses the collected raw data using data processing libraries such as Pandas to impute missing values, correct outliers, and standardize the data, thereby ensuring data quality and converting it into a format suitable for analysis.

[0507] Data analysis

[0508] The server then feeds the preprocessed data into an artificial intelligence model, which uses machine learning algorithms such as Scikit-learn to analyze the data and identify customer behavioral patterns and preferences. For example, if a customer spends a long time in a particular area, it can determine that they are likely interested in products and services related to that area.

[0509] Insight generation

[0510] Based on the analysis results, the server generates customized insights, including recommended actions and promotion strategies for specific customer segments. For example, an insight might be, "This customer segment is interested in the snack area, so we'll offer a special snack promotion at the next event." The insights can also be visualized using Matplotlib and displayed in graphs and charts.

[0511] Providing results

[0512] The generated insights are visualized in graphs and charts by the server and provided to event and store managers. The terminal displays these visualizations so that users can easily understand them. Users (managers) can use these insights to optimize their event and store operations and further marketing strategies.

[0513] Specific examples

[0514] For example, suppose a store collects the following data:

[0515] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[0516] Customer B stayed in the beverage area for 15 minutes.

[0517] Based on this data, the server generates insights such as:

[0518] Customers around the general goods area are very interested in snacks.

[0519] For your next store promotion, it would be effective to run a special snack promotion around the general merchandise area.

[0520] This allows event organizers and store operators to provide personalized services based on customer preferences and behavior, improving fan engagement.

[0521] Example prompts to be input to the generative AI model

[0522] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[0523] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[0524] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0525] Step 1: Data collection

[0526] The server collects data in real time from sensors placed at event venues and physical stores, as well as from smartphone apps used by customers. Specifically, the data collected includes location information, visited locations, length of stay, and purchase history. The device (customer's smartphone) automatically records this data and sends it to the server. The user (customer) gives permission for data collection through the app, which then initiates data collection.

[0527] Input: Raw data from sensors and smartphone apps (location information, visit locations, stay times, purchase history)

[0528] Output: Raw behavioral data aggregated on the server

[0529] Step 2: Data Preprocessing

[0530] The server preprocesses the collected raw data by using Pandas to impute missing values, correct outliers, and standardize the collected data, thereby ensuring data quality and converting it into a format suitable for analysis.

[0531] Input: Collected raw behavioral data

[0532] Output: Preprocessed data with missing value imputation, outlier correction, and standardization

[0533] Step 3: Data analysis

[0534] The preprocessed data is fed into an artificial intelligence model by the server, which then uses machine learning algorithms such as Scikit-learn's KMeans to cluster the data and identify customer behavior patterns and preferences. The server then determines which cluster each customer's behavior data belongs to and analyzes the characteristics of each cluster.

[0535] Input: Preprocessed behavioral data

[0536] Output: Clustering results for each customer and cluster feature data

[0537] Step 4: Insight generation

[0538] The server generates customized insights based on the results of the clustering analysis. Specifically, it generates data for each cluster to suggest the level of interest in specific product areas and promotion strategies. In this process, marketing strategies are proposed based on the average values ​​and behavioral patterns of each cluster.

[0539] Input: Clustering results and cluster feature data

[0540] Output: Insights for specific customer segments (e.g., promotional strategy suggestions)

[0541] Step 5: Visualize and deliver results

[0542] The server visualizes the generated insights in the form of graphs and charts, using visualization libraries such as Matplotlib to display the insights in an easy-to-understand format. The terminal displays these visualizations so that users (event organizers and store operators) can easily understand them.

[0543] Input: Generated insights

[0544] Output: Visualized insights in the form of graphs and charts, displayed visualizations

[0545] As a concrete example, consider the following data collected at a store:

[0546] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[0547] Customer B stayed in the beverage area for 15 minutes.

[0548] Based on this data, the server generates a prompt like this:

[0549] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[0550] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[0551] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0552] The present invention is a system that collects and analyzes fan behavior data to generate insights, and combines this with an emotion engine that recognizes user emotions to provide a more accurate and customized fan experience. This system is composed of a server, terminals, and users working together.

[0553] Data collection

[0554] The server collects fan behavior data from sensors installed at the event venue and from mobile apps. Specifically, it obtains data such as location information, visited locations, and length of stay in real time. The device collects data from fans' smartphones or tablets and sends it to the server. Users (fans) give consent to share their location information and collect behavioral data through the app.

[0555] Emotional Data Collection

[0556] The server also uses an emotion engine to collect emotional data from fans. This emotional data includes emotional information obtained through voice analysis and facial expression analysis. The device transmits the data acquired through the camera and microphone to the server.

[0557] Data Preprocessing

[0558] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by imputing missing values, correcting outliers, and standardizing the data. For emotion data, it also categorizes and scores emotions.

[0559] Data analysis

[0560] The server then inputs the pre-processed data into an artificial intelligence model. The server then uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. For example, if fans who spend a long time in a particular area have positive emotions, the server determines that they are likely to be interested in services and promotions related to that area.

[0561] Insight generation

[0562] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This fan base is interested in food stands and has positive emotions, so we'll offer special food promotions at our next event."

[0563] Visualizing and presenting results

[0564] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizer or team. The device displays these visualizations, allowing the event organizer or team to easily understand the information. The user (event organizer or team) can then use these insights to optimize their event operations and marketing strategies.

[0565] Specific examples

[0566] For example, the following data is collected at a race event:

[0567] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0568] Based on this data, the server generates insights such as:

[0569] Since fans around Stand B are more interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[0570] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[0571] The processing flow will be explained below.

[0572] Step 1:

[0573] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically, data such as location information, visited locations, and length of stay in real time, and receives the data via HTTP requests and APIs.

[0574] Step 2:

[0575] The device collects location information and behavioral data from fans' smartphones or tablets and sends it to a server in real time. Users consent to the sharing of location information and the collection of behavioral data through the app.

[0576] Step 3:

[0577] The server uses an emotion engine to collect emotional data from fans. Specifically, it analyzes voice data and facial expression data from fans as they move around the venue to obtain emotional information.

[0578] Step 4:

[0579] The device captures audio and video data via the fan's smartphone or tablet and transmits this data to a server in real time.

[0580] Step 5:

[0581] The server preprocesses the collected behavioral and emotional data. Specifically, it complements missing values, corrects outliers, and standardizes the data. For emotional data, it also categorizes and scores emotions.

[0582] Step 6:

[0583] The server then feeds the pre-processed data into an artificial intelligence model for analysis, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions.

[0584] Step 7:

[0585] The server generates insights based on the analysis results, including recommended actions for specific fan groups and marketing strategies that take sentiment information into account.

[0586] Step 8:

[0587] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, while the terminal displays these visualized insights for the event organizers and teams to view and understand.

[0588] Specific examples

[0589] For example, suppose the following data is collected at a racing event:

[0590] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0591] Based on this data, the server generates insights like the following and displays them on the device:

[0592] Since fans around Stand B are highly interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[0593] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[0594] Example 2

[0595] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0596] Conventional fan experience delivery systems provide services based solely on fan behavioral data, and are unable to accurately capture fans' emotions and preferences. This has resulted in low accuracy in customizing the services and promotions provided, making it difficult to improve fan engagement. Furthermore, there is no system for centrally collecting and analyzing emotional and behavioral data, making integrated analysis of the data difficult. Given these circumstances, there is a need for an integrated collection and analysis of diverse data, including fans' emotional information, to provide highly accurate, customized fan experiences.

[0597] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting behavioral data of fans, a means for preprocessing the collected behavioral data and emotion data, and a means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to accurately grasp the behavioral patterns and emotions of fans and provide customized services to users.

[0598] "Behavioral data" refers to data that indicates how fans behaved within the event venue, such as their location, the places they visited, and the length of their stay.

[0599] "Emotional data" is data that indicates the emotional state of fans, obtained through voice analysis and facial expression analysis.

[0600] "Preprocessing" refers to the process of converting the collected raw data and emotion data into a format suitable for analysis by complementing missing values, correcting outliers, and standardizing them.

[0601] An "artificial intelligence model" is a model that uses algorithms such as machine learning and deep learning to analyze input data and extract patterns and features.

[0602] "Insights" are insights and recommended actions related to fan behavior and sentiment generated based on the analysis results.

[0603] "Sensors" are devices installed at event venues to collect fan behavior data. Examples include Wi-Fi beacons and GPS.

[0604] A "mobile app" is application software that fans install and use on their smartphones or tablets, and collects behavioral and emotional data.

[0605] "Terminal" refers to a mobile information terminal such as a smartphone or tablet held by a fan, which collects data and transmits it to the server.

[0606] "Data analysis" is the process of feeding pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions.

[0607] "Visualization" is a technique that makes information easier to understand visually by displaying the generated insights in the form of graphs and charts.

[0608] The present invention is a system for generating insights by collecting and analyzing behavioral data and emotional data of fans. This system is mainly composed of a server, terminals, and users working together. Specific embodiments of the system are described below.

[0609] Data collection

[0610] The server collects real-time behavioral data, such as location, visit locations, and duration of stay, from sensors installed at the event venue and mobile apps. Sensors such as Wi-Fi beacons and GPS can be used to determine which areas fans were in and how long they stayed there. For example, the server receives Wi-Fi beacon signals and updates the fan's location information.

[0611] The device sends data acquired from sensors and apps via the fan's smartphone or tablet to a server. The mobile app collects location and behavioral data at regular intervals and sends it to the server using the HTTPS protocol. When the user (fan) launches the app for the first time, they give consent to share their location information and collect behavioral data.

[0612] Emotional Data Collection

[0613] The server uses an emotion engine to analyze data collected from the device's camera and microphone to obtain emotional information about the fan. The camera captures facial expressions, and the microphone collects audio data. For example, the device's camera captures the user's facial expressions at regular intervals, while simultaneously collecting and sending audio data to the server.

[0614] The device sends this data to a server, which then uses voice and facial expression analysis to estimate emotions. Voice analysis extracts features such as pitch, tempo, and volume from the voice data, while facial expression analysis detects facial features to classify emotions.

[0615] Data Preprocessing

[0616] The server complements missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data. For example, if part of the location data is missing, it is complemented using an interpolation algorithm based on the preceding and following data. Furthermore, if an extremely high emotion score is obtained, it is clipped at an upper threshold.

[0617] The server also converts the preprocessed data into a format suitable for analysis, for example by scaling the sentiment scores to a range from 0 to 1.

[0618] Data analysis

[0619] The server then inputs the pre-processed data into an AI model to analyze fan behavior patterns, preferences, and emotions. Machine learning algorithms are used to analyze the data and identify common fan preferences and behavior patterns. For example, it can identify groups of fans who spend a long time in the same area and exhibit positive emotions.

[0620] Insight generation

[0621] The server generates customized insights based on the analysis results, such as "This fan base is interested in food stands and has positive sentiment," which provides useful recommended actions and marketing strategies for event organizers and teams.

[0622] Visualizing and presenting results

[0623] The server visualizes the generated insights in the form of graphs and charts and provides them to event organizers and teams using libraries such as Matplotlib and D3.js. The terminal displays these visualizations, allowing event organizers and teams to easily understand the information.

[0624] Specific examples

[0625] For example, the following data is collected at a race event:

[0626] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0627] Based on this data, the server generates insights such as:

[0628] Fans around Stand B are more interested in food stands and have positive feelings about them, so it would be effective to run a special food promotion at the next event.

