system

Abstract

We provide the system. [Solution] Means of receiving past event data, A means for evaluating the effectiveness of the generated proposals, A means of adjusting proposals based on participant characteristics, A method that utilizes a generation engine to propose the content of events, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] The success rate of an event varies depending on the facility and the characteristics of the participants, and in conventional methods, routine events are often repeated. Therefore, there is a need for a system that can efficiently generate new ideas while utilizing past event data and improve the success rate of events.

Means for Solving the Problems

[0005] The above problems are solved by providing a system including means for receiving past event data, means for evaluating the effectiveness of generated proposals, means for adjusting proposals based on participant characteristics, and means for utilizing a generation engine that proposes event content. This system supports the process of creating new event content and realizes an optimal proposal for the user.

[0006] "Past event data" refers to information and results related to events held in the past, including evaluations and participant reactions.

[0007] "Means for evaluating the effectiveness of generated proposals" refers to methods and processes for determining how effective the generated event proposals are in relation to the participants and the objectives of the event.

[0008] "Participant characteristics" refer to the age, gender, hobbies, interests, and other characteristics of people who are likely to participate in the event.

[0009] A "generation engine" refers to an algorithm or software that automatically generates the content of new events based on the input data.

[0010] "Proposed results" are a collection of new ideas presented to the user, consisting of event content suggestions generated by the generation engine.

[0011] A "user" refers to an individual or group that uses the system to receive event suggestions or provide feedback.

[0012] "Feedback" refers to the act of users providing evaluations and suggestions for improvement regarding proposed events. [Brief explanation of the drawing]

[0013] [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]It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing apparatus and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the 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.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention automates the proposal of event content by appropriately coordinating the server, terminal, and generation engine of the proposed system. In this system, the user inputs past event data using a terminal and sends it to the server. The server receives this data and, using the generation engine, generates appropriate event proposals considering participant characteristics and past data.

[0035] The generated suggestions are sent from the server to the terminal and displayed to the user. The user reviews the suggested events and provides feedback as needed. This allows the system to incorporate user feedback and improve the accuracy of future suggestions.

[0036] As a concrete example, suppose a user inputs data stating, "I previously held cooking classes and workshops at local events, and the participants were mainly in their 30s to 50s." The server analyzes this information and, through its generation engine, suggests a "new workshop combining healthy cooking and community interaction." The user can then receive this suggestion, review its content, and provide feedback.

[0037] This invention makes it possible to quickly and effectively generate new ideas in event planning, break away from monotonous events, and achieve high participant satisfaction.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] Users input past data related to the event (e.g., event name, participant characteristics, satisfaction level, etc.) through the terminal interface.

[0041] Step 2:

[0042] The terminal formats the input data and sends it to the server. During transmission, it verifies data integrity as needed.

[0043] Step 3:

[0044] The server performs data analysis based on the received data. Specifically, it checks the type of event, the characteristics of the participants, and past satisfaction levels to understand the needs of the event.

[0045] Step 4:

[0046] The server uses the data analysis results to provide information to the generation engine and instructs it to generate event proposals. This generation engine has an algorithm that constructs the content of new events.

[0047] Step 5:

[0048] The generation engine generates several event suggestions based on historical data and market trends. It returns these suggested candidates to the server.

[0049] Step 6:

[0050] The server receives the generated event proposals and selects the most suitable one. If necessary, it adjusts multiple proposals to meet the user's needs.

[0051] Step 7:

[0052] The server sends the selected event proposals to the terminal.

[0053] Step 8:

[0054] The terminal receives proposals from the server and displays them in a user-friendly format. It also displays information explaining the details and benefits of the proposals.

[0055] Step 9:

[0056] Users review the proposals and provide feedback as needed. This feedback helps improve the accuracy of future proposals.

[0057] (Example 1)

[0058] 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."

[0059] Traditional event planning methods struggled to generate new ideas and quickly provide optimal proposals tailored to participant characteristics, resulting in a stagnation of events. Furthermore, participant feedback was not adequately utilized, hindering improvements in future event proposals. Additionally, the lack of a system to efficiently manage these processes created a need for increased efficiency in event planning.

[0060] 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.

[0061] In this invention, the server includes means for acquiring information about past events, means for inputting prompt sentences into a generation AI model to generate suggestions, and means for transferring the generated suggestion content to a terminal. This makes it possible to quickly and effectively create new event suggestions tailored to participant characteristics and to improve the accuracy of suggestions for future events by incorporating user feedback.

[0062] "Means for obtaining information on past events" refers to devices or software that have the function of collecting data such as the content, date and time, participant characteristics, and participant feedback of past events.

[0063] "Means for verifying generated proposals" refers to a process or system for evaluating the effectiveness and appropriateness of event proposals created by a generative AI model.

[0064] "Means of adjusting proposals based on participant characteristics" refers to methods or techniques for optimizing proposals by taking into account participants' age, interests, past participation history, etc.

