system

Abstract

We provide the system. [Solution] Means for obtaining information on participants' past behavior, A means for analyzing participants' interests based on the aforementioned behavioral information, A means for selecting an activity that matches the aforementioned interest from a database containing information on multiple activities, A means for automatically generating an optimized activity schedule based on the selected activities, The means for displaying the generated activity schedule, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] At large-scale events, since many activities and shows are held simultaneously, participants often have trouble deciding which activity to choose. Also, it may take a great deal of time and effort to create an optimal schedule based on one's interests and preferences. Due to such problems, participants may not be able to fully enjoy the charm of the event.

Means for Solving the Problems

[0005] This invention provides a system that acquires information on participants' past behavior and analyzes their interests based on that information. This system can select activities that match the participant's interests from multiple activity records stored in a database and automatically generate an optimized activity schedule based on these selections. Furthermore, a function to display the generated activity schedule allows participants to easily check their personalized schedule. Through these means, participants can efficiently select events that suit their preferences and have a fulfilling experience.

[0006] "Participant's past behavior information" refers to information about past events and related activities that each individual participant has attended.

[0007] "Means of analyzing interests" refer to methods and devices for processing and analyzing past behavioral information in order to understand what kinds of events and activities participants are interested in.

[0008] A "database for storing activity information" is a database system used to store and manage detailed information about multiple events and shows.

[0009] "Means for selecting activities that match interests" refers to methods and devices for selecting events and activities that are most relevant to participants' interests based on the analysis results.

[0010] "Means for automatically generating optimized activity schedules" refers to methods or devices for creating schedules based on selected events and activities, enabling participants to participate efficiently and effectively.

[0011] "Means for displaying generated activity schedules" refers to methods or devices for presenting automatically generated schedules to participants in a visually easy-to-understand format. [Brief explanation of the drawing]

[0012] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0018] In the following embodiments, a numbered communication I / F (Interface) is an interface including a communication processor and an antenna. 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), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] The system of this invention is designed to optimize the participant experience at large-scale events. Based on participant behavioral data and profile information, it generates individually customized activity schedules. Specifically, it analyzes participants' interests and suggests highly relevant events and activities based on those interests.

[0034] Program Description

[0035] Data entry and analysis

[0036] Users register information about their areas of interest and past events they have attended. This includes direct input and linking social media accounts.

[0037] The server analyzes the received data to identify event categories that the user is interested in. This analysis uses machine learning algorithms to correlate the user's past behavior data with their interests.

[0038] Retrieving event data

[0039] The server collects detailed event information from external sources and event organizers and stores it in a database. This information includes the type of event, location, time, and participation requirements.

[0040] Schedule generation and presentation

[0041] The server extracts event information from the database based on the user's interests and generates a schedule that considers the optimal combination. This generation takes into account factors such as the time and geographical location of events, and the time required for travel.

[0042] The device displays the generated schedule to the user. The event name, start time, location, and interest level are clearly displayed for the user to easily understand.

[0043] Specific example

[0044] For example, if a participant is attending a technical conference, and has previously attended AI-related sessions, this system analyzes the user's past attendance history and profile to automatically select the latest AI sessions being held at the current event and incorporate them into the schedule. It also takes into account breaks to ensure efficient scheduling for attending relevant sessions.

[0045] Thus, this invention allows participants to efficiently enjoy events that align with their interests.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] Users enter profile information, including their interests, hobbies, and past event participation history. This includes direct input through apps and web portals.

[0049] Step 2:

[0050] The device prepares to securely transmit information entered by the user to the server. Encrypted communication is used to maintain data integrity and privacy.

[0051] Step 3:

[0052] The server stores the received user information in a database and begins initial analysis. Here, it builds data to model the user's past behavioral patterns.

[0053] Step 4:

[0054] The server uses machine learning algorithms to analyze user interests. Based on past event participation history and entered hobbies, it identifies event categories that are likely to interest the user.

[0055] Step 5:

[0056] The server retrieves event information in real time from external event management systems and social media APIs. This information is integrated into a database, maintaining real-time updates of activity information.

[0057] Step 6:

[0058] The server selects activities from the database that match the user's interests. This process includes checking event dates, geographical locations, and adjusting for overlapping events.

[0059] Step 7:

[0060] The server generates an optimal activity schedule based on the selected events. The schedule reflects time, location, and priority based on the relevance of the events.

[0061] Step 8:

[0062] The terminal displays the schedule sent from the server to the user. A graphical interface is used to present the information in a way that is easy for the user to understand visually.

[0063] Step 9:

[0064] Users can review the displayed schedule and make adjustments, such as deleting unnecessary events or adding new events that interest them.

[0065] Step 10:

[0066] The device will store the schedule as last confirmed by the user. It will also maintain the ability to provide alerts or notifications to the user before important events begin.

[0067] (Example 1)

[0068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] In traditional large-scale events, it was difficult for participants to create optimal schedules based on their own interests. Information on various events and activities was scattered, and effective suggestions tailored to individual interests were rare, resulting in generally lower participant satisfaction. In addition, there was a lack of systems that allowed for flexible changes and adjustments to schedules.

[0070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0071] In this invention, the server includes means for acquiring information on a participant's past behavior, means for analyzing the participant's interests using a generation algorithm based on the behavior information, and means for selecting activities that match the interests from an information storage device that stores multiple activity information, and generating an activity schedule considering the optimal combination. This makes it possible for participants to easily create and adjust an optimized schedule that matches their interests.

[0072] "Participant's past behavior information" refers to data about activities and events that users have participated in in the past, and is used to understand users' interests and behavioral tendencies.

[0073] A "generative algorithm" is an algorithm that analyzes input data, extracts regularities and patterns, and generates output that is tailored to a specific purpose.

[0074] "Activities that match the user's interests" refers to events and activities that are judged to have a high probability of satisfying the user's interests and concerns.

[0075] An "information storage device" is an electronic device or system for storing and managing various types of data, and plays a role in efficiently accumulating user data and event information.

[0076] "Generating an activity schedule" refers to the process of creating a schedule that includes the optimal combination of activities, taking into account the user's interests and the characteristics of the event.

[0077] A "display device" is a device or interface that allows users to visually confirm generated schedules and information.

[0078] This system provides users with a customized schedule based on participants' interests to optimize their experience at large-scale events.

[0079] The server collects past behavioral information and interest data provided by users and performs data analysis using machine learning algorithms (generative AI models). This analysis identifies patterns in the user's interests and selects suitable events and activities. The server extracts activity information optimized for these interests from a database stored in storage and generates the most effective schedule for participants. This schedule generation includes calculations that take into account the time allocation and geographical location of events, as well as the optimization of travel time.

[0080] The terminal serves to visually present the generated schedule to the user. Information such as event name, relevance, start time, and location are clearly displayed on the terminal in a way that is easy for the user to understand intuitively. Based on this information, the user can efficiently plan event experiences that align with their interests. For example, if a user has previously attended artificial intelligence-related sessions at technical conferences, the system can automatically select the latest AI sessions and incorporate them into the schedule.

[0081] An example of a prompt for a generative AI model is, "Based on the user's past participation history and interests, generate the optimal AI-related schedule for the next technical conference." This prompt is used as an instruction to the model and serves as a starting point for generating the optimal schedule based on the generated data.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server retrieves interest data and past behavior information from users. Users can provide this information by directly entering it or by linking their social media accounts. The entered data is securely stored by the server in its information storage device. Inputs include user profile data and past event participation history, and output is a record in an organized database.

[0085] Step 2:

[0086] The server begins analysis using a generative AI model with the collected user data. Specifically, it uses machine learning algorithms to analyze users' interests and past event participation trends. This analysis process utilizes data pattern recognition and clustering techniques to identify event categories that users are likely to be interested in. The input is organized user data, and the output is a list of identified interest categories.

[0087] Step 3:

[0088] The server retrieves the latest event information from external sources and event organizers. This information includes event type, location, date and time, and participation requirements. This information is obtained via APIs and stored in a database. The input is event data from external APIs, and the output is a database containing the latest event information.

[0089] Step 4:

[0090] The server extracts event information from a database based on the user's interests and generates an optimal schedule. This generation process considers factors such as event time, geographical location, user interest level, and travel time. Using an optimization algorithm, it outputs the most suitable combination of events as a schedule. The input is the identified interest categories and event information, and the output is the optimized schedule.

[0091] Step 5:

[0092] The terminal displays an optimized schedule sent from the server to the user. The terminal visually displays the event name, time, location, and interest level in an easy-to-understand manner. Based on this information, the user can efficiently plan their event participation. The input is optimized schedule data, and the output is event information displayed in a user-readable format.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] In physical stores, visitors often find it difficult to efficiently select suitable items from a large selection of products, and may not be able to move around the store effectively. Furthermore, information on new products and sales may not be provided insufficient to effectively utilize this information. As a result, there is a challenge in that the visitor's purchasing experience is not fully optimized.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes means for acquiring information on a visitor's past purchase history, means for analyzing the visitor's interests based on the purchase history information, and means for selecting products that match the visitor's interests from a database storing information on multiple products. This makes it possible to provide visitors with an optimal purchasing guide and deliver an efficient and interest-based purchasing experience in physical stores.

[0098] "Participant's past behavioral information" refers to data that shows the history of activities and events that participants have taken part in in the past.

[0099] "Methods for analyzing interests" refer to methods and techniques for identifying areas of interest or products based on the past behavior and history of participants or visitors.

[0100] "Activity information" refers to detailed data about events and activities, including information such as time, location, and type.

[0101] An "optimized activity schedule" refers to a plan of activities that is structured in a way that best suits the participants' interests and schedules.

[0102] "Information on the past purchase history of store visitors" refers to data on products that customers have previously purchased when visiting a physical store.

[0103] "Methods for analyzing interests" refer to techniques and methods for predicting products and services that a visitor might be interested in, using their past behavioral history.

[0104] "Product information" refers to data that shows the details of a product, including the product name, price, stock status, and sales information.

[0105] A "guide to optimize the shopping experience" refers to suggestions and advice provided to help visitors make purchases in stores more efficient and satisfying.

[0106] In an embodiment for carrying out this invention, the system mainly consists of a server and a user terminal.

[0107] The server first retrieves the visitor's past purchase history information from the database. This data retrieval can be done in conjunction with a customer management system. Next, the server analyzes the visitor's interests based on the retrieved purchase history information. For interest analysis, machine learning software (e.g., TENSORFLOW®) is used to execute data analysis algorithms.

[0108] Furthermore, the server retrieves product information from external sources and product management systems and compares it with the information stored in the database. During this process, it utilizes the latest trend information to select products that match the visitor's interests.

[0109] The process of generating an optimized shopping guide utilizes location services to calculate efficient routes within the store. It also automatically generates a list of recommended products and information on special offers based on selected product information.

[0110] The terminal visually displays the purchasing guide sent from the server. Smartphone and smart glasses displays provide a visually intuitive interface, helping visitors navigate the store effectively. Furthermore, push notifications are used to deliver information on new products and special offers in real time.

[0111] For example, if a visitor has previously purchased many health foods, this system can analyze their purchase history and immediately suggest newly arrived health-related products and sales information. As a result, visitors can efficiently purchase the products they are interested in without missing out on any.

[0112] An example of a prompt message is: "You are interested in organic foods. How would you like to be supported in receiving product recommendations and special offers during your next visit to our store?"

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server retrieves the visitor's past purchase history information from the customer database. It receives the visitor's ID as input and extracts the relevant purchase history data. The retrieved purchase history data is returned as output. This history information is used for subsequent analysis and is accessed using the database management system.

[0116] Step 2:

[0117] The server inputs purchase history data into a machine learning algorithm to analyze visitors' interests. Specifically, it identifies product categories preferred by visitors by analyzing past purchase patterns. The output is profile information indicating visitors' interests. Generative AI models such as TensorFlow are used to associate purchase behavior with interests.

[0118] Step 3:

[0119] The server retrieves detailed product information from external sources and product management systems. It receives product IDs and category information via APIs as input, and retrieves attribute data for new products. As output, it provides the latest trending product information. This allows users to select highly relevant products by comparing them with profile information obtained through interest analysis.