[0629] Examples of prompt statements

[0630] Examples of prompts for a generative AI model might include:

[0631] "Based on the data collected during the event, could you please tell us the results of your analysis of the relationship between the amount of time fans spent in a specific area and their emotional scores?"

[0632] This allows the AI ​​model to generate specific insights.

[0633] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0634] Step 1:

[0635] Data collection

[0636] The server collects real-time behavioral data such as location, visited locations, and length of stay from sensors installed at the event venue and mobile apps.

[0637] Input: Location information from sensors, behavioral data from mobile apps.

[0638] Data processing: Receives Wi-Fi beacon and GPS data and records fans' location information and time spent there.

[0639] Output: Recorded behavioral data.

[0640] How it works: The server periodically receives signals from sensors and stores the data in a database. For example, when a fan enters a specific area, it logs their location based on information received from Wi-Fi beacons.

[0641] Step 2:

[0642] Data transmission via fan terminals

[0643] The device transmits data obtained from sensors and apps to a server via the fan's smartphone or tablet.

[0644] Input: Location and behavioral data collected on the device.

[0645] Data processing: Data is batch processed at regular intervals and sent to the server using the HTTPS protocol.

[0646] Output: Behavioral data sent to the server.

[0647] Specific operation: The app sets the collection timing to every minute and sends behavioral data to the server each time, allowing data to be accumulated on the server in real time.

[0648] Step 3:

[0649] Obtaining User Consent

[0650] Users (fans) use the mobile app to give consent to share location information and collect behavioral data.

[0651] Input: The consent screen that appears when the app is first launched.

[0652] Data processing: Data collection will only begin once consent has been obtained.

[0653] Output: Data collection settings based on consent.

[0654] Specific behavior: When the app is launched for the first time, a pop-up regarding location usage and data collection will be displayed, and data collection will not begin until the user presses the consent button.

[0655] Step 4:

[0656] Emotional Data Collection

[0657] The server analyzes emotional information using data collected from the device's camera and microphone.

[0658] Input: Audio and image data sent from the device.

[0659] Data processing: Conduct voice analysis and facial expression analysis to estimate emotions.

[0660] Output: Sentiment score.

[0661] How it works: The device camera captures the user's face and the microphone collects their voice. These data are sent to the server in real time or in batches, and the emotion engine calculates an emotion score.

[0662] Step 5:

[0663] Data Preprocessing

[0664] The server imputes missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data.

[0665] Input: location data, behavioral data, emotion data.

[0666] Data processing: imputation of missing values, correction of outliers, standardization processing.

[0667] Output: Preprocessed data.

[0668] Specific operation: If there are gaps in the location information data, it will be interpolated based on the previous and following data. If an abnormally high value is found in the emotion score, it will be corrected by an upper threshold. This prepares the data in a state suitable for analysis.

[0669] Step 6:

[0670] Data analysis

[0671] The server then feeds the pre-processed data into an AI model to identify fan behavior patterns, preferences, and emotions.

[0672] Input: Preprocessed behavioral and emotional data.

[0673] Data processing: Analysis using machine learning algorithms.

[0674] Output: Analysis results (behavioral patterns, preferences, emotions).

[0675] Specific behavior: Using clustering techniques, we identify groups of fans with similar behavioral patterns, such as fans who spend a long time in the same area and show positive emotions.

[0676] Step 7:

[0677] Insight generation

[0678] The server generates customized insights based on the analysis results.

[0679] Input: Analysis results.

[0680] Data processing: Generating insights.

[0681] Output: Insights (recommended actions, marketing strategies).

[0682] What happens: Based on the analysis results, we can generate insights such as "This fan base is interested in food stands and has positive sentiments," which can then be used to plan special promotions for the next event.

[0683] Step 8:

[0684] Visualizing and presenting results

[0685] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, and the terminals display these visualizations.

[0686] Input: Generated insights.

[0687] Data processing: Visual content generation.

[0688] Output: The displayed graphs and charts.

[0689] Specific operation: Using libraries such as Matplotlib and D3.js, insights are displayed as timelines, heat maps, bar graphs, etc. In the mobile app on the device, this data is displayed on a dashboard and can be manipulated interactively.

[0690] (Application example 2)

[0691] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0692] Traditional fan engagement systems rely solely on behavioral data and are unable to grasp fan sentiment in real time, making it difficult to provide personalized fan experiences. Furthermore, the insights gained from analyzing the collected data are limited and lacking in accuracy. This makes them lack the ability to provide customized services based on fans' interests and emotions.

[0693] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting behavioral data and emotional data of fans, means for preprocessing the collected data, and means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to comprehensively analyze the behavior and emotions of fans and provide users with personalized recommended actions and marketing strategies based on the obtained insights.

[0694] "Behavioral Data" refers to data related to the behavior of fans or users, such as their physical location, visited pages, and duration of stay.

[0695] "Emotional data" is emotional information obtained through voice analysis and facial expression analysis of fans and users, and is data that indicates their emotional state, such as positive or negative.

[0696] "Preprocessing" refers to a series of processes such as data imputation, outlier correction, and standardization to convert collected raw data into a format suitable for analysis.

[0697] An "artificial intelligence model" is a model that uses machine learning and data analysis algorithms to analyze data and derive specific patterns and insights.

[0698] "Insights" are useful knowledge and discoveries obtained based on analyzed data, and are information that can be used to recommend actions and guide marketing strategies that are valuable to users.

[0699] "Personalized recommendations" are customized suggestions for services and promotions based on the individual behavioral patterns and emotional data of fans and users.

[0700] A "marketing strategy" refers to plans and actions designed to increase sales and customer satisfaction, taking into account the preferences and emotions of fans and users.

[0701] "Visualization" is the process of displaying analyzed data and insights in visual formats such as graphs and charts to make them easier to understand.

[0702] This invention is a system that collects and analyzes fan behavioral and emotional data to provide users with a customized fan experience. This system is realized primarily through collaboration between a server, terminals, and users.

[0703] Data collection

[0704] The server collects behavioral and emotional data from fans via sensors and mobile applications installed at event venues and virtual stores. Specifically, in addition to behavioral data such as fans' location, visited pages, and length of stay, it also uses smartphone cameras and microphones to analyze facial expressions and voices to obtain emotional data.

[0705] The terminal (e.g., a smartphone) is a device carried by the fan through which data is collected. An application on the terminal accesses the camera and microphone and transmits the data in real time to a server.

[0706] By using the application, users (fans) agree to the sharing of their location information and the collection of behavioral data, and enjoy the experience within the application.

[0707] Data Preprocessing

[0708] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by interpolating missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[0709] Data analysis

[0710] The pre-processed data is then fed into an artificial intelligence model by a server, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. The server then uses a machine learning platform such as Google Cloud AI Platform to perform the analysis.

[0711] Insight generation

[0712] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This user is interested in electronics and has positive emotions, so we recommend related accessories."

[0713] Visualizing and presenting results

[0714] The generated insights are visualized by the server in the form of graphs and charts and displayed within the user's smartphone application, allowing the user to easily understand the personalized recommended actions and enjoy the experience.

[0715] Specific examples

[0716] For example, if a user spends 15 minutes in the "electronics" section of a virtual store and displays positive emotions, the "related accessories" section will be recommended next.

[0717] Example prompt sentence:

[0718] Thanks for your attention! We understand you're interested in electronics. Why not take a look at some related accessories next?

[0719] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0720] Step 1:

[0721] Data collection

[0722] The device collects behavioral and emotional data from fans. Specifically, the smartphone application accesses the camera and microphone to capture location information, visited pages, time spent on the device, voice and facial expressions.

[0723] Inputs include location information from the smartphone's sensors, video data from the camera, and audio data from the microphone.

[0724] The output is the raw behavioral and emotional data collected.

[0725] Step 2:

[0726] Data transmission

[0727] The device sends the collected raw data to a server, where an application encrypts the data and sends it to the server over the Internet.

[0728] The input is raw behavioral and emotional data collected on the device.

[0729] The output is raw behavioral and emotional data sent to a server.

[0730] Step 3:

[0731] Data Preprocessing

[0732] The server preprocesses the collected raw data, including filling in missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[0733] The input is raw behavioral and emotional data sent from the device.

[0734] The output is the pre-processed data.

[0735] Step 4:

[0736] Data analysis

[0737] The server then feeds the pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions. Specifically, the data is analyzed using machine learning platforms such as Google Cloud AI Platform.

[0738] The input is preprocessed data.

[0739] The output is analysis results such as behavioral patterns, preferences, and emotional data.

[0740] Step 5:

[0741] Insight generation

[0742] The server generates customized insights based on the analysis results, specifically recommended actions and marketing strategies based on specific patterns and sentiments.

[0743] The input is behavioral patterns, preferences, and emotional data obtained from data analysis.

[0744] The output is the insight generated.

[0745] Step 6:

[0746] Visualizing and presenting results

[0747] The server visualizes the generated insights in the form of graphs and charts and sends them to the device, which displays the visualized insights in a smartphone application and provides the user with personalized recommended actions and marketing strategies.

[0748] The input is the generated insight.

[0749] The output is a recommended action or marketing strategy that is displayed within the smartphone application.

[0750] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0751] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0752] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0753] [Third embodiment]

[0754] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0755] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0756] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0757] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0758] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0759] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0760] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0761] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0762] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0763] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0764] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0765] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0766] The present invention is a system that collects and analyzes fan behavior data and provides customized insights to event organizers and teams based on the results. This system is realized through the collaboration of a server, terminals, and users.

[0767] Data collection

[0768] The server collects data in real time from sensors placed at the event venue and from mobile apps used by fans. Specifically, this data includes location information, places visited, length of stay, and purchase history. The devices, such as fans' smartphones and tablets, automatically record location information and behavioral data and send it to the server. Users (fans) grant permission for data collection through the app as they move around the event venue.

[0769] Data Preprocessing

[0770] The server preprocesses the collected raw data, including imputing missing values, correcting outliers, and standardizing the data to ensure data quality and convert it into a format suitable for analysis.

[0771] Data analysis

[0772] The server then feeds the pre-processed data into an artificial intelligence model, which uses machine learning algorithms to analyze the data and identify fan behavior patterns and preferences. For example, it determines that fans who spend a lot of time in a particular area are likely to be interested in services and promotions related to that area.

[0773] Insight generation

[0774] Based on the analysis, the server generates customized insights, including recommended actions and marketing strategies for specific fan segments. For example, an insight could be, "This fan segment is interested in food stands, so we'll offer special food promotions at our next event."

[0775] Visualizing and presenting results

[0776] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams. The terminal displays these visualizations so that users can easily understand them. Users (event organizers and teams) can use these insights to optimize their event operations and marketing strategies.

[0777] Specific examples

[0778] For example, suppose the following data is collected at a race event:

[0779] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[0780] Based on this data, the server generates insights such as:

[0781] Fans around Stand B are very interested in the food stands.

[0782] At your next event, it would be beneficial to run a special food promotion around Stand B.

[0783] This allows event organizers and teams to improve fan engagement by providing personalized services based on fan preferences and behavior.

[0784] The processing flow will be explained below.

[0785] Step 1:

[0786] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically via HTTP requests and APIs to obtain real-time data such as location information, visited locations, and duration of stay.

[0787] Step 2:

[0788] The device collects data from fans' smartphones or tablets through an app and sends it to a server. Users consent to location sharing within the app, and the collection is applied.