[0065] "Means using a generation processing device that automatically generates event content" refers to a device or system that uses AI models or algorithms to automatically create event proposals.

[0066] "Means for transferring generated proposal content to a terminal" refers to a technology or device for transferring event proposals generated from a server to a terminal used by a user via digital communication.

[0067] "A means of inputting prompt sentences into a generative AI model to generate suggestions" refers to a process that uses natural language processing technology to input text containing specific instructions (prompt sentences) into an AI model and creates event suggestions based on that input.

[0068] This invention relates to a system for automating the generation of new proposals in event planning. The system primarily involves the collaboration of a server, terminals, and a generation engine to generate new proposals based on past event data.

[0069] The user first uses a terminal to enter information about past events. This information includes the type of event, the age range of participants, and feedback from past participants. This data is entered on the terminal and sent to the server by executing the data transmission command.

[0070] The server analyzes the received data. This analysis can utilize data analysis libraries such as Python or R. Based on the analyzed data, the server generates new event suggestions using a generative AI model (e.g., GPT-4®). During this process, prompts are input to the generation engine, causing the AI ​​model to return appropriate suggestions.

[0071] The generated suggestions are transferred from the server to the terminal and displayed visually to the user on the terminal. The user reviews the displayed suggestions and provides feedback on their satisfaction level and areas for improvement. This feedback is sent back to the server and used to improve future suggestions.

[0072] As a concrete example, consider a scenario where a user inputs the following prompt into the generation engine: "I previously held cooking classes and workshops for participants aged 30-50. Please suggest ideas for the next event. I would like suggestions that consider new elements and combinations with other activities." Based on this prompt, the AI ​​model suggests "a new workshop combining healthy cooking and community interaction," and the server forwards this suggestion to the user's device. The user receives and reviews this suggestion, enabling them to implement the new event.

[0073] This system allows users to plan new events quickly and effectively, improving participant satisfaction and streamlining operations.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user uses a device to input information about past events. This includes the event name, date and time, age range of participants, and feedback. This data is entered into a form on the device. When the user presses the "Submit" button, the input is converted into a digital data format for transmission to the server.

[0077] Step 2:

[0078] The server receives data sent from the terminal. The received data is first categorized and divided into items such as event name, date and time, age group, and feedback. In this process, data analysis libraries (e.g., Pandas) are used to organize the data. After analysis, the server converts the data into an input format for the generating AI model.

[0079] Step 3:

[0080] The server generates and inputs a prompt message to the AI ​​model. This prompt message includes instructions such as "Generate new suggestions based on past event data." The AI ​​model uses natural language processing techniques to generate new event suggestions based on the input prompt message and data. The output suggestions are temporarily stored on the server as text data.

[0081] Step 4:

[0082] The generated event proposals are transferred from the server to the terminal. The terminal visually displays the received proposals to the user. HTML and CSS are used to ensure that the proposals are displayed in a clear and easy-to-understand format for the user. The user can review the proposals on the terminal and read the specific details.

[0083] Step 5:

[0084] Users provide feedback on the displayed suggestions. They use a feedback form on their device to input information such as the suitability of the suggestion and suggestions for improvement. When the user presses the "Submit Feedback" button, the information is sent to the server. This feedback provides the server with data to improve the accuracy of future suggestion generation.

[0085] (Application Example 1)

[0086] 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."

[0087] In event planning for physical stores, it is crucial to streamline planning operations and improve participant satisfaction by automatically generating efficient and innovative proposals based on past event information and participant characteristics, and evaluating the effectiveness of these proposals. Traditional methods have not adequately utilized information, making it difficult to break away from monotonous event planning.

[0088] 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.

[0089] In this invention, the server includes a device for receiving past event information, a device for evaluating the effectiveness of generated event proposals, and a device for adjusting proposals based on user characteristics. This enables the efficient generation of new event plans for physical stores and allows for optimal event proposals tailored to the needs of participants.

[0090] "Past event information" is a general term for data related to events held in the past, and includes information such as the event content, participant characteristics, venue, and dates.

[0091] "Device" refers to a hardware or software component for performing a specific function, and in this invention, it refers to a device for receiving, analyzing, and displaying information.

[0092] A "generation mechanism" is a part of a system that uses algorithms and AI technology to create new event suggestions based on input data.

[0093] "User characteristics" refer to attribute information about event participants, including parameters such as age group, hobbies, interests, and regional background.

[0094] "Adjusting the proposal" refers to the process of optimizing the generated event plan by taking into account user characteristics and past feedback.

[0095] "Feedback" refers to evaluations and opinions provided by users, and is used to improve generated proposals and enhance the accuracy of future proposals.

[0096] The "function to optimize event planning proposals for administrators" is a function that assists those who manage physical stores in coordinating and planning the most suitable event content based on user needs and past event results.

[0097] In this embodiment, a server, terminal, and generation engine work together to form a system that supports event planning at physical stores. The server first receives past event information sent from the terminal. This includes data such as the event content, participant characteristics, date and time, and location. Based on this data, the server uses the generation engine to generate new event proposals. This generation engine employs Python algorithms and AI technology to automatically create event planning proposals.