[0120] Step 4:

[0121] The server generates an optimized shopping guide based on the visitor's interests. Using interest profile information and product information as input, it creates optimal purchase suggestions using a combined algorithm. As output, it generates a shopping route that allows the visitor to move efficiently within the store and a list of suggested products.

[0122] Step 5:

[0123] The terminal receives a purchase guide sent from the server and displays it on its screen. It receives purchase guide data as input and uses a visualization engine to present it clearly on the user interface. As output, it provides navigation and product information to enhance the visitor's in-store shopping experience.

[0124] Step 6:

[0125] Users navigate the store following the instructions on their device and view recommended products and special offers. By referring to the purchasing guide, users can efficiently find products of interest. Suggestions, such as prompt messages, are expected to increase visitors' purchasing intent.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] The system of the present invention helps participants of large-scale events to participate in activities of interest to them in the most effective and efficient way. In addition to conventional participant information acquisition and schedule generation functions, the present invention further enhances the participant experience by incorporating an emotion engine that recognizes the user's emotions.

[0128] Program Description

[0129] Data collection and emotion recognition

[0130] Users input their profile information into the system and also provide emotional indicators such as facial expression data and voice data. This data is then analyzed by an emotion engine.

[0131] The server runs an emotion engine that analyzes user emotions in real time. This analysis is then used to inform participants' interests and satisfaction with event selection.

[0132] Activity selection and schedule generation

[0133] The server uses the results of the emotion engine to analyze the user's interests in detail. More specifically, it identifies the emotional state in which a user enjoys a particular activity and selects that activity accordingly.

[0134] Furthermore, by combining this with activity information obtained from the database, the system prioritizes and incorporates into the schedule activities that best suit the user's current emotional state.

[0135] Schedule display and adjustment

[0136] The device displays a schedule generated by the server to the user. The schedule displays recommendation levels based on emotional state, making it easier for the user to make choices that align with their own emotions.

[0137] Users can review the generated schedule and adjust or edit it according to their interests and plans.

[0138] Specific example

[0139] For example, if the emotion engine detects that a user is experiencing stress during an event, the system will prioritize suggesting relaxation workshops or activities that provide comfort. Conversely, when the user is feeling happy, it will recommend more social activities or challenging content.

[0140] In this way, by taking user emotions into consideration, the present invention can provide participants with a more personalized and engaging experience.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] Users enter their profile information and past event participation history into an application or web portal. Furthermore, they utilize devices that record emotional data such as facial expressions and voice.

[0144] Step 2:

[0145] The device collects profile information and sentiment indicator data provided by the user and transmits it to the server using a secure communication channel.

[0146] Step 3:

[0147] The server analyzes the received data. It activates the emotion engine, which analyzes facial expressions and voice data to determine the user's current emotional state in real time.

[0148] Step 4:

[0149] The server analyzes the user's interests and satisfaction levels based on their emotional state and past behavioral data. This allows it to identify activity categories recommended for specific emotional states.

[0150] Step 5:

[0151] The server combines event and activity information retrieved from the database with analysis results to select the activity best suited to the emotional state. It sets priorities based on emotions and automatically generates an optimal schedule.

[0152] Step 6:

[0153] The device displays the generated schedule to the user. The schedule includes the sentiment relevance and recommendation reasons for each activity, and is presented in a format that allows the user to easily make selections.

[0154] Step 7:

[0155] Users review the presented schedule and make adjustments as needed to suit their own schedules and interests. They use emotional fit scores as a reference to make adjustments for a better experience.

[0156] Step 8:

[0157] The device will save the final confirmed schedule and provide notifications before important events begin. Furthermore, the possibility of updating the schedule in real time in response to changes in emotional state is also being considered.

[0158] (Example 2)

[0159] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0160] In large-scale events, it can be difficult for participants to choose activities that best suit their emotional state and interests, sometimes resulting in unsatisfactory experiences. To solve this problem, a system is needed that accurately identifies participants' emotions and interests and suggests the most suitable activities based on that information.

[0161] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0162] In this invention, the server includes means for collecting basic information about participants, means for analyzing facial expressions and voice data to identify the participants' emotions, and means for selecting activities that match their interests from a data storage that stores multiple activity data. This enables the suggestion of optimal activities according to the participants' emotional state and the automatic generation of activity schedules.

[0163] A "participant" refers to an individual who participates in an event or activity, and who receives system suggestions based on their personal information and emotional state.

[0164] "Basic information" refers to information provided by participants, such as their name, age, and areas of interest, and is data that the system uses as a participant profile.

[0165] "Facial expression and voice data" refers to data, including facial movements and vocal characteristics, collected to identify the emotions of participants.

[0166] "Means of identifying emotions" refers to the process of identifying a participant's current emotional state by analyzing their facial expressions and voice data.

[0167] "Methods for analyzing interests" refer to methods of analyzing which activities align with participants' interests, based on their emotional state and basic information.

[0168] "Activity data" refers to information related to various activities within an event, including the content, time, and location of the activities.

[0169] "Data storage" refers to memory devices and systems used to store activity data, and plays a role in providing activity information when needed.

[0170] "Methods for selecting activities" refer to the process of choosing the most appropriate activity from among several options, taking into account the participants' interests and emotional information.

[0171] "Methods for automatically generating activity schedules" refer to automated methods that combine selected activities to create the most suitable schedule for participants.

[0172] "Means of visual display" refers to methods of displaying the generated activity schedule on a screen or in printed materials in a way that is easy for participants to understand.

[0173] This invention is a system that optimizes the participant experience at events. Based on the participants' emotional state and interests, this system selects appropriate activities and proposes them as a schedule.

[0174] During system operation, users enter basic profile information via their device. Facial expressions and voice data are also collected using a webcam and microphone. This collected data is sent to a server for emotion recognition.

[0175] The server is equipped with an emotion engine for analyzing facial expressions and voice data. This emotion engine utilizes open-source libraries commonly used in image processing. It also employs a specific algorithm for voice analysis to assess participants' emotional states in real time. Based on the analysis results, it identifies activities that match the participants' interests.

[0176] Based on the analysis results, the server retrieves activity information from its internal data storage and selects the activity most relevant to the participant's emotional state. This data storage contains detailed information for each activity, and the server automatically generates an appropriate schedule based on the selection results.

[0177] The generated schedule is displayed and visualized on the device. The schedule shows the priority of activities and the reasons for suggesting them, allowing users to adjust it according to their interests and schedules.

[0178] For example, if a user experiences stress during an event, the server detects this emotional state and suggests activities aimed at relaxation. This allows the user to choose an activity that suits them and have a more satisfying experience.

[0179] An example of a prompt is, "Please describe an effective method for suggesting activities in a system that combines emotion recognition and schedule generation." By sending this sentence to the generating AI model, further suggestions and improvements can be obtained.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The user uses a device to enter basic profile information for event participation. This information includes name, age, and areas of interest. The device sends this information to the server. The entered profile information is stored in a database and used as reference data for the next processing step.

[0183] Step 2:

[0184] The user provides facial expression data and voice data to the system via webcam and microphone. This data is captured in real time and sent to the server in its raw state. The server receives this data and performs facial expression analysis and voice analysis using an emotion engine. As a result of the analysis, the user's current emotional state (e.g., happy, sad, stressed) is obtained.

[0185] Step 3:

[0186] The server combines the profile information obtained in Step 1 with the emotional state data obtained in Step 2 to perform a detailed analysis of the user's interests. Specifically, it uses an internal algorithm to determine what activities are suitable for the emotional state. This analysis generates a list of candidate activities that can best satisfy the participant's interests.

[0187] Step 4:

[0188] The server retrieves activity information from the activity data storage that matches the previously generated list of candidates. Based on this, it automatically creates an activity schedule optimized for the user's emotional state and interests. This schedule is created taking into account the start time, duration, and content of the activities.

[0189] Step 5:

[0190] The device visually displays the activity schedule sent from the server to the user. The display includes the reasons and priorities for recommended activities. This allows the user to understand suggestions based on their emotional state.

[0191] Step 6:

[0192] Users can review the displayed schedule and make any necessary adjustments based on their interests and other appointments. These adjustments are made directly through the device and transmitted to the server in real time. The server can then review the updated schedule and make any further adjustments as needed.

[0193] (Application Example 2)

[0194] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0195] In large-scale events and shopping facilities, there is a challenge in that participants and customers have difficulty selecting activities and products that best suit their current emotional state. Furthermore, this makes it difficult to optimize the quality of the experience according to individual emotional states, resulting in limited improvements in satisfaction.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0197] In this invention, the server includes means for acquiring information on participants' past behavior, means for analyzing the user's emotional state, and means for selecting activities based on the analyzed emotional state and automatically generating an optimized activity schedule. This makes it possible for individual participants to be automatically presented with activities and products that are best suited to their own emotional state.

[0198] "Participant's past behavioral information" refers to information about participants' past activities and behavioral history at events or for the target audience.

[0199] "Means of analyzing participants' interests based on behavioral information" refers to the processes and methods for analyzing and identifying participants' interests and preferences from past behavioral data.

[0200] An "information recording medium" refers to a data storage device that stores multiple activity records and allows access to them as needed.

[0201] "Means of analyzing a user's emotional state" refers to technologies and methods for determining a user's emotional state by analyzing data such as their facial expressions and voice.

[0202] "Methods for automatically generating optimized activity schedules" refers to a process that automatically creates the most appropriate activity schedule for participants based on analyzed data.

[0203] "Trend information from external sources" refers to information about current trends and popular styles obtained from external sources.

[0204] "Re-recommendation based on changes in emotional state" refers to a process where, when a user's emotions change, the initial recommendation activity is re-evaluated and a new, optimal suggestion is made.

[0205] This invention is a system for recommending optimal activities and products based on users' emotional states at large-scale events and shopping facilities where users participate. The system has a configuration that broadly includes the following processes: data collection, emotion analysis, recommendation generation, and display.

[0206] The server retrieves and analyzes users' past behavioral information by analyzing data stored on an information storage medium, including their participation history and activity history. This past behavioral information is stored using a secure database management system.

[0207] Next, facial recognition software and voice analysis tools are used to analyze the user's emotional state. Specifically, data is acquired in real time via cameras and microphones built into smartphones or smart glasses and sent to a server. The server uses an emotion engine to analyze this data and identify the user's emotional state. Tools such as Amazon Rekognition and Google® Speech-to-Text can be used in this analysis process.

[0208] Based on the analyzed emotional state, the server selects the most suitable activities and products from the information storage medium. This generates a real-time activity schedule tailored to each individual user's emotional state. The generated activity schedule is immediately notified to the user's mobile device, allowing them to view details of the selected activities.

[0209] For example, if the analysis indicates that a user is feeling stressed, the server will recommend information about relaxation products or cafe areas. Conversely, when the user is in a cheerful mood, it can suggest positive activities such as information about new product sales.

[0210] An example of a prompt message is, "What products are recommended when a user is feeling anxious?" By providing recommendations based on emotional states in this way, users can have a more satisfying experience.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] Users enter their information into their mobile devices and send that data to the server. The input data includes past behavioral history and current location information. The server stores the received information on an information storage medium and uses it as basic data for behavioral analysis.

[0214] Step 2:

[0215] The device transmits facial images and audio data collected in real time from its built-in camera and microphone to a server. This data is used as input to analyze the user's emotional state. The server uses facial recognition and audio analysis tools to analyze this data and identify the user's emotional state.

[0216] Step 3:

[0217] The server uses the sentiment analysis results to select activities based on the user's current emotional state. It retrieves activity information most suitable for the identified emotion from the information storage medium and generates an optimized activity schedule based on this information. If the sentiment analysis utilizes a generative AI model, it may also consider prompt text to derive the optimal suggestion.

[0218] Step 4:

[0219] The server sends the generated activity schedule to the user's mobile device. The device notifies the user of this information and displays the activity details and recommendation level on the screen. The user can review this information and select the appropriate action.

[0220] Step 5:

[0221] Users participate in selected activities based on the displayed schedule. If necessary, users can edit their schedules and adjust them to suit their preferences and plans. This allows users to enjoy an experience that aligns with their individual emotional state.