[0789] Step 3:

[0790] The server preprocesses the collected raw data by imputing missing values, correcting outliers, and standardizing the data to convert it into a format suitable for analysis. Specifically, it applies preprocessing techniques including data cleansing, filtering, and scaling.

[0791] Step 4:

[0792] The server then feeds the pre-processed data into an artificial intelligence model for analysis. Machine learning algorithms are used to analyze the data and identify fan behavior patterns and preferences, often using clustering and classification techniques.

[0793] Step 5:

[0794] The server generates insights based on the analysis, which include recommended actions and marketing strategies based on fan interests, such as suggesting campaigns targeted to fan groups interested in specific locations.

[0795] Step 6:

[0796] The server visualizes the generated insights in the form of graphs and charts, and uses data visualization tools to display the insights in an intuitive and easy-to-understand way.

[0797] Step 7:

[0798] The device displays visualized insights that can be viewed by event organizers and teams, who can then use these insights to optimize their event operations and marketing strategies.

[0799] Specific examples

[0800] For example, the following data is collected at a race event:

[0801] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[0802] After going through steps 1 to 7, the server generates the following insight and displays it on the device:

[0803] Fans around Stand B are very interested in the food stands.

[0804] At your next event, it would be beneficial to run a special food promotion around Stand B.

[0805] This allows event organizers and teams to offer personalized services based on fan preferences and behavior, improving fan engagement.

[0806] Example 1

[0807] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0808] In conventional event management, there were few ways to effectively collect visitor behavior data and gain customized insights based on that data. As a result, it was difficult to accurately understand visitor needs and implement effective marketing strategies and services based on those needs. This led to issues such as insufficient improvement of event satisfaction and participant engagement.

[0809] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0810] In this invention, the server includes means for collecting visitor behavior data at an event, means for preprocessing the collected data, means for analyzing the preprocessed data using a machine learning algorithm, means for generating customized insights based on the analysis results, and means for displaying the generated insights as graphs or charts. This makes it possible to effectively collect and analyze visitor behavior data and provide customized insights based on the results. This allows event organizers to accurately understand visitor needs and implement effective marketing strategies and service provision based on those needs, significantly improving event satisfaction and participant engagement.

[0811] "Behavioral data" refers to data such as a visitor's location, the places they visited, the length of their stay, and their purchase history.

[0812] "Data preprocessing" refers to the process of imputing missing values, correcting outliers, and standardizing collected raw data.

[0813] A "machine learning algorithm" is an algorithm that learns patterns based on past data and makes predictions and classifications for future data.

[0814] "Customized insights" are specific suggestions based on analysis results, such as recommended actions and marketing strategies for specific visitor groups.

[0815] "Graphs and charts" are shapes that visually represent collected and analyzed data and generated insights.

[0816] "Event Organizer" means the person or entity responsible for planning, conducting and managing an Event.

[0817] This invention is a system that collects and analyzes visitor behavior data and provides customized insights based on the results, and is realized through the collaboration of servers, terminals, and users.

[0818] Data collection

[0819] The server collects real-time data from multiple sensors placed around the event venue. These sensors include Bluetooth beacons and Wi-Fi access points. These sensors communicate with visitors' smartphones to obtain location information. Mobile apps used by visitors also send data to the server. This data includes location information, locations visited, length of stay, and purchase history.

[0820] The devices are the visitors' smartphones or tablets, which use location services in the background to collect the visitor's location data. For example, when a visitor enters a certain area, the location information is automatically updated and sent to the server.

[0821] When users (visitors) arrive at the event venue, they open the mobile app and grant permission for data collection, specifically by turning on location sharing and in-app notifications.

[0822] Data Preprocessing

[0823] The server pre-processes the collected raw data, including imputing missing values, correcting outliers, and standardizing the data. Specifically, it performs the following processes:

[0824] 1. Data imputation: If some location information is missing, it is imputed using data from adjacent time intervals.

[0825] 2. Anomaly correction: If a visitor suddenly moves beyond the range of the sensor, the data will be deleted or corrected as an anomaly.

[0826] 3. Data standardization: To process collected data on a unified scale, convert coordinate data and other data into a standard format. Use a Python numerical processing library (e.g., Pandas, NumPy).

[0827] Data analysis

[0828] The server then feeds the preprocessed data into an artificial intelligence model, for example using a machine learning library such as Scikit-learn or TensorFlow, to build a model that performs the following analyses:

[0829] 1. Behavioral pattern analysis: Analyze the behavioral patterns of visitors who stay in a specific area for a long time.

[0830] 2. Preference analysis: Identify which foods visitors are interested in based on the number of times they visit the food stand and the time of day.

[0831] Insight generation

[0832] The server generates customized insights based on the data analysis results, including, for example:

[0833] 1. Generate recommended actions: Generate recommended actions for specific visitor demographics.

[0834] Example: An insight that says, "Visitors gathering around Stand G are interested in a particular beverage, so we should promote beverages in that area."

[0835] 2. Marketing strategy proposal: Propose effective measures for the next event.

[0836] Example: "At our next event, we'll be running a special food promotion around Stand B."

[0837] Visualizing and presenting results

[0838] The server visualizes the generated insights as graphs and charts, using the following tools:

[0839] 1. Tableau or Power BI: Generate graphs to visually represent behavioral patterns and preferences.

[0840] 2. Dashboard: Organize insights and present them in an easily accessible format for event organizers and teams.

[0841] The device displays these visualizations, and event organizers and teams can check various graphs and charts on the device to plan on-site measures.

[0842] Users (event organizers and teams) can use the insights provided by the server to optimize their event management and marketing strategies, specifically adjusting the placement and promotional content of their next event.

[0843] Prompt Sentence Examples

[0844] Suggest a marketing strategy for your next event based on the following behavioral data:

[0845] Fan A stayed in Stand B for 15 minutes and then went to the food stand. Use this data to provide insights into services and promotions relevant to that specific area.

[0846] The above is an embodiment of the present invention.

[0847] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0848] Step 1: Data collection

[0849] The server collects data from sensors placed at the event venue and from mobile apps used by visitors. Input includes location information from Bluetooth beacons and Wi-Fi access points, visited locations, length of stay, and purchase history. Specifically, when a visitor enters a specific area, the sensor communicates with the smartphone and sends the location information to the server. The output is streaming location information and behavioral data.

[0850] Step 2: Data Preprocessing

[0851] The server preprocesses the collected data. The input is raw data (location information, visited locations, duration of stay, etc.). If there are missing values ​​in the data at this stage, they are filled in using data from adjacent time intervals. Outliers are removed or corrected. For example, if a visitor moves out of the sensor range at high speed, it is considered an outlier. The server also converts the collected data into a standard format. This process improves the quality of the data and makes it consistent. The output is preprocessed, clean data.

[0852] Step 3: Data analysis

[0853] The server analyzes the preprocessed data using machine learning algorithms. The input is the preprocessed dataset. Specifically, Scikit-learn and TensorFlow are used to analyze and model visitor behavior patterns. Behavior pattern analysis identifies, for example, patterns where visitors spend a long time in a particular area. Preference analysis identifies groups of visitors who may be interested in specific promotions or services. The output is the identified patterns and preference information as the analysis results.

[0854] Step 4: Insight generation

[0855] The server generates customized insights based on the analysis results. The input is the results of data analysis. Specifically, based on the analysis results, it automatically generates recommended actions and marketing strategies tailored to the visitor demographic. For example, it generates an insight that "Since many visitors gather around Stand G, we should implement a beverage promotion in this area." The output is customized insights.

[0856] Step 5: Visualize and deliver results

[0857] The server visualizes the generated insights as graphs and charts. The input is the generated customized insights. Specifically, a data visualization tool (e.g., Tableau or Power BI) is used to visually represent the analysis results, which clearly visualizes visitor behavior patterns and preferences. The terminal displays these visualizations and provides them to the user (event organizer or team) in a format that is easy to understand. The output is visualized insights based on attendee behavior patterns.

[0858] The above is a detailed description of each processing step of the system.

[0859] (Application example 1)

[0860] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0861] Conventional systems do not fully utilize behavioral data of fans and customers at event venues and brick-and-mortar stores, making it difficult to optimize personalized promotion strategies based on customer behavior patterns and preferences. Furthermore, there is a lack of means to clearly visualize the analysis results and make them specifically useful for store management.

[0862] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0863] In this invention, the server includes means for collecting fan behavior data, means for preprocessing the collected data, means for analyzing the preprocessed data using an artificial intelligence model, means for generating insights based on the analysis results, and means for displaying the generated insights and providing promotion strategies, thereby enabling the development of effective promotion strategies based on customer behavior patterns and preferences and the specific visualization of the results.

[0864] "Fan behavior data" refers to data such as the location information of customers (fans) at event venues and physical stores, the places they visit, the length of their stay, and their purchase history.

[0865] "Means for preprocessing collected data" refers to means for executing processes to ensure data quality and convert the data into a format suitable for analysis, such as completing missing values ​​in the data, correcting outliers, and standardizing the data.

[0866] An "artificial intelligence model" is a model that uses machine learning algorithms and other techniques to analyze pre-processed data and identify fan behavior patterns and preferences.

[0867] "Means for generating insights" are means that have the ability to propose recommended actions and promotional strategies for specific fan groups based on the analysis results.

[0868] "Means for displaying the generated insights and providing promotion strategies" refers to means for visualizing the insights obtained through analysis in the form of graphs and charts, displaying them in a way that is easy for operators of event venues and physical stores to understand, and providing specific promotion strategies based on them.

[0869] This invention is a system that collects and analyzes behavioral data of fans and customers at event venues and brick-and-mortar stores, and provides customized promotional strategies based on that data. This system is realized primarily through the collaboration of a server, terminals, and users.

[0870] Data collection

[0871] The server collects data in real time from sensors placed at event venues and brick-and-mortar stores, as well as from mobile apps used by customers. Specifically, data such as location information, places visited, length of stay, and purchase history is collected. The devices are smartphones and tablets held by customers, which automatically record behavioral data and send it to the server. Users (customers) give permission for data collection through the app.

[0872] Data Preprocessing

[0873] The server preprocesses the collected raw data using data processing libraries such as Pandas to impute missing values, correct outliers, and standardize the data, thereby ensuring data quality and converting it into a format suitable for analysis.

[0874] Data analysis

[0875] The server then feeds the preprocessed data into an artificial intelligence model, which uses machine learning algorithms such as Scikit-learn to analyze the data and identify customer behavioral patterns and preferences. For example, if a customer spends a long time in a particular area, it can determine that they are likely interested in products and services related to that area.

[0876] Insight generation

[0877] Based on the analysis results, the server generates customized insights, including recommended actions and promotion strategies for specific customer segments. For example, an insight might be, "This customer segment is interested in the snack area, so we'll offer a special snack promotion at the next event." The insights can also be visualized using Matplotlib and displayed in graphs and charts.

[0878] Providing results

[0879] The generated insights are visualized in graphs and charts by the server and provided to event and store managers. The terminal displays these visualizations so that users can easily understand them. Users (managers) can use these insights to optimize their event and store operations and further marketing strategies.

[0880] Specific examples

[0881] For example, suppose a store collects the following data:

[0882] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[0883] Customer B stayed in the beverage area for 15 minutes.

[0884] Based on this data, the server generates insights such as:

[0885] Customers around the general goods area are very interested in snacks.

[0886] For your next store promotion, it would be effective to run a special snack promotion around the general merchandise area.

[0887] This allows event organizers and store operators to provide personalized services based on customer preferences and behavior, improving fan engagement.