[0098] Users can receive and review event proposals generated from the server using devices such as smartphones and tablets. Providing feedback on the proposals helps improve the accuracy of future proposals. This feedback, including user ratings and comments, is sent to the server and incorporated into future event proposals.

[0099] As a concrete example, a certain cafe sends information from a terminal to a server stating, "We held a picture book reading event last Christmas, and the participants were very satisfied." The server analyzes this information, and a generation engine generates new project proposals, such as "a picture book exhibition in collaboration with local authors," and proposes them to the store manager.

[0100] An example of a prompt to input into the generating AI model is, "Based on information from past 'AA events,' please propose a new event plan." This makes it possible to generate more specific and practical event plans.

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The device collects past event information and sends it to the server. It takes information such as the content of past events, participant characteristics, date, time, and location as input. The device then compiles this information into JSON format and sends it to the server via an HTTP request. The output is a confirmation response indicating that the information was received correctly by the server.

[0104] Step 2:

[0105] The server analyzes the event information received from the terminal and inputs it into the generation engine. The input is event information from the terminal, and the server uses this information to convert it into a format suitable for the generation engine. By performing data analysis, the server prepares to organize the event type and participant characteristics. The output is the correct data input to the generation engine.

[0106] Step 3:

[0107] The generation engine generates new event proposals based on the data. The input is organized event data provided by the server. The generation engine uses an AI algorithm to create new event plans, taking into account past data and participant characteristics. The output is the proposed content to be sent to the server.

[0108] Step 4:

[0109] The server receives event proposals from the generation engine and sends them to the terminal. The input is the proposal from the generation engine, and the server converts this content into a format that can be displayed on the terminal. The output is the event proposal received by the terminal.

[0110] Step 5:

[0111] Users review proposed event plans and send feedback to the server via their terminal as needed. The input is the proposal from the server, which the user evaluates and creates feedback. The output is the feedback sent back to the server. This feedback helps improve the system.

[0112] 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.

[0113] This invention combines an emotion engine with an event content suggestion system to enable dynamic suggestions that take into account the user's emotional state. First, the user inputs past event data and their own basic emotional data via a terminal. The terminal then sends this data to the server.

[0114] The server generates event suggestions using a generation engine based on the received event data, and simultaneously analyzes the user's emotional state using an emotion engine. By considering this emotion data and past event data, the suggestions are adjusted to be more meaningful and interesting to the user.

[0115] The generated suggestions are further customized based on the emotional data recognized by the emotion engine and sent from the server to the terminal as final suggestions. This allows the user to intuitively understand whether the event content is appropriate for their emotions.

[0116] For example, if a user provides emotional data indicating they have been feeling stressed recently, the server will take this into consideration and suggest activities specifically focused on relaxation. Conversely, if the user indicates positive emotions, the server will suggest activities that include more challenging and creative pursuits.

[0117] This system makes it possible to offer more personalized experiences by suggesting events and activities that go beyond simply providing information, and instead directly appeal to the emotions of participants.

[0118] The following describes the processing flow.

[0119] Step 1:

[0120] Users input past event data and self-assessed emotional information via their device. This emotional information includes moods during specific periods and emotional responses to recent events.

[0121] Step 2:

[0122] The terminal sends the input data to the server in a standardized format. A brief check is performed before transmission to ensure there are no data errors.

[0123] Step 3:

[0124] The server analyzes the received event data and uses a generation engine to generate basic event suggestions based on past trends and evaluations.

[0125] Step 4:

[0126] The emotion engine analyzes the user's emotional information and evaluates their current emotional state. This evaluation result has characteristics that influence the generated event suggestions.

[0127] Step 5:

[0128] The server integrates the results from the generation engine and the emotion engine, makes adjustments to adapt to the user's emotional state, and derives the most suitable event suggestions.

[0129] Step 6:

[0130] The server sends a coordinated event proposal to the terminal. This proposal includes information on the reasons for the recommendation and the expected emotional benefits for participants.

[0131] Step 7:

[0132] The device presents suggestions received from the server to the user, clearly displaying their content and reasons. The user can then provide feedback based on their emotional response.

[0133] (Example 2)

[0134] 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".

[0135] Conventional event suggestion systems often fail to consider the user's emotional state, resulting in suggestions that are not optimal for the user. Furthermore, if the suggested results do not meet the user's expectations, the user experience suffers.

[0136] 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.

[0137] In this invention, the server includes means for receiving past event data and sentiment data, means for generating event suggestions using a generation engine, and means for evaluating the user's emotional state using a sentiment analysis engine. This enables personalized event suggestions that take the user's emotional state into consideration.

[0138] "Past event data" refers to information about events and activities that a user has participated in in the past, including the date, time, location, and details of the activities.

[0139] "Emotional data" refers to information that indicates a user's mood and emotional state, expressing emotional conditions such as positive, negative, relaxed, and stressed.