[0222] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0223] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0224] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0225] [Second Embodiment]

[0226] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0227] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0228] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0229] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0230] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0231] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0232] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0233] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0234] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0235] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0236] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0237] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0238] The system of this invention is designed to optimize the participant experience at large-scale events. Based on participant behavioral data and profile information, it generates individually customized activity schedules. Specifically, it analyzes participants' interests and suggests highly relevant events and activities based on those interests.

[0239] Program Description

[0240] Data entry and analysis

[0241] Users register information about their areas of interest and past events they have attended. This includes direct input and linking social media accounts.

[0242] The server analyzes the received data to identify event categories that the user is interested in. This analysis uses machine learning algorithms to correlate the user's past behavior data with their interests.

[0243] Retrieving event data

[0244] The server collects detailed event information from external sources and event organizers and stores it in a database. This information includes the type of event, location, time, and participation requirements.

[0245] Schedule generation and presentation

[0246] The server extracts event information from the database based on the user's interests and generates a schedule that considers the optimal combination. This generation takes into account factors such as the time and geographical location of events, and the time required for travel.

[0247] The device displays the generated schedule to the user. The event name, start time, location, and interest level are clearly displayed for the user to easily understand.

[0248] Specific example

[0249] For example, if a participant is attending a technical conference, and has previously attended AI-related sessions, this system analyzes the user's past attendance history and profile to automatically select the latest AI sessions being held at the current event and incorporate them into the schedule. It also takes into account breaks to ensure efficient scheduling for attending relevant sessions.

[0250] Thus, this invention allows participants to efficiently enjoy events that align with their interests.

[0251] The following describes the processing flow.

[0252] Step 1:

[0253] Users enter profile information, including their interests, hobbies, and past event participation history. This includes direct input through apps and web portals.

[0254] Step 2:

[0255] The device prepares to securely transmit information entered by the user to the server. Encrypted communication is used to maintain data integrity and privacy.

[0256] Step 3:

[0257] The server stores the received user information in a database and begins initial analysis. Here, it builds data to model the user's past behavioral patterns.

[0258] Step 4:

[0259] The server uses machine learning algorithms to analyze user interests. Based on past event participation history and entered hobbies, it identifies event categories that are likely to interest the user.

[0260] Step 5:

[0261] The server retrieves event information in real time from external event management systems and social media APIs. This information is integrated into a database, maintaining real-time updates of activity information.

[0262] Step 6:

[0263] The server selects activities from the database that match the user's interests. This process includes checking event dates, geographical locations, and adjusting for overlapping events.

[0264] Step 7:

[0265] The server generates an optimal activity schedule based on the selected events. The schedule reflects time, location, and priority based on the relevance of the events.

[0266] Step 8:

[0267] The terminal displays the schedule sent from the server to the user. A graphical interface is used to present the information in a way that is easy for the user to understand visually.

[0268] Step 9:

[0269] Users can review the displayed schedule and make adjustments, such as deleting unnecessary events or adding new events that interest them.

[0270] Step 10:

[0271] The device will store the schedule as last confirmed by the user. It will also maintain the ability to provide alerts or notifications to the user before important events begin.

[0272] (Example 1)

[0273] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0274] In traditional large-scale events, it was difficult for participants to create optimal schedules based on their own interests. Information on various events and activities was scattered, and effective suggestions tailored to individual interests were rare, resulting in generally lower participant satisfaction. In addition, there was a lack of systems that allowed for flexible changes and adjustments to schedules.

[0275] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0276] In this invention, the server includes means for acquiring information on a participant's past behavior, means for analyzing the participant's interests using a generation algorithm based on the behavior information, and means for selecting activities that match the interests from an information storage device that stores multiple activity information, and generating an activity schedule considering the optimal combination. This makes it possible for participants to easily create and adjust an optimized schedule that matches their interests.

[0277] "Participant's past behavior information" refers to data about activities and events that users have participated in in the past, and is used to understand users' interests and behavioral tendencies.

[0278] A "generative algorithm" is an algorithm that analyzes input data, extracts regularities and patterns, and generates output that is tailored to a specific purpose.

[0279] "Activities that match the user's interests" refers to events and activities that are judged to have a high probability of satisfying the user's interests and concerns.

[0280] An "information storage device" is an electronic device or system for storing and managing various types of data, and plays a role in efficiently accumulating user data and event information.

[0281] "Generating an activity schedule" refers to the process of creating an optimal combination of activities as a schedule considering the user's interests and event characteristics.

[0282] "Display device" refers to a device or interface that enables the user to visually confirm the generated schedule and information.

[0283] This system provides a customized schedule based on the interests of the participants to optimize the user's experience in large-scale events.

[0284] The server collects the past behavior information and interest data provided by the user and performs data analysis using a machine learning algorithm (generation AI model). Through this analysis, the user's interest pattern is identified, and matching events and activities are selected. The server extracts the activity information optimized for these interests from the database stored in the storage device and generates the most effective schedule for the participants. This schedule generation includes computational processing considering the time allocation, geographical location of the events, and optimization of travel time.

[0285] The terminal plays a role in visually presenting the generated schedule to the user. On the terminal, information such as the event name, relevance, start time, location, etc. is clearly shown so that the user can intuitively understand it. Based on this information, the user can efficiently plan an event experience along with their interests. For example, if the user has participated in AI-related sessions at a technology conference in the past, the system can automatically pick up the latest AI sessions and incorporate them into the schedule.

[0286] Examples of prompt texts for the generative AI model include: "Based on the user's past participation history and interests, generate the optimal artificial intelligence-related schedule for the next technical conference." This prompt text is used as an instruction to the model and serves as a starting point for generating the optimal schedule based on the generated data.

[0287] The flow of the specific process in Example 1 will be described using FIG. 11.

[0288] Step 1:

[0289] The server acquires interest data and past behavior information from the user. The user can directly input this information or provide it by linking social media accounts. The input data is securely stored in the information storage device by the server. The input includes the user's profile data and past event participation history, and the output is the records of the organized database.

[0290] Step 2:

[0291] The server starts the analysis by the generative AI model using the collected user data. Specifically, it analyzes the user's interests and past event participation trends using machine learning algorithms. In this analysis process, data pattern recognition and clustering techniques are utilized to identify the event categories that the user is likely to be interested in. The input is the organized user data, and the output is a list of the identified interest categories.

[0292] Step 3:

[0293] The server acquires the latest event information from external information sources and event organizers. The information obtained includes the type of event, venue, date and time, participation conditions, etc. These information are acquired via APIs and accumulated in the database. The input is the event data from external APIs, and the output is the database with the latest event information registered.

[0294] Step 4:

[0295] The server extracts event information from a database based on the user's interests and generates an optimal schedule. This generation process considers factors such as event time, geographical location, user interest level, and travel time. Using an optimization algorithm, it outputs the most suitable combination of events as a schedule. The input is the identified interest categories and event information, and the output is the optimized schedule.

[0296] Step 5:

[0297] The terminal displays an optimized schedule sent from the server to the user. The terminal visually displays the event name, time, location, and interest level in an easy-to-understand manner. Based on this information, the user can efficiently plan their event participation. The input is optimized schedule data, and the output is event information displayed in a user-readable format.

[0298] (Application Example 1)

[0299] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0300] In physical stores, visitors often find it difficult to efficiently select suitable items from a large selection of products, and may not be able to move around the store effectively. Furthermore, information on new products and sales may not be provided insufficient to effectively utilize this information. As a result, there is a challenge in that the visitor's purchasing experience is not fully optimized.

[0301] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0302] In this invention, the server includes means for obtaining the past purchase history information of visitors, means for analyzing the interests of visitors based on the purchase history information, and means for selecting products that match the interests from a database storing a plurality of product information. Thereby, it becomes possible to provide an optimal purchase guide to visitors and to provide the purchase experience in a physical store efficiently and in line with their interests.

[0303] The "past behavior information of participants" refers to data indicating the history of what activities and events the participants have participated in the past.

[0304] The "means for analyzing interests" refers to methods and technologies for identifying fields and products of interest based on the past behaviors and histories of participants or visitors.

[0305] The "activity information" refers to detailed data regarding events and activities, including information such as time, location, type, etc.

[0306] The "optimized activity plan" refers to a plan of activities assembled in a form most suitable for the interests and schedule of the participants.

[0307] The "past purchase history information of visitors to the store" refers to data regarding the products purchased by customers who have visited the physical store in the past.

[0308] The "means for analyzing interests" refers to technologies and methods for inferring products and services that a visitor is interested in using the visitor's past behavior history.

[0309] The "product information" refers to data indicating the details of the product, including the product name, price, inventory status, sale information, etc.

[0310] The "guide for optimizing the purchase experience" refers to proposals and advice provided to make the visitor's purchase in the store more efficient and satisfactory.

[0311] In an embodiment for carrying out this invention, the system mainly consists of a server and a user terminal.

[0312] The server first retrieves the visitor's past purchase history information from the database. This data retrieval can be done in conjunction with a customer management system. Next, the server analyzes the visitor's interests based on the retrieved purchase history information. Machine learning software (e.g., TensorFlow) is used to execute data analysis algorithms for interest analysis.

[0313] Furthermore, the server retrieves product information from external sources and product management systems and compares it with the information stored in the database. During this process, it utilizes the latest trend information to select products that match the visitor's interests.

[0314] The process of generating an optimized shopping guide utilizes location services to calculate efficient routes within the store. It also automatically generates a list of recommended products and information on special offers based on selected product information.

[0315] The terminal visually displays the purchasing guide sent from the server. Smartphone and smart glasses displays provide a visually intuitive interface, helping visitors navigate the store effectively. Furthermore, push notifications are used to deliver information on new products and special offers in real time.

[0316] For example, if a visitor has previously purchased many health foods, this system can analyze their purchase history and immediately suggest newly arrived health-related products and sales information. As a result, visitors can efficiently purchase the products they are interested in without missing out on any.

[0317] An example of a prompt message is: "You are interested in organic foods. How would you like to be supported in receiving product recommendations and special offers during your next visit to our store?"

[0318] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0319] Step 1:

[0320] The server retrieves the visitor's past purchase history information from the customer database. It receives the visitor's ID as input and extracts the relevant purchase history data. The retrieved purchase history data is returned as output. This history information is used for subsequent analysis and is accessed using the database management system.

[0321] Step 2:

[0322] The server inputs purchase history data into a machine learning algorithm to analyze visitors' interests. Specifically, it identifies product categories preferred by visitors by analyzing past purchase patterns. The output is profile information indicating visitors' interests. Generative AI models such as TensorFlow are used to associate purchase behavior with interests.

[0323] Step 3:

[0324] The server retrieves detailed product information from external sources and product management systems. It receives product IDs and category information via APIs as input, and retrieves attribute data for new products. As output, it provides the latest trending product information. This allows users to select highly relevant products by comparing them with profile information obtained through interest analysis.

[0325] Step 4:

[0326] The server generates an optimized shopping guide based on the visitor's interests. Using interest profile information and product information as input, it creates optimal purchase suggestions using a combined algorithm. As output, it generates a shopping route that allows the visitor to move efficiently within the store and a list of suggested products.

[0327] Step 5:

[0328] The terminal receives a purchase guide sent from the server and displays it on its screen. It receives purchase guide data as input and uses a visualization engine to present it clearly on the user interface. As output, it provides navigation and product information to enhance the visitor's in-store shopping experience.

[0329] Step 6:

[0330] Users navigate the store following the instructions on their device and view recommended products and special offers. By referring to the purchasing guide, users can efficiently find products of interest. Suggestions, such as prompt messages, are expected to increase visitors' purchasing intent.

[0331] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0332] The system of the present invention helps participants of large-scale events to participate in activities of interest to them in the most effective and efficient way. In addition to conventional participant information acquisition and schedule generation functions, the present invention further enhances the participant experience by incorporating an emotion engine that recognizes the user's emotions.

[0333] Program Description

[0334] Data collection and emotion recognition

[0335] Users input their profile information into the system and also provide emotional indicators such as facial expression data and voice data. This data is then analyzed by an emotion engine.

[0336] The server runs an emotion engine that analyzes user emotions in real time. This analysis is then used to inform participants' interests and satisfaction with event selection.

[0337] Activity selection and schedule generation

[0338] The server uses the results of the emotion engine to analyze the user's interests in detail. More specifically, it identifies the emotional state in which a user enjoys a particular activity and selects that activity accordingly.