[0888] Example prompts to be input to the generative AI model

[0889] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[0890] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[0891] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0892] Step 1: Data collection

[0893] The server collects data in real time from sensors placed at event venues and physical stores, as well as from smartphone apps used by customers. Specifically, the data collected includes location information, visited locations, length of stay, and purchase history. The device (customer's smartphone) automatically records this data and sends it to the server. The user (customer) gives permission for data collection through the app, which then initiates data collection.

[0894] Input: Raw data from sensors and smartphone apps (location information, visit locations, stay times, purchase history)

[0895] Output: Raw behavioral data aggregated on the server

[0896] Step 2: Data Preprocessing

[0897] The server preprocesses the collected raw data by using Pandas to impute missing values, correct outliers, and standardize the collected data, thereby ensuring data quality and converting it into a format suitable for analysis.

[0898] Input: Collected raw behavioral data

[0899] Output: Preprocessed data with missing value imputation, outlier correction, and standardization

[0900] Step 3: Data analysis

[0901] The preprocessed data is fed into an artificial intelligence model by the server, which then uses machine learning algorithms such as Scikit-learn's KMeans to cluster the data and identify customer behavior patterns and preferences. The server then determines which cluster each customer's behavior data belongs to and analyzes the characteristics of each cluster.

[0902] Input: Preprocessed behavioral data

[0903] Output: Clustering results for each customer and cluster feature data

[0904] Step 4: Insight generation

[0905] The server generates customized insights based on the results of the clustering analysis. Specifically, it generates data for each cluster to suggest the level of interest in specific product areas and promotion strategies. In this process, marketing strategies are proposed based on the average values ​​and behavioral patterns of each cluster.

[0906] Input: Clustering results and cluster feature data

[0907] Output: Insights for specific customer segments (e.g., promotional strategy suggestions)

[0908] Step 5: Visualize and deliver results

[0909] The server visualizes the generated insights in the form of graphs and charts, using visualization libraries such as Matplotlib to display the insights in an easy-to-understand format. The terminal displays these visualizations so that users (event organizers and store operators) can easily understand them.

[0910] Input: Generated insights

[0911] Output: Visualized insights in the form of graphs and charts, displayed visualizations

[0912] As a concrete example, consider the following data collected at a store:

[0913] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[0914] Customer B stayed in the beverage area for 15 minutes.

[0915] Based on this data, the server generates a prompt like this:

[0916] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[0917] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[0918] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0919] The present invention is a system that collects and analyzes fan behavior data to generate insights, and combines this with an emotion engine that recognizes user emotions to provide a more accurate and customized fan experience. This system is composed of a server, terminals, and users working together.

[0920] Data collection

[0921] The server collects fan behavior data from sensors installed at the event venue and from mobile apps. Specifically, it obtains data such as location information, visited locations, and length of stay in real time. The device collects data from fans' smartphones or tablets and sends it to the server. Users (fans) give consent to share their location information and collect behavioral data through the app.

[0922] Emotional Data Collection

[0923] The server also uses an emotion engine to collect emotional data from fans. This emotional data includes emotional information obtained through voice analysis and facial expression analysis. The device transmits the data acquired through the camera and microphone to the server.

[0924] Data Preprocessing

[0925] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by imputing missing values, correcting outliers, and standardizing the data. For emotion data, it also categorizes and scores emotions.

[0926] Data analysis

[0927] The server then inputs the pre-processed data into an artificial intelligence model. The server then uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. For example, if fans who spend a long time in a particular area have positive emotions, the server determines that they are likely to be interested in services and promotions related to that area.

[0928] Insight generation

[0929] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This fan base is interested in food stands and has positive emotions, so we'll offer special food promotions at our next event."

[0930] Visualizing and presenting results

[0931] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizer or team. The device displays these visualizations, allowing the event organizer or team to easily understand the information. The user (event organizer or team) can then use these insights to optimize their event operations and marketing strategies.

[0932] Specific examples

[0933] For example, the following data is collected at a race event:

[0934] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0935] Based on this data, the server generates insights such as:

[0936] Since fans around Stand B are more interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[0937] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[0938] The processing flow will be explained below.

[0939] Step 1:

[0940] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically, data such as location information, visited locations, and length of stay in real time, and receives the data via HTTP requests and APIs.

[0941] Step 2:

[0942] The device collects location information and behavioral data from fans' smartphones or tablets and sends it to a server in real time. Users consent to the sharing of location information and the collection of behavioral data through the app.

[0943] Step 3:

[0944] The server uses an emotion engine to collect emotional data from fans. Specifically, it analyzes voice data and facial expression data from fans as they move around the venue to obtain emotional information.

[0945] Step 4:

[0946] The device captures audio and video data via the fan's smartphone or tablet and transmits this data to a server in real time.

[0947] Step 5:

[0948] The server preprocesses the collected behavioral and emotional data. Specifically, it complements missing values, corrects outliers, and standardizes the data. For emotional data, it also categorizes and scores emotions.

[0949] Step 6:

[0950] The server then feeds the pre-processed data into an artificial intelligence model for analysis, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions.

[0951] Step 7:

[0952] The server generates insights based on the analysis results, including recommended actions for specific fan groups and marketing strategies that take sentiment information into account.

[0953] Step 8:

[0954] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, while the terminal displays these visualized insights for the event organizers and teams to view and understand.

[0955] Specific examples

[0956] For example, suppose the following data is collected at a racing event:

[0957] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0958] Based on this data, the server generates insights like the following and displays them on the device:

[0959] Since fans around Stand B are highly interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[0960] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[0961] Example 2

[0962] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0963] Conventional fan experience delivery systems provide services based solely on fan behavioral data, and are unable to accurately capture fans' emotions and preferences. This has resulted in low accuracy in customizing the services and promotions provided, making it difficult to improve fan engagement. Furthermore, there is no system for centrally collecting and analyzing emotional and behavioral data, making integrated analysis of the data difficult. Given these circumstances, there is a need for an integrated collection and analysis of diverse data, including fans' emotional information, to provide highly accurate, customized fan experiences.

[0964] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting behavioral data of fans, a means for preprocessing the collected behavioral data and emotion data, and a means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to accurately grasp the behavioral patterns and emotions of fans and provide customized services to users.

[0965] "Behavioral data" refers to data that indicates how fans behaved within the event venue, such as their location, the places they visited, and the length of their stay.

[0966] "Emotional data" is data that indicates the emotional state of fans, obtained through voice analysis and facial expression analysis.

[0967] "Preprocessing" refers to the process of converting the collected raw data and emotion data into a format suitable for analysis by complementing missing values, correcting outliers, and standardizing them.

[0968] An "artificial intelligence model" is a model that uses algorithms such as machine learning and deep learning to analyze input data and extract patterns and features.

[0969] "Insights" are insights and recommended actions related to fan behavior and sentiment generated based on the analysis results.

[0970] "Sensors" are devices installed at event venues to collect fan behavior data. Examples include Wi-Fi beacons and GPS.

[0971] A "mobile app" is application software that fans install and use on their smartphones or tablets, and collects behavioral and emotional data.

[0972] "Terminal" refers to a mobile information terminal such as a smartphone or tablet held by a fan, which collects data and transmits it to the server.

[0973] "Data analysis" is the process of feeding pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions.

[0974] "Visualization" is a technique that makes information easier to understand visually by displaying the generated insights in the form of graphs and charts.

[0975] The present invention is a system for generating insights by collecting and analyzing behavioral data and emotional data of fans. This system is mainly composed of a server, terminals, and users working together. Specific embodiments of the system are described below.

[0976] Data collection

[0977] The server collects real-time behavioral data, such as location, visit locations, and duration of stay, from sensors installed at the event venue and mobile apps. Sensors such as Wi-Fi beacons and GPS can be used to determine which areas fans were in and how long they stayed there. For example, the server receives Wi-Fi beacon signals and updates the fan's location information.

[0978] The device sends data acquired from sensors and apps via the fan's smartphone or tablet to a server. The mobile app collects location and behavioral data at regular intervals and sends it to the server using the HTTPS protocol. When the user (fan) launches the app for the first time, they give consent to share their location information and collect behavioral data.

[0979] Emotional Data Collection

[0980] The server uses an emotion engine to analyze data collected from the device's camera and microphone to obtain emotional information about the fan. The camera captures facial expressions, and the microphone collects audio data. For example, the device's camera captures the user's facial expressions at regular intervals, while simultaneously collecting and sending audio data to the server.

[0981] The device sends this data to a server, which then uses voice and facial expression analysis to estimate emotions. Voice analysis extracts features such as pitch, tempo, and volume from the voice data, while facial expression analysis detects facial features to classify emotions.

[0982] Data Preprocessing

[0983] The server complements missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data. For example, if part of the location data is missing, it is complemented using an interpolation algorithm based on the preceding and following data. Furthermore, if an extremely high emotion score is obtained, it is clipped at an upper threshold.

[0984] The server also converts the preprocessed data into a format suitable for analysis, for example by scaling the sentiment scores to a range from 0 to 1.

[0985] Data analysis

[0986] The server then inputs the pre-processed data into an AI model to analyze fan behavior patterns, preferences, and emotions. Machine learning algorithms are used to analyze the data and identify common fan preferences and behavior patterns. For example, it can identify groups of fans who spend a long time in the same area and exhibit positive emotions.

[0987] Insight generation

[0988] The server generates customized insights based on the analysis results, such as "This fan base is interested in food stands and has positive sentiment," which provides useful recommended actions and marketing strategies for event organizers and teams.

[0989] Visualizing and presenting results

[0990] The server visualizes the generated insights in the form of graphs and charts and provides them to event organizers and teams using libraries such as Matplotlib and D3.js. The terminal displays these visualizations, allowing event organizers and teams to easily understand the information.

[0991] Specific examples

[0992] For example, the following data is collected at a race event:

[0993] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[0994] Based on this data, the server generates insights such as:

[0995] Fans around Stand B are more interested in food stands and have positive feelings about them, so it would be effective to run a special food promotion at the next event.

[0996] Examples of prompt statements

[0997] Examples of prompts for a generative AI model might include:

[0998] "Based on the data collected during the event, could you please tell us the results of your analysis of the relationship between the amount of time fans spent in a specific area and their emotional scores?"

[0999] This allows the AI ​​model to generate specific insights.

[1000] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1001] Step 1:

[1002] Data collection

[1003] The server collects real-time behavioral data such as location, visited locations, and length of stay from sensors installed at the event venue and mobile apps.

[1004] Input: Location information from sensors, behavioral data from mobile apps.

[1005] Data processing: Receives Wi-Fi beacon and GPS data and records fans' location information and time spent there.

[1006] Output: Recorded behavioral data.

[1007] How it works: The server periodically receives signals from sensors and stores the data in a database. For example, when a fan enters a specific area, it logs their location based on information received from Wi-Fi beacons.

[1008] Step 2:

[1009] Data transmission via fan terminals

[1010] The device transmits data obtained from sensors and apps to a server via the fan's smartphone or tablet.

[1011] Input: Location and behavioral data collected on the device.

[1012] Data processing: Data is batch processed at regular intervals and sent to the server using the HTTPS protocol.

[1013] Output: Behavioral data sent to the server.

[1014] Specific operation: The app sets the collection timing to every minute and sends behavioral data to the server each time, allowing data to be accumulated on the server in real time.

[1015] Step 3:

[1016] Obtaining User Consent

[1017] Users (fans) use the mobile app to give consent to share location information and collect behavioral data.