[0140] A "generative engine" is an algorithm or system that generates appropriate event suggestions based on received input data, and utilizes machine learning and inference techniques.

[0141] A "sentiment analysis engine" is a system that analyzes emotional data provided by the user and evaluates and classifies the user's current emotional state, using natural language processing technology.

[0142] "Means for adjusting proposals" refers to a system that modifies or changes generated event proposals to match the user's emotional state and characteristics.

[0143] "User characteristics" refer to the individual attributes, hobbies, interests, and past behavioral history of users, and are used to optimize suggestions.

[0144] This system is designed to provide personalized event suggestions based on the user's emotional state. Users input past event data and emotional data via a terminal. The terminal then sends this data to a server.

[0145] When the server receives data, it uses a generation engine to create event suggestions tailored to the user. The generation engine utilizes a machine learning platform, specifically applying technologies from previous cloud platforms. Simultaneously, the server uses a sentiment analysis engine to analyze the emotional data entered by the user. For example, it leverages natural language processing techniques to analyze emotional elements within the text and classify the user's emotional state based on that analysis.

[0146] The suggestions generated by the generation engine are further refined based on the sentiment analysis results. In this refinement, if the user is in a state of emotional state where they desire relaxation, suggestions specifically focused on relaxation will be prioritized. Conversely, if the user is in an emotional state where they desire challenging activities, events that allow them to learn new skills will be suggested.

[0147] The completed proposal is sent from the server to the terminal and displayed to the user. The user can review the received proposal and participate in events that match their interests and current feelings.

[0148] For example, if a user inputs a feeling like "I want to relax lately," the system will suggest options such as yoga classes or relaxation workshops. An example of a prompt for the generative AI model might be, "What kind of event are you looking for? Are you looking for relaxation or adventure?" This allows for suggestions that meet the user's expectations.

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] Users input past event data and emotional data through their device. Specifically, they enter details of events they attended (e.g., event name, date, time, location) and their mood or emotional state (e.g., "I want to relax," "I'm craving stimulation") on the input screen. The device collects this input data and sends it to the server as data packets.

[0152] Step 2:

[0153] The server processes data packets received from the terminal and inputs them into the generation engine. The generation engine analyzes this data and suggests highly relevant events based on trends from past events. Data processing includes calculating event similarity and weighting past participation history. The output is multiple event suggestions.

[0154] Step 3:

[0155] The server evaluates the user's emotional data using an emotion analysis engine. This step employs natural language processing algorithms to extract emotions from text data and classify them into positive, negative, or neutral states. The output is result data indicating the user's emotional state.

[0156] Step 4:

[0157] The server integrates the generated event suggestions with the sentiment analysis results to provide suggestions optimized for the user's emotions. The suggestions are adjusted to the user's current emotional state; for example, events that are effective in reducing stress or events that include challenging activities are selected. The output is the optimized event suggestions.

[0158] Step 5:

[0159] The server sends the final proposal to the terminal and displays it to the user. The user can review the details of the proposed events and decide whether to participate in events that align with their interests and feelings. The input here is the final proposal, and the output is the presentation of event information to the user.

[0160] (Application Example 2)

[0161] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0162] Conventional event suggestion systems have a problem in that they do not adequately consider the user's emotional state, and therefore the suggested content may not be suitable for the user's current situation. Furthermore, especially in physical stores, providing services that respond to the customer's emotional state in real time is a challenge.

[0163] 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.

[0164] In this invention, the server includes a component that receives past event data, a component that combines emotion recognition technology for analyzing emotional states, and a component that optimizes the information displayed on the device based on the customer's emotions. This enables personalized suggestions that are appropriate to the user's emotional state.

[0165] "Past event data" refers to information about events and activities that the user has previously participated in.

[0166] "Proposal efficiency" refers to the degree to which the generated proposals align with the user's needs and emotions.

[0167] "Participant characteristics" refer to the individual characteristics of each user, such as their age, gender, and hobbies.

[0168] A "generative mechanism" refers to an algorithm or platform used to generate proposals.

[0169] "Emotion recognition technology" refers to technology that analyzes a user's facial expressions and voice to determine their emotional state.

[0170] "Information displayed on the device" refers to the content of suggestions provided to the user through devices such as smart glasses.

[0171] The system for carrying out this invention consists of using smart glasses as hardware and implementing emotion recognition and suggestion generation software. The smart glasses are equipped with a camera to capture the user's facial expressions and emotion recognition technology to analyze emotions. This technology can be implemented, for example, using the Affectiva SDK.

[0172] The server uses facial expression data received from the smart glasses to evaluate the user's emotional state in real time. This emotional data, along with the user's past event data, is sent to the server, and a generative AI model generates suggestions. For example, OpenAI's GPT series is used for this model. The server optimizes the generated suggestions to match the user's emotions and displays them on the smart glasses. This information includes product and event information relevant to the user at that time.

[0173] For example, if a customer feels stressed upon entering a store, the server will generate suggestions for relaxation products and services. Conversely, if positive emotions are detected, recommendations for products that promote creative activities will be made.