[0339] Furthermore, by combining this with activity information obtained from the database, the system prioritizes and incorporates into the schedule activities that best suit the user's current emotional state.

[0340] Schedule display and adjustment

[0341] The device displays a schedule generated by the server to the user. The schedule displays recommendation levels based on emotional state, making it easier for the user to make choices that align with their own emotions.

[0342] Users can review the generated schedule and adjust or edit it according to their interests and plans.

[0343] Specific example

[0344] For example, if the emotion engine detects that a user is experiencing stress during an event, the system will prioritize suggesting relaxation workshops or activities that provide comfort. Conversely, when the user is feeling happy, it will recommend more social activities or challenging content.

[0345] In this way, by taking user emotions into consideration, the present invention can provide participants with a more personalized and engaging experience.

[0346] The following describes the processing flow.

[0347] Step 1:

[0348] Users enter their profile information and past event participation history into an application or web portal. Furthermore, they utilize devices that record emotional data such as facial expressions and voice.

[0349] Step 2:

[0350] The device collects profile information and sentiment indicator data provided by the user and transmits it to the server using a secure communication channel.

[0351] Step 3:

[0352] The server analyzes the received data. It activates the emotion engine, which analyzes facial expressions and voice data to determine the user's current emotional state in real time.

[0353] Step 4:

[0354] The server analyzes the user's interests and satisfaction levels based on their emotional state and past behavioral data. This allows it to identify activity categories recommended for specific emotional states.

[0355] Step 5:

[0356] The server combines event and activity information retrieved from the database with analysis results to select the activity best suited to the emotional state. It sets priorities based on emotions and automatically generates an optimal schedule.

[0357] Step 6:

[0358] The device displays the generated schedule to the user. The schedule includes the sentiment relevance and recommendation reasons for each activity, and is presented in a format that allows the user to easily make selections.

[0359] Step 7:

[0360] Users review the presented schedule and make adjustments as needed to suit their own schedules and interests. They use emotional fit scores as a reference to make adjustments for a better experience.

[0361] Step 8:

[0362] The device will save the final confirmed schedule and provide notifications before important events begin. Furthermore, the possibility of updating the schedule in real time in response to changes in emotional state is also being considered.

[0363] (Example 2)

[0364] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0365] In large-scale events, it can be difficult for participants to choose activities that best suit their emotional state and interests, sometimes resulting in unsatisfactory experiences. To solve this problem, a system is needed that accurately identifies participants' emotions and interests and suggests the most suitable activities based on that information.

[0366] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0367] In this invention, the server includes means for collecting basic information about participants, means for analyzing facial expressions and voice data to identify the participants' emotions, and means for selecting activities that match their interests from a data storage that stores multiple activity data. This enables the suggestion of optimal activities according to the participants' emotional state and the automatic generation of activity schedules.

[0368] A "participant" refers to an individual who participates in an event or activity, and who receives system suggestions based on their personal information and emotional state.

[0369] "Basic information" refers to information provided by participants, such as their name, age, and areas of interest, and is data that the system uses as a participant profile.

[0370] "Facial expression and voice data" refers to data, including facial movements and vocal characteristics, collected to identify the emotions of participants.

[0371] "Means of identifying emotions" refers to the process of identifying a participant's current emotional state by analyzing their facial expressions and voice data.

[0372] "Methods for analyzing interests" refer to methods of analyzing which activities align with participants' interests, based on their emotional state and basic information.

[0373] "Activity data" refers to information related to various activities within an event, including the content, time, and location of the activities.

[0374] "Data storage" refers to memory devices and systems used to store activity data, and plays a role in providing activity information when needed.

[0375] "Methods for selecting activities" refer to the process of choosing the most appropriate activity from among several options, taking into account the participants' interests and emotional information.

[0376] "Methods for automatically generating activity schedules" refer to automated methods that combine selected activities to create the most suitable schedule for participants.

[0377] "Means of visual display" refers to methods of displaying the generated activity schedule on a screen or in printed materials in a way that is easy for participants to understand.

[0378] This invention is a system that optimizes the participant experience at events. Based on the participants' emotional state and interests, this system selects appropriate activities and proposes them as a schedule.

[0379] During system operation, users enter basic profile information via their device. Facial expressions and voice data are also collected using a webcam and microphone. This collected data is sent to a server for emotion recognition.

[0380] The server is equipped with an emotion engine for analyzing facial expressions and voice data. This emotion engine utilizes open-source libraries commonly used in image processing. It also employs a specific algorithm for voice analysis to assess participants' emotional states in real time. Based on the analysis results, it identifies activities that match the participants' interests.

[0381] Based on the analysis results, the server retrieves activity information from its internal data storage and selects the activity most relevant to the participant's emotional state. This data storage contains detailed information for each activity, and the server automatically generates an appropriate schedule based on the selection results.

[0382] The generated schedule is displayed and visualized on the device. The schedule shows the priority of activities and the reasons for suggesting them, allowing users to adjust it according to their interests and schedules.

[0383] For example, if a user experiences stress during an event, the server detects this emotional state and suggests activities aimed at relaxation. This allows the user to choose an activity that suits them and have a more satisfying experience.

[0384] An example of a prompt is, "Please describe an effective method for suggesting activities in a system that combines emotion recognition and schedule generation." By sending this sentence to the generating AI model, further suggestions and improvements can be obtained.

[0385] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0386] Step 1:

[0387] The user uses a device to enter basic profile information for event participation. This information includes name, age, and areas of interest. The device sends this information to the server. The entered profile information is stored in a database and used as reference data for the next processing step.

[0388] Step 2:

[0389] The user provides facial expression data and voice data to the system via webcam and microphone. This data is captured in real time and sent to the server in its raw state. The server receives this data and performs facial expression analysis and voice analysis using an emotion engine. As a result of the analysis, the user's current emotional state (e.g., happy, sad, stressed) is obtained.

[0390] Step 3:

[0391] The server combines the profile information obtained in Step 1 with the emotional state data obtained in Step 2 to perform a detailed analysis of the user's interests. Specifically, it uses an internal algorithm to determine what activities are suitable for the emotional state. This analysis generates a list of candidate activities that can best satisfy the participant's interests.

[0392] Step 4:

[0393] The server retrieves activity information from the activity data storage that matches the previously generated list of candidates. Based on this, it automatically creates an activity schedule optimized for the user's emotional state and interests. This schedule is created taking into account the start time, duration, and content of the activities.

[0394] Step 5:

[0395] The device visually displays the activity schedule sent from the server to the user. The display includes the reasons and priorities for recommended activities. This allows the user to understand suggestions based on their emotional state.

[0396] Step 6:

[0397] Users can review the displayed schedule and make any necessary adjustments based on their interests and other appointments. These adjustments are made directly through the device and transmitted to the server in real time. The server can then review the updated schedule and make any further adjustments as needed.

[0398] (Application Example 2)

[0399] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0400] In large-scale events and shopping facilities, there is a challenge in that participants and customers have difficulty selecting activities and products that best suit their current emotional state. Furthermore, this makes it difficult to optimize the quality of the experience according to individual emotional states, resulting in limited improvements in satisfaction.

[0401] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0402] In this invention, the server includes means for acquiring information on participants' past behavior, means for analyzing the user's emotional state, and means for selecting activities based on the analyzed emotional state and automatically generating an optimized activity schedule. This makes it possible for individual participants to be automatically presented with activities and products that are best suited to their own emotional state.

[0403] "Participant's past behavioral information" refers to information about participants' past activities and behavioral history at events or for the target audience.

[0404] "Means of analyzing participants' interests based on behavioral information" refers to the processes and methods for analyzing and identifying participants' interests and preferences from past behavioral data.

[0405] An "information recording medium" refers to a data storage device that stores multiple activity records and allows access to them as needed.

[0406] "Means of analyzing a user's emotional state" refers to technologies and methods for determining a user's emotional state by analyzing data such as their facial expressions and voice.

[0407] "Methods for automatically generating optimized activity schedules" refers to a process that automatically creates the most appropriate activity schedule for participants based on analyzed data.

[0408] "Trend information from external sources" refers to information about current trends and popular styles obtained from external sources.

[0409] "Re-recommendation based on changes in emotional state" refers to a process where, when a user's emotions change, the initial recommendation activity is re-evaluated and a new, optimal suggestion is made.

[0410] This invention is a system for recommending optimal activities and products based on users' emotional states at large-scale events and shopping facilities where users participate. The system has a configuration that broadly includes the following processes: data collection, emotion analysis, recommendation generation, and display.

[0411] The server retrieves and analyzes users' past behavioral information by analyzing data stored on an information storage medium, including their participation history and activity history. This past behavioral information is stored using a secure database management system.

[0412] Next, facial recognition software and voice analysis tools are used to analyze the user's emotional state. Specifically, data is acquired in real time via cameras and microphones built into smartphones or smart glasses and sent to a server. The server uses an emotion engine to analyze this data and identify the user's emotional state. Tools such as Amazon Rekognition and Google Speech-to-Text can be used in this analysis process.

[0413] Based on the analyzed emotional state, the server selects the most suitable activities and products from the information storage medium. This generates a real-time activity schedule tailored to each individual user's emotional state. The generated activity schedule is immediately notified to the user's mobile device, allowing them to view details of the selected activities.

[0414] For example, if the analysis indicates that a user is feeling stressed, the server will recommend information about relaxation products or cafe areas. Conversely, when the user is in a cheerful mood, it can suggest positive activities such as information about new product sales.

[0415] An example of a prompt message is, "What products are recommended when a user is feeling anxious?" By providing recommendations based on emotional states in this way, users can have a more satisfying experience.

[0416] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0417] Step 1:

[0418] Users enter their information into their mobile devices and send that data to the server. The input data includes past behavioral history and current location information. The server stores the received information on an information storage medium and uses it as basic data for behavioral analysis.

[0419] Step 2:

[0420] The device transmits facial images and audio data collected in real time from its built-in camera and microphone to a server. This data is used as input to analyze the user's emotional state. The server uses facial recognition and audio analysis tools to analyze this data and identify the user's emotional state.

[0421] Step 3:

[0422] The server uses the sentiment analysis results to select activities based on the user's current emotional state. It retrieves activity information most suitable for the identified emotion from the information storage medium and generates an optimized activity schedule based on this information. If the sentiment analysis utilizes a generative AI model, it may also consider prompt text to derive the optimal suggestion.

[0423] Step 4:

[0424] The server sends the generated activity schedule to the user's mobile device. The device notifies the user of this information and displays the activity details and recommendation level on the screen. The user can review this information and select the appropriate action.

[0425] Step 5:

[0426] Users participate in selected activities based on the displayed schedule. If necessary, users can edit their schedules and adjust them to suit their preferences and plans. This allows users to enjoy an experience that aligns with their individual emotional state.

[0427] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0428] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0429] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0430] [Third Embodiment]

[0431] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0432] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0433] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0434] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0435] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0436] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0437] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0438] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0439] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0440] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0441] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0442] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0443] The system of this invention is designed to optimize the participant experience at large-scale events. Based on participant behavioral data and profile information, it generates individually customized activity schedules. Specifically, it analyzes participants' interests and suggests highly relevant events and activities based on those interests.

[0444] Program Description

[0445] Data entry and analysis

[0446] Users register information about their areas of interest and past events they have attended. This includes direct input and linking social media accounts.

[0447] The server analyzes the received data to identify event categories that the user is interested in. This analysis uses machine learning algorithms to correlate the user's past behavior data with their interests.

[0448] Retrieving event data

[0449] The server collects detailed event information from external sources and event organizers and stores it in a database. This information includes the type of event, location, time, and participation requirements.

[0450] Schedule generation and presentation

[0451] The server extracts event information from the database based on the user's interests and generates a schedule that considers the optimal combination. This generation takes into account factors such as the time and geographical location of events, and the time required for travel.

[0452] The device displays the generated schedule to the user. The event name, start time, location, and interest level are clearly displayed for the user to easily understand.

[0453] Specific example

[0454] For example, if a participant is attending a technical conference, and has previously attended AI-related sessions, this system analyzes the user's past attendance history and profile to automatically select the latest AI sessions being held at the current event and incorporate them into the schedule. It also takes into account breaks to ensure efficient scheduling for attending relevant sessions.