[1018] Input: The consent screen that appears when the app is first launched.

[1019] Data processing: Data collection will only begin once consent has been obtained.

[1020] Output: Data collection settings based on consent.

[1021] Specific behavior: When the app is launched for the first time, a pop-up regarding location usage and data collection will be displayed, and data collection will not begin until the user presses the consent button.

[1022] Step 4:

[1023] Emotional Data Collection

[1024] The server analyzes emotional information using data collected from the device's camera and microphone.

[1025] Input: Audio and image data sent from the device.

[1026] Data processing: Conduct voice analysis and facial expression analysis to estimate emotions.

[1027] Output: Sentiment score.

[1028] How it works: The device camera captures the user's face and the microphone collects their voice. These data are sent to the server in real time or in batches, and the emotion engine calculates an emotion score.

[1029] Step 5:

[1030] Data Preprocessing

[1031] The server imputes missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data.

[1032] Input: location data, behavioral data, emotion data.

[1033] Data processing: imputation of missing values, correction of outliers, standardization processing.

[1034] Output: Preprocessed data.

[1035] Specific operation: If there are gaps in the location information data, it will be interpolated based on the previous and following data. If an abnormally high value is found in the emotion score, it will be corrected by an upper threshold. This prepares the data in a state suitable for analysis.

[1036] Step 6:

[1037] Data analysis

[1038] The server then feeds the pre-processed data into an AI model to identify fan behavior patterns, preferences, and emotions.

[1039] Input: Preprocessed behavioral and emotional data.

[1040] Data processing: Analysis using machine learning algorithms.

[1041] Output: Analysis results (behavioral patterns, preferences, emotions).

[1042] Specific behavior: Using clustering techniques, we identify groups of fans with similar behavioral patterns, such as fans who spend a long time in the same area and show positive emotions.

[1043] Step 7:

[1044] Insight generation

[1045] The server generates customized insights based on the analysis results.

[1046] Input: Analysis results.

[1047] Data processing: Generating insights.

[1048] Output: Insights (recommended actions, marketing strategies).

[1049] What happens: Based on the analysis results, we can generate insights such as "This fan base is interested in food stands and has positive sentiments," which can then be used to plan special promotions for the next event.

[1050] Step 8:

[1051] Visualizing and presenting results

[1052] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, and the terminals display these visualizations.

[1053] Input: Generated insights.

[1054] Data processing: Visual content generation.

[1055] Output: The displayed graphs and charts.

[1056] Specific operation: Using libraries such as Matplotlib and D3.js, insights are displayed as timelines, heat maps, bar graphs, etc. In the mobile app on the device, this data is displayed on a dashboard and can be manipulated interactively.

[1057] (Application example 2)

[1058] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1059] Traditional fan engagement systems rely solely on behavioral data and are unable to grasp fan sentiment in real time, making it difficult to provide personalized fan experiences. Furthermore, the insights gained from analyzing the collected data are limited and lacking in accuracy. This makes them lack the ability to provide customized services based on fans' interests and emotions.

[1060] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting behavioral data and emotional data of fans, means for preprocessing the collected data, and means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to comprehensively analyze the behavior and emotions of fans and provide users with personalized recommended actions and marketing strategies based on the obtained insights.

[1061] "Behavioral Data" refers to data related to the behavior of fans or users, such as their physical location, visited pages, and duration of stay.

[1062] "Emotional data" is emotional information obtained through voice analysis and facial expression analysis of fans and users, and is data that indicates their emotional state, such as positive or negative.

[1063] "Preprocessing" refers to a series of processes such as data imputation, outlier correction, and standardization to convert collected raw data into a format suitable for analysis.

[1064] An "artificial intelligence model" is a model that uses machine learning and data analysis algorithms to analyze data and derive specific patterns and insights.

[1065] "Insights" are useful knowledge and discoveries obtained based on analyzed data, and are information that can be used to recommend actions and guide marketing strategies that are valuable to users.

[1066] "Personalized recommendations" are customized suggestions for services and promotions based on the individual behavioral patterns and emotional data of fans and users.

[1067] A "marketing strategy" refers to plans and actions designed to increase sales and customer satisfaction, taking into account the preferences and emotions of fans and users.

[1068] "Visualization" is the process of displaying analyzed data and insights in visual formats such as graphs and charts to make them easier to understand.

[1069] This invention is a system that collects and analyzes fan behavioral and emotional data to provide users with a customized fan experience. This system is realized primarily through collaboration between a server, terminals, and users.

[1070] Data collection

[1071] The server collects behavioral and emotional data from fans via sensors and mobile applications installed at event venues and virtual stores. Specifically, in addition to behavioral data such as fans' location, visited pages, and length of stay, it also uses smartphone cameras and microphones to analyze facial expressions and voices to obtain emotional data.

[1072] The terminal (e.g., a smartphone) is a device carried by the fan through which data is collected. An application on the terminal accesses the camera and microphone and transmits the data in real time to a server.

[1073] By using the application, users (fans) agree to the sharing of their location information and the collection of behavioral data, and enjoy the experience within the application.

[1074] Data Preprocessing

[1075] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by interpolating missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[1076] Data analysis

[1077] The pre-processed data is then fed into an artificial intelligence model by a server, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. The server then uses a machine learning platform such as Google Cloud AI Platform to perform the analysis.

[1078] Insight generation

[1079] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This user is interested in electronics and has positive emotions, so we recommend related accessories."

[1080] Visualizing and presenting results

[1081] The generated insights are visualized by the server in the form of graphs and charts and displayed within the user's smartphone application, allowing the user to easily understand the personalized recommended actions and enjoy the experience.

[1082] Specific examples

[1083] For example, if a user spends 15 minutes in the "electronics" section of a virtual store and displays positive emotions, the "related accessories" section will be recommended next.

[1084] Example prompt sentence:

[1085] Thanks for your attention! We understand you're interested in electronics. Why not take a look at some related accessories next?

[1086] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1087] Step 1:

[1088] Data collection

[1089] The device collects behavioral and emotional data from fans. Specifically, the smartphone application accesses the camera and microphone to capture location information, visited pages, time spent on the device, voice and facial expressions.

[1090] Inputs include location information from the smartphone's sensors, video data from the camera, and audio data from the microphone.

[1091] The output is the raw behavioral and emotional data collected.

[1092] Step 2:

[1093] Data transmission

[1094] The device sends the collected raw data to a server, where an application encrypts the data and sends it to the server over the Internet.

[1095] The input is raw behavioral and emotional data collected on the device.

[1096] The output is raw behavioral and emotional data sent to a server.

[1097] Step 3:

[1098] Data Preprocessing

[1099] The server preprocesses the collected raw data, including filling in missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[1100] The input is raw behavioral and emotional data sent from the device.

[1101] The output is the pre-processed data.

[1102] Step 4:

[1103] Data analysis

[1104] The server then feeds the pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions. Specifically, the data is analyzed using machine learning platforms such as Google Cloud AI Platform.

[1105] The input is preprocessed data.

[1106] The output is analysis results such as behavioral patterns, preferences, and emotional data.

[1107] Step 5:

[1108] Insight generation

[1109] The server generates customized insights based on the analysis results, specifically recommended actions and marketing strategies based on specific patterns and sentiments.

[1110] The input is behavioral patterns, preferences, and emotional data obtained from data analysis.

[1111] The output is the insight generated.

[1112] Step 6:

[1113] Visualizing and presenting results

[1114] The server visualizes the generated insights in the form of graphs and charts and sends them to the device, which displays the visualized insights in a smartphone application and provides the user with personalized recommended actions and marketing strategies.

[1115] The input is the generated insight.

[1116] The output is a recommended action or marketing strategy that is displayed within the smartphone application.

[1117] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1118] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1119] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1120] [Fourth embodiment]

[1121] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1122] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1123] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1124] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1125] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1128] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1129] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1130] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1132] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1133] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1134] The present invention is a system that collects and analyzes fan behavior data and provides customized insights to event organizers and teams based on the results. This system is realized through the collaboration of a server, terminals, and users.

[1135] Data collection

[1136] The server collects data in real time from sensors placed at the event venue and from mobile apps used by fans. Specifically, this data includes location information, places visited, length of stay, and purchase history. The devices, such as fans' smartphones and tablets, automatically record location information and behavioral data and send it to the server. Users (fans) grant permission for data collection through the app as they move around the event venue.

[1137] Data Preprocessing

[1138] The server preprocesses the collected raw data, including imputing missing values, correcting outliers, and standardizing the data to ensure data quality and convert it into a format suitable for analysis.

[1139] Data analysis

[1140] The server then feeds the pre-processed data into an artificial intelligence model, which uses machine learning algorithms to analyze the data and identify fan behavior patterns and preferences. For example, it determines that fans who spend a lot of time in a particular area are likely to be interested in services and promotions related to that area.

[1141] Insight generation

[1142] Based on the analysis, the server generates customized insights, including recommended actions and marketing strategies for specific fan segments. For example, an insight could be, "This fan segment is interested in food stands, so we'll offer special food promotions at our next event."

[1143] Visualizing and presenting results

[1144] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams. The terminal displays these visualizations so that users can easily understand them. Users (event organizers and teams) can use these insights to optimize their event operations and marketing strategies.

[1145] Specific examples

[1146] For example, suppose the following data is collected at a race event:

[1147] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[1148] Based on this data, the server generates insights such as:

[1149] Fans around Stand B are very interested in the food stands.

[1150] At your next event, it would be beneficial to run a special food promotion around Stand B.

[1151] This allows event organizers and teams to improve fan engagement by providing personalized services based on fan preferences and behavior.

[1152] The processing flow will be explained below.

[1153] Step 1:

[1154] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically via HTTP requests and APIs to obtain real-time data such as location information, visited locations, and duration of stay.

[1155] Step 2:

[1156] The device collects data from fans' smartphones or tablets through an app and sends it to a server. Users consent to location sharing within the app, and the collection is applied.

[1157] Step 3:

[1158] The server preprocesses the collected raw data by imputing missing values, correcting outliers, and standardizing the data to convert it into a format suitable for analysis. Specifically, it applies preprocessing techniques including data cleansing, filtering, and scaling.

[1159] Step 4:

[1160] The server then feeds the pre-processed data into an artificial intelligence model for analysis. Machine learning algorithms are used to analyze the data and identify fan behavior patterns and preferences, often using clustering and classification techniques.

[1161] Step 5:

[1162] The server generates insights based on the analysis, which include recommended actions and marketing strategies based on fan interests, such as suggesting campaigns targeted to fan groups interested in specific locations.

[1163] Step 6:

[1164] The server visualizes the generated insights in the form of graphs and charts, and uses data visualization tools to display the insights in an intuitive and easy-to-understand way.

[1165] Step 7:

[1166] The device displays visualized insights that can be viewed by event organizers and teams, who can then use these insights to optimize their event operations and marketing strategies.

[1167] Specific examples

[1168] For example, the following data is collected at a race event:

[1169] Fan A stays in Stand B for 15 minutes and then goes to the food stand.

[1170] After going through steps 1 to 7, the server generates the following insight and displays it on the device:

[1171] Fans around Stand B are very interested in the food stands.

[1172] At your next event, it would be beneficial to run a special food promotion around Stand B.

[1173] This allows event organizers and teams to offer personalized services based on fan preferences and behavior, improving fan engagement.