[0174] The following prompt statements are used when utilizing generative AI models.

[0175] Emotional state: Stress

[0176] Past purchase history: Scented candles, premium tea

[0177] Please generate recommendations.

[0178] Emotional state: positive

[0179] Past purchase history: DIY kits, handmade accessories

[0180] Please generate recommendations.

[0181] This invention makes it possible to provide emotion-based, real-time, personalized experiences even in physical stores.

[0182] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0183] Step 1:

[0184] The device uses the camera on smart glasses to capture the user's face and collect facial expression data in real time. This data is analyzed using emotion recognition technology to determine the user's emotional state (e.g., stressed, positive). The input is facial expression image data, and the output is the analyzed emotional state.

[0185] Step 2:

[0186] The user provides information about past events on their device. This includes a history of past purchases and events attended. This data is sent directly to the server and used for suggestion generation. The input is the user-provided historical data, and the output is structured event data.

[0187] Step 3:

[0188] The server integrates the emotional state and past event data received from the terminal. Based on this, it creates prompt sentences for the generative AI model to generate the optimal suggestion. The input is the emotional state and past event data, and the output is the prompt sentence. An example of a prompt sentence is, "Emotional state: Stress, Past purchase history: Aromatherapy candle, Premium tea."

[0189] Step 4:

[0190] The server uses a generative AI model to analyze the prompt text and generate personalized suggestions for the user. This process utilizes data processing and natural language generation technologies. The input is the prompt text, and the output is the generated suggestions. These suggestions may include relaxation products or event announcements.

[0191] Step 5:

[0192] The server sends the generated suggestions to the terminal and displays them on the smart glasses' screen. This allows the user to directly access the suggested items and make selections or purchases on the spot. The input is the generated suggestions, and the output is the visualized information.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] [Second Embodiment]

[0197] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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).

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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".

[0209] This invention automates the proposal of event content by appropriately coordinating the server, terminal, and generation engine of the proposed system. In this system, the user inputs past event data using a terminal and sends it to the server. The server receives this data and, using the generation engine, generates appropriate event proposals considering participant characteristics and past data.

[0210] The generated suggestions are sent from the server to the terminal and displayed to the user. The user reviews the suggested events and provides feedback as needed. This allows the system to incorporate user feedback and improve the accuracy of future suggestions.

[0211] As a concrete example, suppose a user inputs data stating, "I previously held cooking classes and workshops at local events, and the participants were mainly in their 30s to 50s." The server analyzes this information and, through its generation engine, suggests a "new workshop combining healthy cooking and community interaction." The user can then receive this suggestion, review its content, and provide feedback.

[0212] This invention makes it possible to quickly and effectively generate new ideas in event planning, break away from monotonous events, and achieve high participant satisfaction.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] Users input past data related to the event (e.g., event name, participant characteristics, satisfaction level, etc.) through the terminal interface.

[0216] Step 2:

[0217] The terminal formats the input data and sends it to the server. During transmission, it verifies data integrity as needed.

[0218] Step 3:

[0219] The server performs data analysis based on the received data. Specifically, it checks the type of event, the characteristics of the participants, and past satisfaction levels to understand the needs of the event.

[0220] Step 4:

[0221] The server uses the data analysis results to provide information to the generation engine and instructs it to generate event proposals. This generation engine has an algorithm that constructs the content of new events.

[0222] Step 5:

[0223] The generation engine generates several event suggestions based on historical data and market trends. It returns these suggested candidates to the server.

[0224] Step 6:

[0225] The server receives the generated event proposals and selects the most suitable one. If necessary, it adjusts multiple proposals to meet the user's needs.

[0226] Step 7:

[0227] The server sends the selected event proposals to the terminal.

[0228] Step 8:

[0229] The terminal receives proposals from the server and displays them in a user-friendly format. It also displays information explaining the details and benefits of the proposals.

[0230] Step 9:

[0231] Users review the proposals and provide feedback as needed. This feedback helps improve the accuracy of future proposals.

[0232] (Example 1)

[0233] 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."

[0234] Traditional event planning methods struggled to generate new ideas and quickly provide optimal proposals tailored to participant characteristics, resulting in a stagnation of events. Furthermore, participant feedback was not adequately utilized, hindering improvements in future event proposals. Additionally, the lack of a system to efficiently manage these processes created a need for increased efficiency in event planning.

[0235] 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.

[0236] In this invention, the server includes means for acquiring information about past events, means for inputting prompt sentences into a generation AI model to generate suggestions, and means for transferring the generated suggestion content to a terminal. This makes it possible to quickly and effectively create new event suggestions tailored to participant characteristics and to improve the accuracy of suggestions for future events by incorporating user feedback.

[0237] "Means for obtaining information on past events" refers to devices or software that have the function of collecting data such as the content, date and time, participant characteristics, and participant feedback of past events.

[0238] "Means for verifying generated proposals" refers to a process or system for evaluating the effectiveness and appropriateness of event proposals created by a generative AI model.