[0455] Thus, this invention allows participants to efficiently enjoy events that align with their interests.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] Users enter profile information, including their interests, hobbies, and past event participation history. This includes direct input through apps and web portals.

[0459] Step 2:

[0460] The device prepares to securely transmit information entered by the user to the server. Encrypted communication is used to maintain data integrity and privacy.

[0461] Step 3:

[0462] The server stores the received user information in a database and begins initial analysis. Here, it builds data to model the user's past behavioral patterns.

[0463] Step 4:

[0464] The server uses machine learning algorithms to analyze user interests. Based on past event participation history and entered hobbies, it identifies event categories that are likely to interest the user.

[0465] Step 5:

[0466] The server retrieves event information in real time from external event management systems and social media APIs. This information is integrated into a database, maintaining real-time updates of activity information.

[0467] Step 6:

[0468] The server selects activities from the database that match the user's interests. This process includes checking event dates, geographical locations, and adjusting for overlapping events.

[0469] Step 7:

[0470] The server generates an optimal activity schedule based on the selected events. The schedule reflects time, location, and priority based on the relevance of the events.

[0471] Step 8:

[0472] The terminal displays the schedule sent from the server to the user. A graphical interface is used to present the information in a way that is easy for the user to understand visually.

[0473] Step 9:

[0474] Users can review the displayed schedule and make adjustments, such as deleting unnecessary events or adding new events that interest them.

[0475] Step 10:

[0476] The device will store the schedule as last confirmed by the user. It will also maintain the ability to provide alerts or notifications to the user before important events begin.

[0477] (Example 1)

[0478] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0479] In traditional large-scale events, it was difficult for participants to create optimal schedules based on their own interests. Information on various events and activities was scattered, and effective suggestions tailored to individual interests were rare, resulting in generally lower participant satisfaction. In addition, there was a lack of systems that allowed for flexible changes and adjustments to schedules.

[0480] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0481] In this invention, the server includes means for acquiring information on a participant's past behavior, means for analyzing the participant's interests using a generation algorithm based on the behavior information, and means for selecting activities that match the interests from an information storage device that stores multiple activity information, and generating an activity schedule considering the optimal combination. This makes it possible for participants to easily create and adjust an optimized schedule that matches their interests.

[0482] "Participant's past behavior information" refers to data about activities and events that users have participated in in the past, and is used to understand users' interests and behavioral tendencies.

[0483] A "generative algorithm" is an algorithm that analyzes input data, extracts regularities and patterns, and generates output that is tailored to a specific purpose.

[0484] "Activities that match the user's interests" refers to events and activities that are judged to have a high probability of satisfying the user's interests and concerns.

[0485] An "information storage device" is an electronic device or system for storing and managing various types of data, and plays a role in efficiently accumulating user data and event information.

[0486] "Generating an activity schedule" refers to the process of creating a schedule that includes the optimal combination of activities, taking into account the user's interests and the characteristics of the event.

[0487] A "display device" is a device or interface that allows users to visually confirm generated schedules and information.

[0488] This system provides users with a customized schedule based on participants' interests to optimize their experience at large-scale events.

[0489] The server collects past behavioral information and interest data provided by users and performs data analysis using machine learning algorithms (generative AI models). This analysis identifies patterns in the user's interests and selects suitable events and activities. The server extracts activity information optimized for these interests from a database stored in storage and generates the most effective schedule for participants. This schedule generation includes calculations that take into account the time allocation and geographical location of events, as well as the optimization of travel time.

[0490] The terminal serves to visually present the generated schedule to the user. Information such as event name, relevance, start time, and location are clearly displayed on the terminal in a way that is easy for the user to understand intuitively. Based on this information, the user can efficiently plan event experiences that align with their interests. For example, if a user has previously attended artificial intelligence-related sessions at technical conferences, the system can automatically select the latest AI sessions and incorporate them into the schedule.

[0491] An example of a prompt for a generative AI model is, "Based on the user's past participation history and interests, generate the optimal AI-related schedule for the next technical conference." This prompt is used as an instruction to the model and serves as a starting point for generating the optimal schedule based on the generated data.

[0492] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0493] Step 1:

[0494] The server retrieves interest data and past behavior information from users. Users can provide this information by directly entering it or by linking their social media accounts. The entered data is securely stored by the server in its information storage device. Inputs include user profile data and past event participation history, and output is a record in an organized database.

[0495] Step 2:

[0496] The server begins analysis using a generative AI model with the collected user data. Specifically, it uses machine learning algorithms to analyze users' interests and past event participation trends. This analysis process utilizes data pattern recognition and clustering techniques to identify event categories that users are likely to be interested in. The input is organized user data, and the output is a list of identified interest categories.

[0497] Step 3:

[0498] The server retrieves the latest event information from external sources and event organizers. This information includes event type, location, date and time, and participation requirements. This information is obtained via APIs and stored in a database. The input is event data from external APIs, and the output is a database containing the latest event information.

[0499] Step 4:

[0500] The server extracts event information from a database based on the user's interests and generates an optimal schedule. This generation process considers factors such as event time, geographical location, user interest level, and travel time. Using an optimization algorithm, it outputs the most suitable combination of events as a schedule. The input is the identified interest categories and event information, and the output is the optimized schedule.

[0501] Step 5:

[0502] The terminal displays an optimized schedule sent from the server to the user. The terminal visually displays the event name, time, location, and interest level in an easy-to-understand manner. Based on this information, the user can efficiently plan their event participation. The input is optimized schedule data, and the output is event information displayed in a user-readable format.

[0503] (Application Example 1)

[0504] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0505] In physical stores, visitors often find it difficult to efficiently select suitable items from a large selection of products, and may not be able to move around the store effectively. Furthermore, information on new products and sales may not be provided insufficient to effectively utilize this information. As a result, there is a challenge in that the visitor's purchasing experience is not fully optimized.

[0506] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0507] In this invention, the server includes means for acquiring information on a visitor's past purchase history, means for analyzing the visitor's interests based on the purchase history information, and means for selecting products that match the visitor's interests from a database storing information on multiple products. This makes it possible to provide visitors with an optimal purchasing guide and deliver an efficient and interest-based purchasing experience in physical stores.

[0508] "Participant's past behavioral information" refers to data that shows the history of activities and events that participants have taken part in in the past.

[0509] "Methods for analyzing interests" refer to methods and techniques for identifying areas of interest or products based on the past behavior and history of participants or visitors.

[0510] "Activity information" refers to detailed data about events and activities, including information such as time, location, and type.

[0511] An "optimized activity schedule" refers to a plan of activities that is structured in a way that best suits the participants' interests and schedules.

[0512] "Information on the past purchase history of store visitors" refers to data on products that customers have previously purchased when visiting a physical store.

[0513] "Methods for analyzing interests" refer to techniques and methods for predicting products and services that a visitor might be interested in, using their past behavioral history.

[0514] "Product information" refers to data that shows the details of a product, including the product name, price, stock status, and sales information.

[0515] A "guide to optimize the shopping experience" refers to suggestions and advice provided to help visitors make purchases in stores more efficient and satisfying.

[0516] In an embodiment for carrying out this invention, the system mainly consists of a server and a user terminal.

[0517] The server first retrieves the visitor's past purchase history information from the database. This data retrieval can be done in conjunction with a customer management system. Next, the server analyzes the visitor's interests based on the retrieved purchase history information. Machine learning software (e.g., TensorFlow) is used to execute data analysis algorithms for interest analysis.

[0518] Furthermore, the server retrieves product information from external sources and product management systems and compares it with the information stored in the database. During this process, it utilizes the latest trend information to select products that match the visitor's interests.

[0519] The process of generating an optimized shopping guide utilizes location services to calculate efficient routes within the store. It also automatically generates a list of recommended products and information on special offers based on selected product information.

[0520] The terminal visually displays the purchasing guide sent from the server. Smartphone and smart glasses displays provide a visually intuitive interface, helping visitors navigate the store effectively. Furthermore, push notifications are used to deliver information on new products and special offers in real time.

[0521] For example, if a visitor has previously purchased many health foods, this system can analyze their purchase history and immediately suggest newly arrived health-related products and sales information. As a result, visitors can efficiently purchase the products they are interested in without missing out on any.

[0522] An example of a prompt message is: "You are interested in organic foods. How would you like to be supported in receiving product recommendations and special offers during your next visit to our store?"

[0523] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0524] Step 1:

[0525] The server retrieves the visitor's past purchase history information from the customer database. It receives the visitor's ID as input and extracts the relevant purchase history data. The retrieved purchase history data is returned as output. This history information is used for subsequent analysis and is accessed using the database management system.

[0526] Step 2:

[0527] The server inputs purchase history data into a machine learning algorithm to analyze visitors' interests. Specifically, it identifies product categories preferred by visitors by analyzing past purchase patterns. The output is profile information indicating visitors' interests. Generative AI models such as TensorFlow are used to associate purchase behavior with interests.

[0528] Step 3:

[0529] The server retrieves detailed product information from external sources and product management systems. It receives product IDs and category information via APIs as input, and retrieves attribute data for new products. As output, it provides the latest trending product information. This allows users to select highly relevant products by comparing them with profile information obtained through interest analysis.

[0530] Step 4:

[0531] The server generates an optimized shopping guide based on the visitor's interests. Using interest profile information and product information as input, it creates optimal purchase suggestions using a combined algorithm. As output, it generates a shopping route that allows the visitor to move efficiently within the store and a list of suggested products.

[0532] Step 5:

[0533] The terminal receives a purchase guide sent from the server and displays it on its screen. It receives purchase guide data as input and uses a visualization engine to present it clearly on the user interface. As output, it provides navigation and product information to enhance the visitor's in-store shopping experience.

[0534] Step 6:

[0535] Users navigate the store following the instructions on their device and view recommended products and special offers. By referring to the purchasing guide, users can efficiently find products of interest. Suggestions, such as prompt messages, are expected to increase visitors' purchasing intent.

[0536] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0537] The system of the present invention helps participants of large-scale events to participate in activities of interest to them in the most effective and efficient way. In addition to conventional participant information acquisition and schedule generation functions, the present invention further enhances the participant experience by incorporating an emotion engine that recognizes the user's emotions.

[0538] Program Description

[0539] Data collection and emotion recognition

[0540] Users input their profile information into the system and also provide emotional indicators such as facial expression data and voice data. This data is then analyzed by an emotion engine.

[0541] The server runs an emotion engine that analyzes user emotions in real time. This analysis is then used to inform participants' interests and satisfaction with event selection.

[0542] Activity selection and schedule generation

[0543] The server uses the results of the emotion engine to analyze the user's interests in detail. More specifically, it identifies the emotional state in which a user enjoys a particular activity and selects that activity accordingly.

[0544] Furthermore, by combining this with activity information obtained from the database, the system prioritizes and incorporates into the schedule activities that best suit the user's current emotional state.

[0545] Schedule display and adjustment

[0546] The device displays a schedule generated by the server to the user. The schedule displays recommendation levels based on emotional state, making it easier for the user to make choices that align with their own emotions.

[0547] Users can review the generated schedule and adjust or edit it according to their interests and plans.

[0548] Specific example

[0549] For example, if the emotion engine detects that a user is experiencing stress during an event, the system will prioritize suggesting relaxation workshops or activities that provide comfort. Conversely, when the user is feeling happy, it will recommend more social activities or challenging content.

[0550] In this way, by taking user emotions into consideration, the present invention can provide participants with a more personalized and engaging experience.

[0551] The following describes the processing flow.

[0552] Step 1:

[0553] Users enter their profile information and past event participation history into an application or web portal. Furthermore, they utilize devices that record emotional data such as facial expressions and voice.

[0554] Step 2:

[0555] The device collects profile information and sentiment indicator data provided by the user and transmits it to the server using a secure communication channel.

[0556] Step 3:

[0557] The server analyzes the received data. It activates the emotion engine, which analyzes facial expressions and voice data to determine the user's current emotional state in real time.

[0558] Step 4:

[0559] The server analyzes the user's interests and satisfaction levels based on their emotional state and past behavioral data. This allows it to identify activity categories recommended for specific emotional states.