[1174] Example 1

[1175] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1176] In conventional event management, there were few ways to effectively collect visitor behavior data and gain customized insights based on that data. As a result, it was difficult to accurately understand visitor needs and implement effective marketing strategies and services based on those needs. This led to issues such as insufficient improvement of event satisfaction and participant engagement.

[1177] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1178] In this invention, the server includes means for collecting visitor behavior data at an event, means for preprocessing the collected data, means for analyzing the preprocessed data using a machine learning algorithm, means for generating customized insights based on the analysis results, and means for displaying the generated insights as graphs or charts. This makes it possible to effectively collect and analyze visitor behavior data and provide customized insights based on the results. This allows event organizers to accurately understand visitor needs and implement effective marketing strategies and service provision based on those needs, significantly improving event satisfaction and participant engagement.

[1179] "Behavioral data" refers to data such as a visitor's location, the places they visited, the length of their stay, and their purchase history.

[1180] "Data preprocessing" refers to the process of imputing missing values, correcting outliers, and standardizing collected raw data.

[1181] A "machine learning algorithm" is an algorithm that learns patterns based on past data and makes predictions and classifications for future data.

[1182] "Customized insights" are specific suggestions based on analysis results, such as recommended actions and marketing strategies for specific visitor groups.

[1183] "Graphs and charts" are shapes that visually represent collected and analyzed data and generated insights.

[1184] "Event Organizer" means the person or entity responsible for planning, conducting and managing an Event.

[1185] This invention is a system that collects and analyzes visitor behavior data and provides customized insights based on the results, and is realized through the collaboration of servers, terminals, and users.

[1186] Data collection

[1187] The server collects real-time data from multiple sensors placed around the event venue. These sensors include Bluetooth beacons and Wi-Fi access points. These sensors communicate with visitors' smartphones to obtain location information. Mobile apps used by visitors also send data to the server. This data includes location information, locations visited, length of stay, and purchase history.

[1188] The devices are the visitors' smartphones or tablets, which use location services in the background to collect the visitor's location data. For example, when a visitor enters a certain area, the location information is automatically updated and sent to the server.

[1189] When users (visitors) arrive at the event venue, they open the mobile app and grant permission for data collection, specifically by turning on location sharing and in-app notifications.

[1190] Data Preprocessing

[1191] The server pre-processes the collected raw data, including imputing missing values, correcting outliers, and standardizing the data. Specifically, it performs the following processes:

[1192] 1. Data imputation: If some location information is missing, it is imputed using data from adjacent time intervals.

[1193] 2. Anomaly correction: If a visitor suddenly moves beyond the range of the sensor, the data will be deleted or corrected as an anomaly.

[1194] 3. Data standardization: To process collected data on a unified scale, convert coordinate data and other data into a standard format. Use a Python numerical processing library (e.g., Pandas, NumPy).

[1195] Data analysis

[1196] The server then feeds the preprocessed data into an artificial intelligence model, for example using a machine learning library such as Scikit-learn or TensorFlow, to build a model that performs the following analyses:

[1197] 1. Behavioral pattern analysis: Analyze the behavioral patterns of visitors who stay in a specific area for a long time.

[1198] 2. Preference analysis: Identify which foods visitors are interested in based on the number of times they visit the food stand and the time of day.

[1199] Insight generation

[1200] The server generates customized insights based on the data analysis results, including, for example:

[1201] 1. Generate recommended actions: Generate recommended actions for specific visitor demographics.

[1202] Example: An insight that says, "Visitors gathering around Stand G are interested in a particular beverage, so we should promote beverages in that area."

[1203] 2. Marketing strategy proposal: Propose effective measures for the next event.

[1204] Example: "At our next event, we'll be running a special food promotion around Stand B."

[1205] Visualizing and presenting results

[1206] The server visualizes the generated insights as graphs and charts, using the following tools:

[1207] 1. Tableau or Power BI: Generate graphs to visually represent behavioral patterns and preferences.

[1208] 2. Dashboard: Organize insights and present them in an easily accessible format for event organizers and teams.

[1209] The device displays these visualizations, and event organizers and teams can check various graphs and charts on the device to plan on-site measures.

[1210] Users (event organizers and teams) can use the insights provided by the server to optimize their event management and marketing strategies, specifically adjusting the placement and promotional content of their next event.

[1211] Prompt Sentence Examples

[1212] Suggest a marketing strategy for your next event based on the following behavioral data:

[1213] Fan A stayed in Stand B for 15 minutes and then went to the food stand. Use this data to provide insights into services and promotions relevant to that specific area.

[1214] The above is an embodiment of the present invention.

[1215] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1216] Step 1: Data collection

[1217] The server collects data from sensors placed at the event venue and from mobile apps used by visitors. Input includes location information from Bluetooth beacons and Wi-Fi access points, visited locations, length of stay, and purchase history. Specifically, when a visitor enters a specific area, the sensor communicates with the smartphone and sends the location information to the server. The output is streaming location information and behavioral data.

[1218] Step 2: Data Preprocessing

[1219] The server preprocesses the collected data. The input is raw data (location information, visited locations, duration of stay, etc.). If there are missing values ​​in the data at this stage, they are filled in using data from adjacent time intervals. Outliers are removed or corrected. For example, if a visitor moves out of the sensor range at high speed, it is considered an outlier. The server also converts the collected data into a standard format. This process improves the quality of the data and makes it consistent. The output is preprocessed, clean data.

[1220] Step 3: Data analysis

[1221] The server analyzes the preprocessed data using machine learning algorithms. The input is the preprocessed dataset. Specifically, Scikit-learn and TensorFlow are used to analyze and model visitor behavior patterns. Behavior pattern analysis identifies, for example, patterns where visitors spend a long time in a particular area. Preference analysis identifies groups of visitors who may be interested in specific promotions or services. The output is the identified patterns and preference information as the analysis results.

[1222] Step 4: Insight generation

[1223] The server generates customized insights based on the analysis results. The input is the results of data analysis. Specifically, based on the analysis results, it automatically generates recommended actions and marketing strategies tailored to the visitor demographic. For example, it generates an insight that "Since many visitors gather around Stand G, we should implement a beverage promotion in this area." The output is customized insights.

[1224] Step 5: Visualize and deliver results

[1225] The server visualizes the generated insights as graphs and charts. The input is the generated customized insights. Specifically, a data visualization tool (e.g., Tableau or Power BI) is used to visually represent the analysis results, which clearly visualizes visitor behavior patterns and preferences. The terminal displays these visualizations and provides them to the user (event organizer or team) in a format that is easy to understand. The output is visualized insights based on attendee behavior patterns.

[1226] The above is a detailed description of each processing step of the system.

[1227] (Application example 1)

[1228] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1229] Conventional systems do not fully utilize behavioral data of fans and customers at event venues and brick-and-mortar stores, making it difficult to optimize personalized promotion strategies based on customer behavior patterns and preferences. Furthermore, there is a lack of means to clearly visualize the analysis results and make them specifically useful for store management.

[1230] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1231] In this invention, the server includes means for collecting fan behavior data, means for preprocessing the collected data, means for analyzing the preprocessed data using an artificial intelligence model, means for generating insights based on the analysis results, and means for displaying the generated insights and providing promotion strategies, thereby enabling the development of effective promotion strategies based on customer behavior patterns and preferences and the specific visualization of the results.

[1232] "Fan behavior data" refers to data such as the location information of customers (fans) at event venues and physical stores, the places they visit, the length of their stay, and their purchase history.

[1233] "Means for preprocessing collected data" refers to means for executing processes to ensure data quality and convert the data into a format suitable for analysis, such as completing missing values ​​in the data, correcting outliers, and standardizing the data.

[1234] An "artificial intelligence model" is a model that uses machine learning algorithms and other techniques to analyze pre-processed data and identify fan behavior patterns and preferences.

[1235] "Means for generating insights" are means that have the ability to propose recommended actions and promotional strategies for specific fan groups based on the analysis results.

[1236] "Means for displaying the generated insights and providing promotion strategies" refers to means for visualizing the insights obtained through analysis in the form of graphs and charts, displaying them in a way that is easy for operators of event venues and physical stores to understand, and providing specific promotion strategies based on them.

[1237] This invention is a system that collects and analyzes behavioral data of fans and customers at event venues and brick-and-mortar stores, and provides customized promotional strategies based on that data. This system is realized primarily through the collaboration of a server, terminals, and users.

[1238] Data collection

[1239] The server collects data in real time from sensors placed at event venues and brick-and-mortar stores, as well as from mobile apps used by customers. Specifically, data such as location information, places visited, length of stay, and purchase history is collected. The devices are smartphones and tablets held by customers, which automatically record behavioral data and send it to the server. Users (customers) give permission for data collection through the app.

[1240] Data Preprocessing

[1241] The server preprocesses the collected raw data using data processing libraries such as Pandas to impute missing values, correct outliers, and standardize the data, thereby ensuring data quality and converting it into a format suitable for analysis.

[1242] Data analysis

[1243] The server then feeds the preprocessed data into an artificial intelligence model, which uses machine learning algorithms such as Scikit-learn to analyze the data and identify customer behavioral patterns and preferences. For example, if a customer spends a long time in a particular area, it can determine that they are likely interested in products and services related to that area.

[1244] Insight generation

[1245] Based on the analysis results, the server generates customized insights, including recommended actions and promotion strategies for specific customer segments. For example, an insight might be, "This customer segment is interested in the snack area, so we'll offer a special snack promotion at the next event." The insights can also be visualized using Matplotlib and displayed in graphs and charts.

[1246] Providing results

[1247] The generated insights are visualized in graphs and charts by the server and provided to event and store managers. The terminal displays these visualizations so that users can easily understand them. Users (managers) can use these insights to optimize their event and store operations and further marketing strategies.

[1248] Specific examples

[1249] For example, suppose a store collects the following data:

[1250] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[1251] Customer B stayed in the beverage area for 15 minutes.

[1252] Based on this data, the server generates insights such as:

[1253] Customers around the general goods area are very interested in snacks.

[1254] For your next store promotion, it would be effective to run a special snack promotion around the general merchandise area.

[1255] This allows event organizers and store operators to provide personalized services based on customer preferences and behavior, improving fan engagement.

[1256] Example prompts to be input to the generative AI model

[1257] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[1258] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[1259] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1260] Step 1: Data collection

[1261] The server collects data in real time from sensors placed at event venues and physical stores, as well as from smartphone apps used by customers. Specifically, the data collected includes location information, visited locations, length of stay, and purchase history. The device (customer's smartphone) automatically records this data and sends it to the server. The user (customer) gives permission for data collection through the app, which then initiates data collection.

[1262] Input: Raw data from sensors and smartphone apps (location information, visit locations, stay times, purchase history)

[1263] Output: Raw behavioral data aggregated on the server

[1264] Step 2: Data Preprocessing

[1265] The server preprocesses the collected raw data by using Pandas to impute missing values, correct outliers, and standardize the collected data, thereby ensuring data quality and converting it into a format suitable for analysis.

[1266] Input: Collected raw behavioral data

[1267] Output: Preprocessed data with missing value imputation, outlier correction, and standardization

[1268] Step 3: Data analysis

[1269] The preprocessed data is fed into an artificial intelligence model by the server, which then uses machine learning algorithms such as Scikit-learn's KMeans to cluster the data and identify customer behavior patterns and preferences. The server then determines which cluster each customer's behavior data belongs to and analyzes the characteristics of each cluster.