[0239] "Means of adjusting proposals based on participant characteristics" refers to methods or techniques for optimizing proposals by taking into account participants' age, interests, past participation history, etc.

[0240] "Means using a generation processing device that automatically generates event content" refers to a device or system that uses AI models or algorithms to automatically create event proposals.

[0241] "Means for transferring generated proposal content to a terminal" refers to a technology or device for transferring event proposals generated from a server to a terminal used by a user via digital communication.

[0242] "A means of inputting prompt sentences into a generative AI model to generate suggestions" refers to a process that uses natural language processing technology to input text containing specific instructions (prompt sentences) into an AI model and creates event suggestions based on that input.

[0243] This invention relates to a system for automating the generation of new proposals in event planning. The system primarily involves the collaboration of a server, terminals, and a generation engine to generate new proposals based on past event data.

[0244] The user first uses a terminal to enter information about past events. This information includes the type of event, the age range of participants, and feedback from past participants. This data is entered on the terminal and sent to the server by executing the data transmission command.

[0245] The server analyzes the received data. This analysis can utilize data analysis libraries such as Python or R. Based on the analyzed data, the server generates new event suggestions using a generative AI model (e.g., GPT-4). During this process, prompts are input to the generation engine, which then returns appropriate suggestions.

[0246] The generated suggestions are transferred from the server to the terminal and displayed visually to the user on the terminal. The user reviews the displayed suggestions and provides feedback on their satisfaction level and areas for improvement. This feedback is sent back to the server and used to improve future suggestions.

[0247] As a concrete example, consider a scenario where a user inputs the following prompt into the generation engine: "I previously held cooking classes and workshops for participants aged 30-50. Please suggest ideas for the next event. I would like suggestions that consider new elements and combinations with other activities." Based on this prompt, the AI ​​model suggests "a new workshop combining healthy cooking and community interaction," and the server forwards this suggestion to the user's device. The user receives and reviews this suggestion, enabling them to implement the new event.

[0248] This system allows users to plan new events quickly and effectively, improving participant satisfaction and streamlining operations.

[0249] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0250] Step 1:

[0251] The user uses a device to input information about past events. This includes the event name, date and time, age range of participants, and feedback. This data is entered into a form on the device. When the user presses the "Submit" button, the input is converted into a digital data format for transmission to the server.

[0252] Step 2:

[0253] The server receives data sent from the terminal. The received data is first categorized and divided into items such as event name, date and time, age group, and feedback. In this process, data analysis libraries (e.g., Pandas) are used to organize the data. After analysis, the server converts the data into an input format for the generating AI model.

[0254] Step 3:

[0255] The server generates and inputs a prompt message to the AI ​​model. This prompt message includes instructions such as "Generate new suggestions based on past event data." The AI ​​model uses natural language processing techniques to generate new event suggestions based on the input prompt message and data. The output suggestions are temporarily stored on the server as text data.

[0256] Step 4:

[0257] The generated event proposals are transferred from the server to the terminal. The terminal visually displays the received proposals to the user. HTML and CSS are used to ensure that the proposals are displayed in a clear and easy-to-understand format for the user. The user can review the proposals on the terminal and read the specific details.

[0258] Step 5:

[0259] Users provide feedback on the displayed suggestions. They use a feedback form on their device to input information such as the suitability of the suggestion and suggestions for improvement. When the user presses the "Submit Feedback" button, the information is sent to the server. This feedback provides the server with data to improve the accuracy of future suggestion generation.

[0260] (Application Example 1)

[0261] 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."

[0262] In event planning for physical stores, it is crucial to streamline planning operations and improve participant satisfaction by automatically generating efficient and innovative proposals based on past event information and participant characteristics, and evaluating the effectiveness of these proposals. Traditional methods have not adequately utilized information, making it difficult to break away from monotonous event planning.

[0263] 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.

[0264] In this invention, the server includes a device for receiving past event information, a device for evaluating the effectiveness of generated event proposals, and a device for adjusting proposals based on user characteristics. This enables the efficient generation of new event plans for physical stores and allows for optimal event proposals tailored to the needs of participants.

[0265] "Past event information" is a general term for data related to events held in the past, and includes information such as the event content, participant characteristics, venue, and dates.

[0266] "Device" refers to a hardware or software component for performing a specific function, and in this invention, it refers to a device for receiving, analyzing, and displaying information.

[0267] A "generation mechanism" is a part of a system that uses algorithms and AI technology to create new event suggestions based on input data.

[0268] "User characteristics" refer to attribute information about event participants, including parameters such as age group, hobbies, interests, and regional background.

[0269] "Adjusting the proposal" refers to the process of optimizing the generated event plan by taking into account user characteristics and past feedback.

[0270] "Feedback" refers to evaluations and opinions provided by users, and is used to improve generated proposals and enhance the accuracy of future proposals.

[0271] The "function to optimize event planning proposals for administrators" is a function that assists those who manage physical stores in coordinating and planning the most suitable event content based on user needs and past event results.