[0560] Step 5:

[0561] The server combines event and activity information retrieved from the database with analysis results to select the activity best suited to the emotional state. It sets priorities based on emotions and automatically generates an optimal schedule.

[0562] Step 6:

[0563] The device displays the generated schedule to the user. The schedule includes the sentiment relevance and recommendation reasons for each activity, and is presented in a format that allows the user to easily make selections.

[0564] Step 7:

[0565] Users review the presented schedule and make adjustments as needed to suit their own schedules and interests. They use emotional fit scores as a reference to make adjustments for a better experience.

[0566] Step 8:

[0567] The device will save the final confirmed schedule and provide notifications before important events begin. Furthermore, the possibility of updating the schedule in real time in response to changes in emotional state is also being considered.

[0568] (Example 2)

[0569] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0570] In large-scale events, it can be difficult for participants to choose activities that best suit their emotional state and interests, sometimes resulting in unsatisfactory experiences. To solve this problem, a system is needed that accurately identifies participants' emotions and interests and suggests the most suitable activities based on that information.

[0571] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0572] In this invention, the server includes means for collecting basic information about participants, means for analyzing facial expressions and voice data to identify the participants' emotions, and means for selecting activities that match their interests from a data storage that stores multiple activity data. This enables the suggestion of optimal activities according to the participants' emotional state and the automatic generation of activity schedules.

[0573] A "participant" refers to an individual who participates in an event or activity, and who receives system suggestions based on their personal information and emotional state.

[0574] "Basic information" refers to information provided by participants, such as their name, age, and areas of interest, and is data that the system uses as a participant profile.

[0575] "Facial expression and voice data" refers to data, including facial movements and vocal characteristics, collected to identify the emotions of participants.

[0576] "Means of identifying emotions" refers to the process of identifying a participant's current emotional state by analyzing their facial expressions and voice data.

[0577] "Methods for analyzing interests" refer to methods of analyzing which activities align with participants' interests, based on their emotional state and basic information.

[0578] "Activity data" refers to information related to various activities within an event, including the content, time, and location of the activities.

[0579] "Data storage" refers to memory devices and systems used to store activity data, and plays a role in providing activity information when needed.

[0580] "Methods for selecting activities" refer to the process of choosing the most appropriate activity from among several options, taking into account the participants' interests and emotional information.

[0581] "Methods for automatically generating activity schedules" refer to automated methods that combine selected activities to create the most suitable schedule for participants.

[0582] "Means of visual display" refers to methods of displaying the generated activity schedule on a screen or in printed materials in a way that is easy for participants to understand.

[0583] This invention is a system that optimizes the participant experience at events. Based on the participants' emotional state and interests, this system selects appropriate activities and proposes them as a schedule.

[0584] During system operation, users enter basic profile information via their device. Facial expressions and voice data are also collected using a webcam and microphone. This collected data is sent to a server for emotion recognition.

[0585] The server is equipped with an emotion engine for analyzing facial expressions and voice data. This emotion engine utilizes open-source libraries commonly used in image processing. It also employs a specific algorithm for voice analysis to assess participants' emotional states in real time. Based on the analysis results, it identifies activities that match the participants' interests.

[0586] Based on the analysis results, the server retrieves activity information from its internal data storage and selects the activity most relevant to the participant's emotional state. This data storage contains detailed information for each activity, and the server automatically generates an appropriate schedule based on the selection results.

[0587] The generated schedule is displayed and visualized on the device. The schedule shows the priority of activities and the reasons for suggesting them, allowing users to adjust it according to their interests and schedules.

[0588] For example, if a user experiences stress during an event, the server detects this emotional state and suggests activities aimed at relaxation. This allows the user to choose an activity that suits them and have a more satisfying experience.

[0589] An example of a prompt is, "Please describe an effective method for suggesting activities in a system that combines emotion recognition and schedule generation." By sending this sentence to the generating AI model, further suggestions and improvements can be obtained.

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1:

[0592] The user uses a device to enter basic profile information for event participation. This information includes name, age, and areas of interest. The device sends this information to the server. The entered profile information is stored in a database and used as reference data for the next processing step.

[0593] Step 2:

[0594] The user provides facial expression data and voice data to the system via webcam and microphone. This data is captured in real time and sent to the server in its raw state. The server receives this data and performs facial expression analysis and voice analysis using an emotion engine. As a result of the analysis, the user's current emotional state (e.g., happy, sad, stressed) is obtained.

[0595] Step 3:

[0596] The server combines the profile information obtained in Step 1 with the emotional state data obtained in Step 2 to perform a detailed analysis of the user's interests. Specifically, it uses an internal algorithm to determine what activities are suitable for the emotional state. This analysis generates a list of candidate activities that can best satisfy the participant's interests.

[0597] Step 4:

[0598] The server retrieves activity information from the activity data storage that matches the previously generated list of candidates. Based on this, it automatically creates an activity schedule optimized for the user's emotional state and interests. This schedule is created taking into account the start time, duration, and content of the activities.

[0599] Step 5:

[0600] The device visually displays the activity schedule sent from the server to the user. The display includes the reasons and priorities for recommended activities. This allows the user to understand suggestions based on their emotional state.

[0601] Step 6:

[0602] Users can review the displayed schedule and make any necessary adjustments based on their interests and other appointments. These adjustments are made directly through the device and transmitted to the server in real time. The server can then review the updated schedule and make any further adjustments as needed.

[0603] (Application Example 2)

[0604] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0605] In large-scale events and shopping facilities, there is a challenge in that participants and customers have difficulty selecting activities and products that best suit their current emotional state. Furthermore, this makes it difficult to optimize the quality of the experience according to individual emotional states, resulting in limited improvements in satisfaction.

[0606] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0607] In this invention, the server includes means for acquiring information on participants' past behavior, means for analyzing the user's emotional state, and means for selecting activities based on the analyzed emotional state and automatically generating an optimized activity schedule. This makes it possible for individual participants to be automatically presented with activities and products that are best suited to their own emotional state.

[0608] "Participant's past behavioral information" refers to information about participants' past activities and behavioral history at events or for the target audience.

[0609] "Means of analyzing participants' interests based on behavioral information" refers to the processes and methods for analyzing and identifying participants' interests and preferences from past behavioral data.

[0610] An "information recording medium" refers to a data storage device that stores multiple activity records and allows access to them as needed.

[0611] "Means of analyzing a user's emotional state" refers to technologies and methods for determining a user's emotional state by analyzing data such as their facial expressions and voice.

[0612] "Methods for automatically generating optimized activity schedules" refers to a process that automatically creates the most appropriate activity schedule for participants based on analyzed data.

[0613] "Trend information from external sources" refers to information about current trends and popular styles obtained from external sources.

[0614] "Re-recommendation based on changes in emotional state" refers to a process where, when a user's emotions change, the initial recommendation activity is re-evaluated and a new, optimal suggestion is made.

[0615] This invention is a system for recommending optimal activities and products based on users' emotional states at large-scale events and shopping facilities where users participate. The system has a configuration that broadly includes the following processes: data collection, emotion analysis, recommendation generation, and display.

[0616] The server retrieves and analyzes users' past behavioral information by analyzing data stored on an information storage medium, including their participation history and activity history. This past behavioral information is stored using a secure database management system.

[0617] Next, facial recognition software and voice analysis tools are used to analyze the user's emotional state. Specifically, data is acquired in real time via cameras and microphones built into smartphones or smart glasses and sent to a server. The server uses an emotion engine to analyze this data and identify the user's emotional state. Tools such as Amazon Rekognition and Google Speech-to-Text can be used in this analysis process.

[0618] Based on the analyzed emotional state, the server selects the most suitable activities and products from the information storage medium. This generates a real-time activity schedule tailored to each individual user's emotional state. The generated activity schedule is immediately notified to the user's mobile device, allowing them to view details of the selected activities.

[0619] For example, if the analysis indicates that a user is feeling stressed, the server will recommend information about relaxation products or cafe areas. Conversely, when the user is in a cheerful mood, it can suggest positive activities such as information about new product sales.

[0620] An example of a prompt message is, "What products are recommended when a user is feeling anxious?" By providing recommendations based on emotional states in this way, users can have a more satisfying experience.

[0621] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0622] Step 1:

[0623] Users enter their information into their mobile devices and send that data to the server. The input data includes past behavioral history and current location information. The server stores the received information on an information storage medium and uses it as basic data for behavioral analysis.

[0624] Step 2:

[0625] The device transmits facial images and audio data collected in real time from its built-in camera and microphone to a server. This data is used as input to analyze the user's emotional state. The server uses facial recognition and audio analysis tools to analyze this data and identify the user's emotional state.

[0626] Step 3:

[0627] The server uses the sentiment analysis results to select activities based on the user's current emotional state. It retrieves activity information most suitable for the identified emotion from the information storage medium and generates an optimized activity schedule based on this information. If the sentiment analysis utilizes a generative AI model, it may also consider prompt text to derive the optimal suggestion.

[0628] Step 4:

[0629] The server sends the generated activity schedule to the user's mobile device. The device notifies the user of this information and displays the activity details and recommendation level on the screen. The user can review this information and select the appropriate action.

[0630] Step 5:

[0631] Users participate in selected activities based on the displayed schedule. If necessary, users can edit their schedules and adjust them to suit their preferences and plans. This allows users to enjoy an experience that aligns with their individual emotional state.

[0632] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0633] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0634] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0635] [Fourth Embodiment]

[0636] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0637] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0638] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0639] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0640] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0641] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0642] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0643] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0644] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0645] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0646] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0647] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0648] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0649] The system of this invention is designed to optimize the participant experience at large-scale events. Based on participant behavioral data and profile information, it generates individually customized activity schedules. Specifically, it analyzes participants' interests and suggests highly relevant events and activities based on those interests.

[0650] Program Description

[0651] Data entry and analysis

[0652] Users register information about their areas of interest and past events they have attended. This includes direct input and linking social media accounts.

[0653] The server analyzes the received data to identify event categories that the user is interested in. This analysis uses machine learning algorithms to correlate the user's past behavior data with their interests.

[0654] Retrieving event data

[0655] The server collects detailed event information from external sources and event organizers and stores it in a database. This information includes the type of event, location, time, and participation requirements.

[0656] Schedule generation and presentation

[0657] The server extracts event information from the database based on the user's interests and generates a schedule that considers the optimal combination. This generation takes into account factors such as the time and geographical location of events, and the time required for travel.

[0658] The device displays the generated schedule to the user. The event name, start time, location, and interest level are clearly displayed for the user to easily understand.

[0659] Specific example

[0660] For example, if a participant is attending a technical conference, and has previously attended AI-related sessions, this system analyzes the user's past attendance history and profile to automatically select the latest AI sessions being held at the current event and incorporate them into the schedule. It also takes into account breaks to ensure efficient scheduling for attending relevant sessions.

[0661] Thus, this invention allows participants to efficiently enjoy events that align with their interests.

[0662] The following describes the processing flow.

[0663] Step 1:

[0664] Users enter profile information, including their interests, hobbies, and past event participation history. This includes direct input through apps and web portals.

[0665] Step 2:

[0666] The device prepares to securely transmit information entered by the user to the server. Encrypted communication is used to maintain data integrity and privacy.

[0667] Step 3:

[0668] The server stores the received user information in a database and begins initial analysis. Here, it builds data to model the user's past behavioral patterns.

[0669] Step 4:

[0670] The server uses machine learning algorithms to analyze user interests. Based on past event participation history and entered hobbies, it identifies event categories that are likely to interest the user.

[0671] Step 5:

[0672] The server retrieves event information in real time from external event management systems and social media APIs. This information is integrated into a database, maintaining real-time updates of activity information.

[0673] Step 6:

[0674] The server selects activities from the database that match the user's interests. This process includes checking event dates, geographical locations, and adjusting for overlapping events.

[0675] Step 7:

[0676] The server generates an optimal activity schedule based on the selected events. The schedule reflects time, location, and priority based on the relevance of the events.

[0677] Step 8:

[0678] The terminal displays the schedule sent from the server to the user. A graphical interface is used to present the information in a way that is easy for the user to understand visually.

[0679] Step 9:

[0680] Users can review the displayed schedule and make adjustments, such as deleting unnecessary events or adding new events that interest them.