[1270] Input: Preprocessed behavioral data

[1271] Output: Clustering results for each customer and cluster feature data

[1272] Step 4: Insight generation

[1273] The server generates customized insights based on the results of the clustering analysis. Specifically, it generates data for each cluster to suggest the level of interest in specific product areas and promotion strategies. In this process, marketing strategies are proposed based on the average values ​​and behavioral patterns of each cluster.

[1274] Input: Clustering results and cluster feature data

[1275] Output: Insights for specific customer segments (e.g., promotional strategy suggestions)

[1276] Step 5: Visualize and deliver results

[1277] The server visualizes the generated insights in the form of graphs and charts, using visualization libraries such as Matplotlib to display the insights in an easy-to-understand format. The terminal displays these visualizations so that users (event organizers and store operators) can easily understand them.

[1278] Input: Generated insights

[1279] Output: Visualized insights in the form of graphs and charts, displayed visualizations

[1280] As a concrete example, consider the following data collected at a store:

[1281] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area.

[1282] Customer B stayed in the beverage area for 15 minutes.

[1283] Based on this data, the server generates a prompt like this:

[1284] Customer A stayed in the general goods area for 10 minutes and then moved to the snack area. Customer B stayed in the beverage area for 15 minutes. Use this data to analyze customer behavior patterns and preferences.

[1285] This provides a foundation for implementing specific and effective promotional strategies for events and store operations.

[1286] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1287] The present invention is a system that collects and analyzes fan behavior data to generate insights, and combines this with an emotion engine that recognizes user emotions to provide a more accurate and customized fan experience. This system is composed of a server, terminals, and users working together.

[1288] Data collection

[1289] The server collects fan behavior data from sensors installed at the event venue and from mobile apps. Specifically, it obtains data such as location information, visited locations, and length of stay in real time. The device collects data from fans' smartphones or tablets and sends it to the server. Users (fans) give consent to share their location information and collect behavioral data through the app.

[1290] Emotional Data Collection

[1291] The server also uses an emotion engine to collect emotional data from fans. This emotional data includes emotional information obtained through voice analysis and facial expression analysis. The device transmits the data acquired through the camera and microphone to the server.

[1292] Data Preprocessing

[1293] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by imputing missing values, correcting outliers, and standardizing the data. For emotion data, it also categorizes and scores emotions.

[1294] Data analysis

[1295] The server then inputs the pre-processed data into an artificial intelligence model. The server then uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. For example, if fans who spend a long time in a particular area have positive emotions, the server determines that they are likely to be interested in services and promotions related to that area.

[1296] Insight generation

[1297] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This fan base is interested in food stands and has positive emotions, so we'll offer special food promotions at our next event."

[1298] Visualizing and presenting results

[1299] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizer or team. The device displays these visualizations, allowing the event organizer or team to easily understand the information. The user (event organizer or team) can then use these insights to optimize their event operations and marketing strategies.

[1300] Specific examples

[1301] For example, the following data is collected at a race event:

[1302] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[1303] Based on this data, the server generates insights such as:

[1304] Since fans around Stand B are more interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[1305] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[1306] The processing flow will be explained below.

[1307] Step 1:

[1308] The server collects fan behavior data from sensors installed at the event venue and mobile apps, specifically, data such as location information, visited locations, and length of stay in real time, and receives the data via HTTP requests and APIs.

[1309] Step 2:

[1310] The device collects location information and behavioral data from fans' smartphones or tablets and sends it to a server in real time. Users consent to the sharing of location information and the collection of behavioral data through the app.

[1311] Step 3:

[1312] The server uses an emotion engine to collect emotional data from fans. Specifically, it analyzes voice data and facial expression data from fans as they move around the venue to obtain emotional information.

[1313] Step 4:

[1314] The device captures audio and video data via the fan's smartphone or tablet and transmits this data to a server in real time.

[1315] Step 5:

[1316] The server preprocesses the collected behavioral and emotional data. Specifically, it complements missing values, corrects outliers, and standardizes the data. For emotional data, it also categorizes and scores emotions.

[1317] Step 6:

[1318] The server then feeds the pre-processed data into an artificial intelligence model for analysis, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions.

[1319] Step 7:

[1320] The server generates insights based on the analysis results, including recommended actions for specific fan groups and marketing strategies that take sentiment information into account.

[1321] Step 8:

[1322] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, while the terminal displays these visualized insights for the event organizers and teams to view and understand.

[1323] Specific examples

[1324] For example, suppose the following data is collected at a racing event:

[1325] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[1326] Based on this data, the server generates insights like the following and displays them on the device:

[1327] Since fans around Stand B are highly interested in food stands and have positive feelings about them, it would be effective to run a special food promotion around Stand B at the next event.

[1328] This allows event organizers and teams to provide personalized services based on fans' preferences and emotions, improving fan engagement.

[1329] Example 2

[1330] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1331] Conventional fan experience delivery systems provide services based solely on fan behavioral data, and are unable to accurately capture fans' emotions and preferences. This has resulted in low accuracy in customizing the services and promotions provided, making it difficult to improve fan engagement. Furthermore, there is no system for centrally collecting and analyzing emotional and behavioral data, making integrated analysis of the data difficult. Given these circumstances, there is a need for an integrated collection and analysis of diverse data, including fans' emotional information, to provide highly accurate, customized fan experiences.

[1332] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting behavioral data of fans, a means for preprocessing the collected behavioral data and emotion data, and a means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to accurately grasp the behavioral patterns and emotions of fans and provide customized services to users.

[1333] "Behavioral data" refers to data that indicates how fans behaved within the event venue, such as their location, the places they visited, and the length of their stay.

[1334] "Emotional data" is data that indicates the emotional state of fans, obtained through voice analysis and facial expression analysis.

[1335] "Preprocessing" refers to the process of converting the collected raw data and emotion data into a format suitable for analysis by complementing missing values, correcting outliers, and standardizing them.

[1336] An "artificial intelligence model" is a model that uses algorithms such as machine learning and deep learning to analyze input data and extract patterns and features.

[1337] "Insights" are insights and recommended actions related to fan behavior and sentiment generated based on the analysis results.

[1338] "Sensors" are devices installed at event venues to collect fan behavior data. Examples include Wi-Fi beacons and GPS.

[1339] A "mobile app" is application software that fans install and use on their smartphones or tablets, and collects behavioral and emotional data.

[1340] "Terminal" refers to a mobile information terminal such as a smartphone or tablet held by a fan, which collects data and transmits it to the server.

[1341] "Data analysis" is the process of feeding pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions.

[1342] "Visualization" is a technique that makes information easier to understand visually by displaying the generated insights in the form of graphs and charts.

[1343] The present invention is a system for generating insights by collecting and analyzing behavioral data and emotional data of fans. This system is mainly composed of a server, terminals, and users working together. Specific embodiments of the system are described below.

[1344] Data collection

[1345] The server collects real-time behavioral data, such as location, visit locations, and duration of stay, from sensors installed at the event venue and mobile apps. Sensors such as Wi-Fi beacons and GPS can be used to determine which areas fans were in and how long they stayed there. For example, the server receives Wi-Fi beacon signals and updates the fan's location information.

[1346] The device sends data acquired from sensors and apps via the fan's smartphone or tablet to a server. The mobile app collects location and behavioral data at regular intervals and sends it to the server using the HTTPS protocol. When the user (fan) launches the app for the first time, they give consent to share their location information and collect behavioral data.

[1347] Emotional Data Collection

[1348] The server uses an emotion engine to analyze data collected from the device's camera and microphone to obtain emotional information about the fan. The camera captures facial expressions, and the microphone collects audio data. For example, the device's camera captures the user's facial expressions at regular intervals, while simultaneously collecting and sending audio data to the server.

[1349] The device sends this data to a server, which then uses voice and facial expression analysis to estimate emotions. Voice analysis extracts features such as pitch, tempo, and volume from the voice data, while facial expression analysis detects facial features to classify emotions.

[1350] Data Preprocessing

[1351] The server complements missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data. For example, if part of the location data is missing, it is complemented using an interpolation algorithm based on the preceding and following data. Furthermore, if an extremely high emotion score is obtained, it is clipped at an upper threshold.

[1352] The server also converts the preprocessed data into a format suitable for analysis, for example by scaling the sentiment scores to a range from 0 to 1.

[1353] Data analysis

[1354] The server then inputs the pre-processed data into an AI model to analyze fan behavior patterns, preferences, and emotions. Machine learning algorithms are used to analyze the data and identify common fan preferences and behavior patterns. For example, it can identify groups of fans who spend a long time in the same area and exhibit positive emotions.

[1355] Insight generation

[1356] The server generates customized insights based on the analysis results, such as "This fan base is interested in food stands and has positive sentiment," which provides useful recommended actions and marketing strategies for event organizers and teams.

[1357] Visualizing and presenting results

[1358] The server visualizes the generated insights in the form of graphs and charts and provides them to event organizers and teams using libraries such as Matplotlib and D3.js. The terminal displays these visualizations, allowing event organizers and teams to easily understand the information.

[1359] Specific examples

[1360] For example, the following data is collected at a race event:

[1361] Fan A stayed in Stand B for 15 minutes, then went to the food stand, and displayed positive emotions during his stay.

[1362] Based on this data, the server generates insights such as:

[1363] Fans around Stand B are more interested in food stands and have positive feelings about them, so it would be effective to run a special food promotion at the next event.

[1364] Examples of prompt statements

[1365] Examples of prompts for a generative AI model might include:

[1366] "Based on the data collected during the event, could you please tell us the results of your analysis of the relationship between the amount of time fans spent in a specific area and their emotional scores?"

[1367] This allows the AI ​​model to generate specific insights.

[1368] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1369] Step 1:

[1370] Data collection

[1371] The server collects real-time behavioral data such as location, visited locations, and length of stay from sensors installed at the event venue and mobile apps.

[1372] Input: Location information from sensors, behavioral data from mobile apps.

[1373] Data processing: Receives Wi-Fi beacon and GPS data and records fans' location information and time spent there.

[1374] Output: Recorded behavioral data.

[1375] How it works: The server periodically receives signals from sensors and stores the data in a database. For example, when a fan enters a specific area, it logs their location based on information received from Wi-Fi beacons.

[1376] Step 2:

[1377] Data transmission via fan terminals

[1378] The device transmits data obtained from sensors and apps to a server via the fan's smartphone or tablet.

[1379] Input: Location and behavioral data collected on the device.

[1380] Data processing: Data is batch processed at regular intervals and sent to the server using the HTTPS protocol.

[1381] Output: Behavioral data sent to the server.

[1382] Specific operation: The app sets the collection timing to every minute and sends behavioral data to the server each time, allowing data to be accumulated on the server in real time.

[1383] Step 3:

[1384] Obtaining User Consent

[1385] Users (fans) use the mobile app to give consent to share location information and collect behavioral data.

[1386] Input: The consent screen that appears when the app is first launched.

[1387] Data processing: Data collection will only begin once consent has been obtained.

[1388] Output: Data collection settings based on consent.

[1389] Specific behavior: When the app is launched for the first time, a pop-up regarding location usage and data collection will be displayed, and data collection will not begin until the user presses the consent button.

[1390] Step 4:

[1391] Emotional Data Collection

[1392] The server analyzes emotional information using data collected from the device's camera and microphone.

[1393] Input: Audio and image data sent from the device.

[1394] Data processing: Conduct voice analysis and facial expression analysis to estimate emotions.

[1395] Output: Sentiment score.