[0272] In this embodiment, a server, terminal, and generation engine work together to form a system that supports event planning at physical stores. The server first receives past event information sent from the terminal. This includes data such as the event content, participant characteristics, date and time, and location. Based on this data, the server uses the generation engine to generate new event proposals. This generation engine employs Python algorithms and AI technology to automatically create event planning proposals.

[0273] Users can receive and review event proposals generated from the server using devices such as smartphones and tablets. Providing feedback on the proposals helps improve the accuracy of future proposals. This feedback, including user ratings and comments, is sent to the server and incorporated into future event proposals.

[0274] As a concrete example, a certain cafe sends information from a terminal to a server stating, "We held a picture book reading event last Christmas, and the participants were very satisfied." The server analyzes this information, and a generation engine generates new project proposals, such as "a picture book exhibition in collaboration with local authors," and proposes them to the store manager.

[0275] An example of a prompt to input into the generating AI model is, "Based on information from past 'AA events,' please propose a new event plan." This makes it possible to generate more specific and practical event plans.

[0276] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0277] Step 1:

[0278] The terminal collects past event information and sends it to the server. Information such as the content of past events, participant characteristics, date and time of the event, and location is input as the input. The terminal summarizes this information in JSON format and sends it to the server via an HTTP request. The output is a confirmation response indicating that the information has been accurately received by the server.

[0279] Step 2:

[0280] The server analyzes the event information received from the terminal and inputs it into the generation engine. The input is the event information from the terminal, and the server uses this information to convert it into a format suitable for the generation engine. By performing data analysis, preparations are made to organize the types of events and participant characteristics. The output is the correct data input to the generation engine.

[0281] Step 3:

[0282] The generation engine generates a new event proposal based on the data. The input is the organized event data provided by the server. The generation engine uses an AI algorithm to create a new event plan while considering past data and participant characteristics. The output is the content of the proposal to be sent to the server.

[0283] Step 4:

[0284] The server receives the event plan proposed by the generation engine and sends it to the terminal. The input is the content of the proposal from the generation engine, and the server converts this content into a format that can be displayed on the terminal. The output is the event plan received by the terminal.

[0285] Step 5:

[0286] The user checks the proposed event plan and sends feedback to the server through the terminal if necessary. The input is the content of the proposal from the server, and the user evaluates this and creates feedback. The output is the content of the feedback sent back to the server. This feedback helps to improve the system.

[0287] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion specific model 59 and perform specific processing using the user's emotion.

[0288] The present invention enables dynamic proposals considering the user's emotional state by combining an emotion engine with an event content proposal system. First, the user inputs past event data and their own basic emotion data via a terminal. The terminal transmits the data to the server.

[0289] The server generates event proposals using a generation engine based on the received event data, and at the same time analyzes the user's emotional state using an emotion engine. By considering this emotion data and past event data, the proposed content is adjusted so as to be more meaningful and interesting to the user.

[0290] The generated proposal is further customized based on the emotion data recognized by the emotion engine and is transmitted from the server to the terminal as the final proposal. Thereby, the user can intuitively understand whether the content of the event suits their emotion.

[0291] For example, when the user provides emotion data such as "I've been stressed lately", the server takes this into account and proposes event content specialized in relaxation. Also, when the user shows a positive emotion, proposals including more challenging and creative activities are made.

[0292] With this system, proposals for events and activities are not just simple information provision, but by directly appealing to the emotions of the participants, it becomes possible to provide a more personalized experience.

[0293] The processing flow will be described below.

[0294] Step 1:

[0295] Users input past event data and self-assessed emotional information via their device. This emotional information includes moods during specific periods and emotional responses to recent events.

[0296] Step 2:

[0297] The terminal sends the input data to the server in a standardized format. A brief check is performed before transmission to ensure there are no data errors.

[0298] Step 3:

[0299] The server analyzes the received event data and uses a generation engine to generate basic event suggestions based on past trends and evaluations.

[0300] Step 4:

[0301] The emotion engine analyzes the user's emotional information and evaluates their current emotional state. This evaluation result has characteristics that influence the generated event suggestions.

[0302] Step 5:

[0303] The server integrates the results from the generation engine and the emotion engine, makes adjustments to adapt to the user's emotional state, and derives the most suitable event suggestions.

[0304] Step 6:

[0305] The server sends a coordinated event proposal to the terminal. This proposal includes information on the reasons for the recommendation and the expected emotional benefits for participants.

[0306] Step 7:

[0307] The device presents suggestions received from the server to the user, clearly displaying their content and reasons. The user can then provide feedback based on their emotional response.

[0308] (Example 2)

[0309] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0310] In the conventional event proposal system, there is a problem that proposals are made without considering the user's emotional state, so that the optimal proposal for the user is not made. In addition, when the proposal result does not meet the user's expectations, there is also a problem that the user experience deteriorates.