[0681] Step 10:

[0682] The device will store the schedule as last confirmed by the user. It will also maintain the ability to provide alerts or notifications to the user before important events begin.

[0683] (Example 1)

[0684] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0685] In traditional large-scale events, it was difficult for participants to create optimal schedules based on their own interests. Information on various events and activities was scattered, and effective suggestions tailored to individual interests were rare, resulting in generally lower participant satisfaction. In addition, there was a lack of systems that allowed for flexible changes and adjustments to schedules.

[0686] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0687] In this invention, the server includes means for acquiring information on a participant's past behavior, means for analyzing the participant's interests using a generation algorithm based on the behavior information, and means for selecting activities that match the interests from an information storage device that stores multiple activity information, and generating an activity schedule considering the optimal combination. This makes it possible for participants to easily create and adjust an optimized schedule that matches their interests.

[0688] "Participant's past behavior information" refers to data about activities and events that users have participated in in the past, and is used to understand users' interests and behavioral tendencies.

[0689] A "generative algorithm" is an algorithm that analyzes input data, extracts regularities and patterns, and generates output that is tailored to a specific purpose.

[0690] "Activities that match the user's interests" refers to events and activities that are judged to have a high probability of satisfying the user's interests and concerns.

[0691] An "information storage device" is an electronic device or system for storing and managing various types of data, and plays a role in efficiently accumulating user data and event information.

[0692] "Generating an activity schedule" refers to the process of creating a schedule that includes the optimal combination of activities, taking into account the user's interests and the characteristics of the event.

[0693] A "display device" is a device or interface that allows users to visually confirm generated schedules and information.

[0694] This system provides users with a customized schedule based on participants' interests to optimize their experience at large-scale events.

[0695] The server collects past behavioral information and interest data provided by users and performs data analysis using machine learning algorithms (generative AI models). This analysis identifies patterns in the user's interests and selects suitable events and activities. The server extracts activity information optimized for these interests from a database stored in storage and generates the most effective schedule for participants. This schedule generation includes calculations that take into account the time allocation and geographical location of events, as well as the optimization of travel time.

[0696] The terminal serves to visually present the generated schedule to the user. Information such as event name, relevance, start time, and location are clearly displayed on the terminal in a way that is easy for the user to understand intuitively. Based on this information, the user can efficiently plan event experiences that align with their interests. For example, if a user has previously attended artificial intelligence-related sessions at technical conferences, the system can automatically select the latest AI sessions and incorporate them into the schedule.

[0697] An example of a prompt for a generative AI model is, "Based on the user's past participation history and interests, generate the optimal AI-related schedule for the next technical conference." This prompt is used as an instruction to the model and serves as a starting point for generating the optimal schedule based on the generated data.

[0698] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0699] Step 1:

[0700] The server retrieves interest data and past behavior information from users. Users can provide this information by directly entering it or by linking their social media accounts. The entered data is securely stored by the server in its information storage device. Inputs include user profile data and past event participation history, and output is a record in an organized database.

[0701] Step 2:

[0702] The server begins analysis using a generative AI model with the collected user data. Specifically, it uses machine learning algorithms to analyze users' interests and past event participation trends. This analysis process utilizes data pattern recognition and clustering techniques to identify event categories that users are likely to be interested in. The input is organized user data, and the output is a list of identified interest categories.

[0703] Step 3:

[0704] The server retrieves the latest event information from external sources and event organizers. This information includes event type, location, date and time, and participation requirements. This information is obtained via APIs and stored in a database. The input is event data from external APIs, and the output is a database containing the latest event information.

[0705] Step 4:

[0706] The server extracts event information from a database based on the user's interests and generates an optimal schedule. This generation process considers factors such as event time, geographical location, user interest level, and travel time. Using an optimization algorithm, it outputs the most suitable combination of events as a schedule. The input is the identified interest categories and event information, and the output is the optimized schedule.

[0707] Step 5:

[0708] The terminal displays an optimized schedule sent from the server to the user. The terminal visually displays the event name, time, location, and interest level in an easy-to-understand manner. Based on this information, the user can efficiently plan their event participation. The input is optimized schedule data, and the output is event information displayed in a user-readable format.

[0709] (Application Example 1)

[0710] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0711] In physical stores, visitors often find it difficult to efficiently select suitable items from a large selection of products, and may not be able to move around the store effectively. Furthermore, information on new products and sales may not be provided insufficient to effectively utilize this information. As a result, there is a challenge in that the visitor's purchasing experience is not fully optimized.

[0712] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0713] In this invention, the server includes means for acquiring information on a visitor's past purchase history, means for analyzing the visitor's interests based on the purchase history information, and means for selecting products that match the visitor's interests from a database storing information on multiple products. This makes it possible to provide visitors with an optimal purchasing guide and deliver an efficient and interest-based purchasing experience in physical stores.

[0714] "Participant's past behavioral information" refers to data that shows the history of activities and events that participants have taken part in in the past.

[0715] "Methods for analyzing interests" refer to methods and techniques for identifying areas of interest or products based on the past behavior and history of participants or visitors.

[0716] "Activity information" refers to detailed data about events and activities, including information such as time, location, and type.

[0717] An "optimized activity schedule" refers to a plan of activities that is structured in a way that best suits the participants' interests and schedules.

[0718] "Information on the past purchase history of store visitors" refers to data on products that customers have previously purchased when visiting a physical store.

[0719] "Methods for analyzing interests" refer to techniques and methods for predicting products and services that a visitor might be interested in, using their past behavioral history.

[0720] "Product information" refers to data that shows the details of a product, including the product name, price, stock status, and sales information.

[0721] A "guide to optimize the shopping experience" refers to suggestions and advice provided to help visitors make purchases in stores more efficient and satisfying.

[0722] In an embodiment for carrying out this invention, the system mainly consists of a server and a user terminal.

[0723] The server first retrieves the visitor's past purchase history information from the database. This data retrieval can be done in conjunction with a customer management system. Next, the server analyzes the visitor's interests based on the retrieved purchase history information. Machine learning software (e.g., TensorFlow) is used to execute data analysis algorithms for interest analysis.

[0724] Furthermore, the server retrieves product information from external sources and product management systems and compares it with the information stored in the database. During this process, it utilizes the latest trend information to select products that match the visitor's interests.

[0725] The process of generating an optimized shopping guide utilizes location services to calculate efficient routes within the store. It also automatically generates a list of recommended products and information on special offers based on selected product information.

[0726] The terminal visually displays the purchasing guide sent from the server. Smartphone and smart glasses displays provide a visually intuitive interface, helping visitors navigate the store effectively. Furthermore, push notifications are used to deliver information on new products and special offers in real time.

[0727] For example, if a visitor has previously purchased many health foods, this system can analyze their purchase history and immediately suggest newly arrived health-related products and sales information. As a result, visitors can efficiently purchase the products they are interested in without missing out on any.

[0728] An example of a prompt message is: "You are interested in organic foods. How would you like to be supported in receiving product recommendations and special offers during your next visit to our store?"

[0729] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0730] Step 1:

[0731] The server retrieves the visitor's past purchase history information from the customer database. It receives the visitor's ID as input and extracts the relevant purchase history data. The retrieved purchase history data is returned as output. This history information is used for subsequent analysis and is accessed using the database management system.

[0732] Step 2:

[0733] The server inputs purchase history data into a machine learning algorithm to analyze visitors' interests. Specifically, it identifies product categories preferred by visitors by analyzing past purchase patterns. The output is profile information indicating visitors' interests. Generative AI models such as TensorFlow are used to associate purchase behavior with interests.

[0734] Step 3:

[0735] The server retrieves detailed product information from external sources and product management systems. It receives product IDs and category information via APIs as input, and retrieves attribute data for new products. As output, it provides the latest trending product information. This allows users to select highly relevant products by comparing them with profile information obtained through interest analysis.

[0736] Step 4:

[0737] The server generates an optimized shopping guide based on the visitor's interests. Using interest profile information and product information as input, it creates optimal purchase suggestions using a combined algorithm. As output, it generates a shopping route that allows the visitor to move efficiently within the store and a list of suggested products.

[0738] Step 5:

[0739] The terminal receives a purchase guide sent from the server and displays it on its screen. It receives purchase guide data as input and uses a visualization engine to present it clearly on the user interface. As output, it provides navigation and product information to enhance the visitor's in-store shopping experience.

[0740] Step 6:

[0741] Users navigate the store following the instructions on their device and view recommended products and special offers. By referring to the purchasing guide, users can efficiently find products of interest. Suggestions, such as prompt messages, are expected to increase visitors' purchasing intent.

[0742] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0743] The system of the present invention helps participants of large-scale events to participate in activities of interest to them in the most effective and efficient way. In addition to conventional participant information acquisition and schedule generation functions, the present invention further enhances the participant experience by incorporating an emotion engine that recognizes the user's emotions.

[0744] Program Description

[0745] Data collection and emotion recognition

[0746] Users input their profile information into the system and also provide emotional indicators such as facial expression data and voice data. This data is then analyzed by an emotion engine.

[0747] The server runs an emotion engine that analyzes user emotions in real time. This analysis is then used to inform participants' interests and satisfaction with event selection.

[0748] Activity selection and schedule generation

[0749] The server uses the results of the emotion engine to analyze the user's interests in detail. More specifically, it identifies the emotional state in which a user enjoys a particular activity and selects that activity accordingly.

[0750] Furthermore, by combining this with activity information obtained from the database, the system prioritizes and incorporates into the schedule activities that best suit the user's current emotional state.

[0751] Schedule display and adjustment

[0752] The device displays a schedule generated by the server to the user. The schedule displays recommendation levels based on emotional state, making it easier for the user to make choices that align with their own emotions.

[0753] Users can review the generated schedule and adjust or edit it according to their interests and plans.

[0754] Specific example

[0755] For example, if the emotion engine detects that a user is experiencing stress during an event, the system will prioritize suggesting relaxation workshops or activities that provide comfort. Conversely, when the user is feeling happy, it will recommend more social activities or challenging content.

[0756] In this way, by taking user emotions into consideration, the present invention can provide participants with a more personalized and engaging experience.

[0757] The following describes the processing flow.

[0758] Step 1:

[0759] Users enter their profile information and past event participation history into an application or web portal. Furthermore, they utilize devices that record emotional data such as facial expressions and voice.

[0760] Step 2:

[0761] The device collects profile information and sentiment indicator data provided by the user and transmits it to the server using a secure communication channel.

[0762] Step 3:

[0763] The server analyzes the received data. It activates the emotion engine, which analyzes facial expressions and voice data to determine the user's current emotional state in real time.

[0764] Step 4:

[0765] The server analyzes the user's interests and satisfaction levels based on their emotional state and past behavioral data. This allows it to identify activity categories recommended for specific emotional states.

[0766] Step 5:

[0767] The server combines event and activity information retrieved from the database with analysis results to select the activity best suited to the emotional state. It sets priorities based on emotions and automatically generates an optimal schedule.

[0768] Step 6:

[0769] The device displays the generated schedule to the user. The schedule includes the sentiment relevance and recommendation reasons for each activity, and is presented in a format that allows the user to easily make selections.

[0770] Step 7:

[0771] Users review the presented schedule and make adjustments as needed to suit their own schedules and interests. They use emotional fit scores as a reference to make adjustments for a better experience.

[0772] Step 8:

[0773] The device will save the final confirmed schedule and provide notifications before important events begin. Furthermore, the possibility of updating the schedule in real time in response to changes in emotional state is also being considered.

[0774] (Example 2)

[0775] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0776] In large-scale events, it can be difficult for participants to choose activities that best suit their emotional state and interests, sometimes resulting in unsatisfactory experiences. To solve this problem, a system is needed that accurately identifies participants' emotions and interests and suggests the most suitable activities based on that information.

[0777] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0778] In this invention, the server includes means for collecting basic information about participants, means for analyzing facial expressions and voice data to identify the participants' emotions, and means for selecting activities that match their interests from a data storage that stores multiple activity data. This enables the suggestion of optimal activities according to the participants' emotional state and the automatic generation of activity schedules.

[0779] A "participant" refers to an individual who participates in an event or activity, and who receives system suggestions based on their personal information and emotional state.

[0780] "Basic information" refers to information provided by participants, such as their name, age, and areas of interest, and is data that the system uses as a participant profile.