[1396] How it works: The device camera captures the user's face and the microphone collects their voice. These data are sent to the server in real time or in batches, and the emotion engine calculates an emotion score.

[1397] Step 5:

[1398] Data Preprocessing

[1399] The server imputes missing values ​​in the collected raw data and emotion data, corrects outliers, and standardizes the data.

[1400] Input: location data, behavioral data, emotion data.

[1401] Data processing: imputation of missing values, correction of outliers, standardization processing.

[1402] Output: Preprocessed data.

[1403] Specific operation: If there are gaps in the location information data, it will be interpolated based on the previous and following data. If an abnormally high value is found in the emotion score, it will be corrected by an upper threshold. This prepares the data in a state suitable for analysis.

[1404] Step 6:

[1405] Data analysis

[1406] The server then feeds the pre-processed data into an AI model to identify fan behavior patterns, preferences, and emotions.

[1407] Input: Preprocessed behavioral and emotional data.

[1408] Data processing: Analysis using machine learning algorithms.

[1409] Output: Analysis results (behavioral patterns, preferences, emotions).

[1410] Specific behavior: Using clustering techniques, we identify groups of fans with similar behavioral patterns, such as fans who spend a long time in the same area and show positive emotions.

[1411] Step 7:

[1412] Insight generation

[1413] The server generates customized insights based on the analysis results.

[1414] Input: Analysis results.

[1415] Data processing: Generating insights.

[1416] Output: Insights (recommended actions, marketing strategies).

[1417] What happens: Based on the analysis results, we can generate insights such as "This fan base is interested in food stands and has positive sentiments," which can then be used to plan special promotions for the next event.

[1418] Step 8:

[1419] Visualizing and presenting results

[1420] The server visualizes the generated insights in the form of graphs and charts and provides them to the event organizers and teams, and the terminals display these visualizations.

[1421] Input: Generated insights.

[1422] Data processing: Visual content generation.

[1423] Output: The displayed graphs and charts.

[1424] Specific operation: Using libraries such as Matplotlib and D3.js, insights are displayed as timelines, heat maps, bar graphs, etc. In the mobile app on the device, this data is displayed on a dashboard and can be manipulated interactively.

[1425] (Application example 2)

[1426] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1427] Traditional fan engagement systems rely solely on behavioral data and are unable to grasp fan sentiment in real time, making it difficult to provide personalized fan experiences. Furthermore, the insights gained from analyzing the collected data are limited and lacking in accuracy. This makes them lack the ability to provide customized services based on fans' interests and emotions.

[1428] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting behavioral data and emotional data of fans, means for preprocessing the collected data, and means for analyzing the preprocessed data using an artificial intelligence model. This makes it possible to comprehensively analyze the behavior and emotions of fans and provide users with personalized recommended actions and marketing strategies based on the obtained insights.

[1429] "Behavioral Data" refers to data related to the behavior of fans or users, such as their physical location, visited pages, and duration of stay.

[1430] "Emotional data" is emotional information obtained through voice analysis and facial expression analysis of fans and users, and is data that indicates their emotional state, such as positive or negative.

[1431] "Preprocessing" refers to a series of processes such as data imputation, outlier correction, and standardization to convert collected raw data into a format suitable for analysis.

[1432] An "artificial intelligence model" is a model that uses machine learning and data analysis algorithms to analyze data and derive specific patterns and insights.

[1433] "Insights" are useful knowledge and discoveries obtained based on analyzed data, and are information that can be used to recommend actions and guide marketing strategies that are valuable to users.

[1434] "Personalized recommendations" are customized suggestions for services and promotions based on the individual behavioral patterns and emotional data of fans and users.

[1435] A "marketing strategy" refers to plans and actions designed to increase sales and customer satisfaction, taking into account the preferences and emotions of fans and users.

[1436] "Visualization" is the process of displaying analyzed data and insights in visual formats such as graphs and charts to make them easier to understand.

[1437] This invention is a system that collects and analyzes fan behavioral and emotional data to provide users with a customized fan experience. This system is realized primarily through collaboration between a server, terminals, and users.

[1438] Data collection

[1439] The server collects behavioral and emotional data from fans via sensors and mobile applications installed at event venues and virtual stores. Specifically, in addition to behavioral data such as fans' location, visited pages, and length of stay, it also uses smartphone cameras and microphones to analyze facial expressions and voices to obtain emotional data.

[1440] The terminal (e.g., a smartphone) is a device carried by the fan through which data is collected. An application on the terminal accesses the camera and microphone and transmits the data in real time to a server.

[1441] By using the application, users (fans) agree to the sharing of their location information and the collection of behavioral data, and enjoy the experience within the application.

[1442] Data Preprocessing

[1443] The server preprocesses the collected raw data and emotion data. Specifically, it converts the data into a format suitable for analysis by interpolating missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[1444] Data analysis

[1445] The pre-processed data is then fed into an artificial intelligence model by a server, which uses machine learning algorithms to analyze the data and identify fan behavior patterns, preferences, and emotions. The server then uses a machine learning platform such as Google Cloud AI Platform to perform the analysis.

[1446] Insight generation

[1447] Based on the analysis results, the server generates customized insights, including recommended actions and marketing strategies that take into account the user's emotional information. For example, the insight could be, "This user is interested in electronics and has positive emotions, so we recommend related accessories."

[1448] Visualizing and presenting results

[1449] The generated insights are visualized by the server in the form of graphs and charts and displayed within the user's smartphone application, allowing the user to easily understand the personalized recommended actions and enjoy the experience.

[1450] Specific examples

[1451] For example, if a user spends 15 minutes in the "electronics" section of a virtual store and displays positive emotions, the "related accessories" section will be recommended next.

[1452] Example prompt sentence:

[1453] Thanks for your attention! We understand you're interested in electronics. Why not take a look at some related accessories next?

[1454] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1455] Step 1:

[1456] Data collection

[1457] The device collects behavioral and emotional data from fans. Specifically, the smartphone application accesses the camera and microphone to capture location information, visited pages, time spent on the device, voice and facial expressions.

[1458] Inputs include location information from the smartphone's sensors, video data from the camera, and audio data from the microphone.

[1459] The output is the raw behavioral and emotional data collected.

[1460] Step 2:

[1461] Data transmission

[1462] The device sends the collected raw data to a server, where an application encrypts the data and sends it to the server over the Internet.

[1463] The input is raw behavioral and emotional data collected on the device.

[1464] The output is raw behavioral and emotional data sent to a server.

[1465] Step 3:

[1466] Data Preprocessing

[1467] The server preprocesses the collected raw data, including filling in missing values, correcting outliers, and standardizing the data. It also categorizes and scores emotion data.

[1468] The input is raw behavioral and emotional data sent from the device.

[1469] The output is the pre-processed data.

[1470] Step 4:

[1471] Data analysis

[1472] The server then feeds the pre-processed data into an artificial intelligence model to identify fan behavior patterns, preferences, and emotions. Specifically, the data is analyzed using machine learning platforms such as Google Cloud AI Platform.

[1473] The input is preprocessed data.

[1474] The output is analysis results such as behavioral patterns, preferences, and emotional data.

[1475] Step 5:

[1476] Insight generation

[1477] The server generates customized insights based on the analysis results, specifically recommended actions and marketing strategies based on specific patterns and sentiments.

[1478] The input is behavioral patterns, preferences, and emotional data obtained from data analysis.

[1479] The output is the insight generated.

[1480] Step 6:

[1481] Visualizing and presenting results

[1482] The server visualizes the generated insights in the form of graphs and charts and sends them to the device, which displays the visualized insights in a smartphone application and provides the user with personalized recommended actions and marketing strategies.

[1483] The input is the generated insight.

[1484] The output is a recommended action or marketing strategy that is displayed within the smartphone application.

[1485] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1486] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1487] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1488] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1489] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1490] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1491] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1492] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1493] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1494] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1495] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1496] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1497] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1498] 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.

[1499] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1500] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1501] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1502] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1503] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1504] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1505] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1506] The following is further disclosed regarding the above embodiment.

[1507] (Claim 1)

[1508] A means of collecting fan behavior data;

[1509] means for pre-processing the collected data;

[1510] means for analyzing the preprocessed data with an artificial intelligence model;

[1511] a means for generating insights based on the analysis results;

[1512] a means of displaying the generated insights;

[1513] A system including:

[1514] (Claim 2)

[1515] 10. The system of claim 1, wherein the system collects data including fan location and behavior data.

[1516] (Claim 3)

[1517] 10. The system of claim 1, wherein the generated insights are visualized as graphs or charts.

[1518] "Example 1"

[1519] (Claim 1)

[1520] A means of collecting visitor behavior data at the event;

[1521] means for pre-processing the collected data;

[1522] means for analyzing the preprocessed data using a machine learning algorithm;

[1523] a means for generating customized insights based on the analysis results;

[1524] A means to display the generated insights as graphs and charts;

[1525] A system including:

[1526] (Claim 2)

[1527] 10. The system of claim 1, wherein the system collects data including visitor location and behavioral data.

[1528] (Claim 3)

[1529] 10. The system of claim 1, wherein the system outputs a visual representation of the generated insights.

[1530] "Application Example 1"

[1531] (Claim 1)

[1532] A means of collecting fan behavior data;

[1533] means for pre-processing the collected data;

[1534] means for analyzing the preprocessed data with an artificial intelligence model;

[1535] a means for generating insights based on the analysis results;

[1536] A means to display the generated insights and inform promotion strategies;

[1537] A system including:

[1538] (Claim 2)

[1539] 10. The system of claim 1, wherein data including location information and behavioral data of fans is collected and analyzed to analyze customer behavior patterns within the store.

[1540] (Claim 3)

[1541] The system of claim 1, wherein the generated insights are visualized as graphs or charts and utilized as marketing data.

[1542] "Example 2: Combining Emotion Engines"

[1543] (Claim 1)

[1544] A means of collecting fan behavior data;

[1545] means for preprocessing the collected behavioral and emotional data;

[1546] means for analyzing the preprocessed data with an artificial intelligence model;

[1547] a means for generating insights based on the analysis results;

[1548] a means of displaying the generated insights;

[1549] A system including:

[1550] (Claim 2)

[1551] 10. The system of claim 1, wherein the system collects data including fan location information, dwell time, and sentiment data.

[1552] (Claim 3)

[1553] The system of claim 1, wherein the generated insights are visualized as graphs or charts and displayed on a terminal.

[1554] "Application example 2 when combining emotion engines"

[1555] (Claim 1)

[1556] a means for collecting fan behavioral and emotional data;

[1557] means for pre-processing the collected data;

[1558] means for analyzing the preprocessed data with an artificial intelligence model;

[1559] a means for generating insights based on the analysis results;

[1560] A means to display the generated insights and provide users with personalized recommended actions and marketing strategies;

[1561] A system including:

[1562] (Claim 2)

[1563] 2. The system according to claim 1, wherein location information, behavioral data, and emotional data from facial expression analysis of fans are collected.

[1564] (Claim 3)

[1565] 10. The system of claim 1, wherein the generated insights are visualized as graphs and charts and personalized shopping recommendations are displayed to the fan within the application. [Explanation of symbols]

[1566] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting fan behavior data; means for pre-processing the collected data; means for analyzing the preprocessed data with an artificial intelligence model; a means for generating insights based on the analysis results; a means of displaying the generated insights; A system including:

2. 10. The system of claim 1, wherein the system collects data including fan location and behavior data.

3. The system of claim 1 , wherein the generated insights are visualized as graphs or charts.

Images