[0781] "Facial expression and voice data" refers to data, including facial movements and vocal characteristics, collected to identify the emotions of participants.

[0782] "Means of identifying emotions" refers to the process of identifying a participant's current emotional state by analyzing their facial expressions and voice data.

[0783] "Methods for analyzing interests" refer to methods of analyzing which activities align with participants' interests, based on their emotional state and basic information.

[0784] "Activity data" refers to information related to various activities within an event, including the content, time, and location of the activities.

[0785] "Data storage" refers to memory devices and systems used to store activity data, and plays a role in providing activity information when needed.

[0786] "Methods for selecting activities" refer to the process of choosing the most appropriate activity from among several options, taking into account the participants' interests and emotional information.

[0787] "Methods for automatically generating activity schedules" refer to automated methods that combine selected activities to create the most suitable schedule for participants.

[0788] "Means of visual display" refers to methods of displaying the generated activity schedule on a screen or in printed materials in a way that is easy for participants to understand.

[0789] This invention is a system that optimizes the participant experience at events. Based on the participants' emotional state and interests, this system selects appropriate activities and proposes them as a schedule.

[0790] During system operation, users enter basic profile information via their device. Facial expressions and voice data are also collected using a webcam and microphone. This collected data is sent to a server for emotion recognition.

[0791] The server is equipped with an emotion engine for analyzing facial expressions and voice data. This emotion engine utilizes open-source libraries commonly used in image processing. It also employs a specific algorithm for voice analysis to assess participants' emotional states in real time. Based on the analysis results, it identifies activities that match the participants' interests.

[0792] Based on the analysis results, the server retrieves activity information from its internal data storage and selects the activity most relevant to the participant's emotional state. This data storage contains detailed information for each activity, and the server automatically generates an appropriate schedule based on the selection results.

[0793] The generated schedule is displayed and visualized on the device. The schedule shows the priority of activities and the reasons for suggesting them, allowing users to adjust it according to their interests and schedules.

[0794] For example, if a user experiences stress during an event, the server detects this emotional state and suggests activities aimed at relaxation. This allows the user to choose an activity that suits them and have a more satisfying experience.

[0795] An example of a prompt is, "Please describe an effective method for suggesting activities in a system that combines emotion recognition and schedule generation." By sending this sentence to the generating AI model, further suggestions and improvements can be obtained.

[0796] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0797] Step 1:

[0798] The user uses a device to enter basic profile information for event participation. This information includes name, age, and areas of interest. The device sends this information to the server. The entered profile information is stored in a database and used as reference data for the next processing step.

[0799] Step 2:

[0800] The user provides facial expression data and voice data to the system via webcam and microphone. This data is captured in real time and sent to the server in its raw state. The server receives this data and performs facial expression analysis and voice analysis using an emotion engine. As a result of the analysis, the user's current emotional state (e.g., happy, sad, stressed) is obtained.

[0801] Step 3:

[0802] The server combines the profile information obtained in Step 1 with the emotional state data obtained in Step 2 to perform a detailed analysis of the user's interests. Specifically, it uses an internal algorithm to determine what activities are suitable for the emotional state. This analysis generates a list of candidate activities that can best satisfy the participant's interests.

[0803] Step 4:

[0804] The server retrieves activity information from the activity data storage that matches the previously generated list of candidates. Based on this, it automatically creates an activity schedule optimized for the user's emotional state and interests. This schedule is created taking into account the start time, duration, and content of the activities.

[0805] Step 5:

[0806] The device visually displays the activity schedule sent from the server to the user. The display includes the reasons and priorities for recommended activities. This allows the user to understand suggestions based on their emotional state.

[0807] Step 6:

[0808] Users can review the displayed schedule and make any necessary adjustments based on their interests and other appointments. These adjustments are made directly through the device and transmitted to the server in real time. The server can then review the updated schedule and make any further adjustments as needed.

[0809] (Application Example 2)

[0810] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0811] In large-scale events and shopping facilities, there is a challenge in that participants and customers have difficulty selecting activities and products that best suit their current emotional state. Furthermore, this makes it difficult to optimize the quality of the experience according to individual emotional states, resulting in limited improvements in satisfaction.

[0812] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0813] In this invention, the server includes means for acquiring information on participants' past behavior, means for analyzing the user's emotional state, and means for selecting activities based on the analyzed emotional state and automatically generating an optimized activity schedule. This makes it possible for individual participants to be automatically presented with activities and products that are best suited to their own emotional state.

[0814] "Participant's past behavioral information" refers to information about participants' past activities and behavioral history at events or for the target audience.

[0815] "Means of analyzing participants' interests based on behavioral information" refers to the processes and methods for analyzing and identifying participants' interests and preferences from past behavioral data.

[0816] An "information recording medium" refers to a data storage device that stores multiple activity records and allows access to them as needed.

[0817] "Means of analyzing a user's emotional state" refers to technologies and methods for determining a user's emotional state by analyzing data such as their facial expressions and voice.

[0818] "Methods for automatically generating optimized activity schedules" refers to a process that automatically creates the most appropriate activity schedule for participants based on analyzed data.

[0819] "Trend information from external sources" refers to information about current trends and popular styles obtained from external sources.

[0820] "Re-recommendation based on changes in emotional state" refers to a process where, when a user's emotions change, the initial recommendation activity is re-evaluated and a new, optimal suggestion is made.

[0821] This invention is a system for recommending optimal activities and products based on users' emotional states at large-scale events and shopping facilities where users participate. The system has a configuration that broadly includes the following processes: data collection, emotion analysis, recommendation generation, and display.

[0822] The server retrieves and analyzes users' past behavioral information by analyzing data stored on an information storage medium, including their participation history and activity history. This past behavioral information is stored using a secure database management system.

[0823] Next, facial recognition software and voice analysis tools are used to analyze the user's emotional state. Specifically, data is acquired in real time via cameras and microphones built into smartphones or smart glasses and sent to a server. The server uses an emotion engine to analyze this data and identify the user's emotional state. Tools such as Amazon Rekognition and Google Speech-to-Text can be used in this analysis process.

[0824] Based on the analyzed emotional state, the server selects the most suitable activities and products from the information storage medium. This generates a real-time activity schedule tailored to each individual user's emotional state. The generated activity schedule is immediately notified to the user's mobile device, allowing them to view details of the selected activities.

[0825] For example, if the analysis indicates that a user is feeling stressed, the server will recommend information about relaxation products or cafe areas. Conversely, when the user is in a cheerful mood, it can suggest positive activities such as information about new product sales.

[0826] An example of a prompt message is, "What products are recommended when a user is feeling anxious?" By providing recommendations based on emotional states in this way, users can have a more satisfying experience.

[0827] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0828] Step 1:

[0829] Users enter their information into their mobile devices and send that data to the server. The input data includes past behavioral history and current location information. The server stores the received information on an information storage medium and uses it as basic data for behavioral analysis.

[0830] Step 2:

[0831] The device transmits facial images and audio data collected in real time from its built-in camera and microphone to a server. This data is used as input to analyze the user's emotional state. The server uses facial recognition and audio analysis tools to analyze this data and identify the user's emotional state.

[0832] Step 3:

[0833] The server uses the sentiment analysis results to select activities based on the user's current emotional state. It retrieves activity information most suitable for the identified emotion from the information storage medium and generates an optimized activity schedule based on this information. If the sentiment analysis utilizes a generative AI model, it may also consider prompt text to derive the optimal suggestion.

[0834] Step 4:

[0835] The server sends the generated activity schedule to the user's mobile device. The device notifies the user of this information and displays the activity details and recommendation level on the screen. The user can review this information and select the appropriate action.

[0836] Step 5:

[0837] Users participate in selected activities based on the displayed schedule. If necessary, users can edit their schedules and adjust them to suit their preferences and plans. This allows users to enjoy an experience that aligns with their individual emotional state.

[0838] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0839] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0840] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0841] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0842] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0843] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0844] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0845] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0846] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0847] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0848] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0849] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0850] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0851] 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.

[0852] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0853] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0854] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0855] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0856] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0857] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0858] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0859] The following is further disclosed regarding the embodiments described above.

[0860] (Claim 1)

[0861] Means for obtaining information on participants' past behavior,

[0862] A means for analyzing participants' interests based on the aforementioned behavioral information,

[0863] A means for selecting an activity that matches the aforementioned interest from a database containing information on multiple activities,

[0864] A means for automatically generating an optimized activity schedule based on the selected activities,

[0865] The means for displaying the generated activity schedule,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, comprising means for obtaining trend information from external sources and utilizing it for analysis.

[0869] (Claim 3)

[0870] The system according to claim 1, comprising means for allowing participants to edit the generated activity schedule.

[0871] "Example 1"

[0872] (Claim 1)

[0873] Means for obtaining information on participants' past behavior,

[0874] A means for analyzing participants' interests using a generation algorithm based on the aforementioned behavioral information,

[0875] A means for selecting activities that match the aforementioned interests from an information storage device that stores information on multiple activities, and generating an activity schedule considering the optimal combination,

[0876] A means for visually displaying the generated activity schedule on a display device,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, comprising means for collecting trend information from external sources and utilizing it for the analysis.

[0880] (Claim 3)

[0881] The system according to claim 1, further comprising means that participants can manually modify the generated activity schedule.

[0882] "Application Example 1"

[0883] (Claim 1)

[0884] Means for obtaining information on participants' past behavior,

[0885] A means for analyzing participants' interests based on the aforementioned behavioral information,

[0886] A means for selecting an activity that matches the aforementioned interest from a database containing information on multiple activities,

[0887] A means for automatically generating an optimized activity schedule based on the selected activities,

[0888] The means for displaying the generated activity schedule,

[0889] A means of obtaining information on the past purchase history of store visitors,

[0890] A means for analyzing the interests of visitors based on the aforementioned purchase history information,

[0891] A means for selecting a product that matches the aforementioned interest from a database containing information on multiple products,

[0892] A means for automatically generating a guide to optimize the visitor's purchasing experience based on the selected products,

[0893] Means for displaying the generated guide,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, comprising means for obtaining trend information from external sources and utilizing it for analysis.

[0897] (Claim 3)

[0898] The system according to claim 1, comprising means for enabling visitors to edit the generated purchasing guide.

[0899] "Example 2 of combining an emotion engine"

[0900] (Claim 1)

[0901] Means for collecting basic information about participants,

[0902] A means of identifying participants' emotions by analyzing facial expressions and voice data,

[0903] A means for analyzing participants' interests based on the aforementioned emotional information,

[0904] A means for selecting activities that match the aforementioned interests from a data storage that stores multiple activity data,

[0905] A means for automatically generating an activity schedule that corresponds to the emotional state of the participants based on the selected activities,

[0906] A means for visually displaying the generated activity schedule,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, comprising means for obtaining trend information from external sources and utilizing it for analyzing participants' interests.

[0910] (Claim 3)

[0911] The system according to claim 1, comprising means for participants to review and adjust the generated activity schedule.

[0912] "Application example 2 when combining with an emotional engine"

[0913] (Claim 1)

[0914] Means for obtaining information on participants' past behavior,

[0915] A means for analyzing participants' interests based on the aforementioned behavioral information,

[0916] A means for selecting an activity that matches the interest from an information recording medium storing multiple activity information,

[0917] A means of analyzing the emotional state of users,

[0918] A means for selecting activities based on analyzed emotional states and automatically generating an optimized activity schedule,

[0919] The means for displaying the generated activity schedule,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, comprising means for obtaining trend information from external sources and combining it with user sentiment data for analysis.

[0923] (Claim 3)

[0924] The system according to claim 1, comprising means for allowing participants to edit the generated activity schedule and for providing revised recommendations in response to changes in their emotional state. [Explanation of symbols]

[0925] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for obtaining information on participants' past behavior, A means for analyzing participants' interests based on the aforementioned behavioral information, A means for selecting an activity that matches the aforementioned interest from a database containing information on multiple activities, A means for automatically generating an optimized activity schedule based on the selected activities, The means for displaying the generated activity schedule, A system that includes this.

2. The system according to claim 1, comprising means for obtaining trend information from external sources and utilizing it for analysis.

3. The system according to claim 1, comprising means for allowing participants to edit the generated activity schedule.

Images