[0311] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0312] In this invention, the server includes means for receiving past event data and emotion data, means for generating an event proposal using a generation engine, and means for evaluating the user's emotional state using an emotion analysis engine. Thereby, it becomes possible to make a personalized event proposal considering the user's emotional state.

[0313] The "past event data" is information about events and activities that the user has participated in so far, and includes the date and time, location, activity content, and the like.

[0314] The "emotion data" is information indicating the user's mood and emotional state, and represents emotional states such as positive, negative, relaxed, and stressed.

[0315] The "generation engine" is an algorithm or system that generates an appropriate event proposal based on the received input data, and uses machine learning and inference techniques.

[0316] A "sentiment analysis engine" is a system that analyzes emotional data provided by the user and evaluates and classifies the user's current emotional state, using natural language processing technology.

[0317] "Means for adjusting proposals" refers to a system that modifies or changes generated event proposals to match the user's emotional state and characteristics.

[0318] "User characteristics" refer to the individual attributes, hobbies, interests, and past behavioral history of users, and are used to optimize suggestions.

[0319] This system is designed to provide personalized event suggestions based on the user's emotional state. Users input past event data and emotional data via a terminal. The terminal then sends this data to a server.

[0320] When the server receives data, it uses a generation engine to create event suggestions tailored to the user. The generation engine utilizes a machine learning platform, specifically applying technologies from previous cloud platforms. Simultaneously, the server uses a sentiment analysis engine to analyze the emotional data entered by the user. For example, it leverages natural language processing techniques to analyze emotional elements within the text and classify the user's emotional state based on that analysis.

[0321] The suggestions generated by the generation engine are further refined based on the sentiment analysis results. In this refinement, if the user is in a state of emotional state where they desire relaxation, suggestions specifically focused on relaxation will be prioritized. Conversely, if the user is in an emotional state where they desire challenging activities, events that allow them to learn new skills will be suggested.

[0322] The completed proposal is sent from the server to the terminal and displayed to the user. The user can review the received proposal and participate in events that match their interests and current feelings.

[0323] For example, if a user inputs a feeling like "I want to relax lately," the system will suggest options such as yoga classes or relaxation workshops. An example of a prompt for the generative AI model might be, "What kind of event are you looking for? Are you looking for relaxation or adventure?" This allows for suggestions that meet the user's expectations.

[0324] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0325] Step 1:

[0326] Users input past event data and emotional data through their device. Specifically, they enter details of events they attended (e.g., event name, date, time, location) and their mood or emotional state (e.g., "I want to relax," "I'm craving stimulation") on the input screen. The device collects this input data and sends it to the server as data packets.

[0327] Step 2:

[0328] The server processes data packets received from the terminal and inputs them into the generation engine. The generation engine analyzes this data and suggests highly relevant events based on trends from past events. Data processing includes calculating event similarity and weighting past participation history. The output is multiple event suggestions.

[0329] Step 3:

[0330] The server evaluates the user's emotional data using an emotion analysis engine. This step employs natural language processing algorithms to extract emotions from text data and classify them into positive, negative, or neutral states. The output is result data indicating the user's emotional state.

[0331] Step 4:

[0332] The server integrates the generated event suggestions with the sentiment analysis results to provide suggestions optimized for the user's emotions. The suggestions are adjusted to the user's current emotional state; for example, events that are effective in reducing stress or events that include challenging activities are selected. The output is the optimized event suggestions.

[0333] Step 5:

[0334] The server sends the final proposal to the terminal and displays it to the user. The user can review the details of the proposed events and decide whether to participate in events that align with their interests and feelings. The input here is the final proposal, and the output is the presentation of event information to the user.

[0335] (Application Example 2)

[0336] 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."

[0337] Conventional event suggestion systems have a problem in that they do not adequately consider the user's emotional state, and therefore the suggested content may not be suitable for the user's current situation. Furthermore, especially in physical stores, providing services that respond to the customer's emotional state in real time is a challenge.

[0338] 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.

[0339] In this invention, the server includes a component that receives past event data, a component that combines emotion recognition technology for analyzing emotional states, and a component that optimizes the information displayed on the device based on the customer's emotions. This enables personalized suggestions that are appropriate to the user's emotional state.

[0340] "Past event data" refers to information about events and activities that the user has previously participated in.

[0341] "Proposal efficiency" refers to the degree to which the generated proposals align with the user's needs and emotions.

[0342] "Participant characteristics" refer to the individual characteristics of each user, such as their age, gender, and hobbies.

[0343] A "generative mechanism" refers to an algorithm or platform used to generate proposals.

[0344] "Emotion recognition technology" refers to technology that analyzes a user's facial expressions and voice to determine their emotional state.

[0345] "Information displayed on the device" refers to the content of suggestions provided to the user through devices such as smart glasses.

[0346] The system for carrying out this invention consists of using smart glasses as hardware and implementing emotion recognition and suggestion generation software. The smart glasses are equipped with a camera to capture the user's facial expressions and emotion recognition technology to analyze emotions. This technology can be implemented, for example, using the Affectiva SDK.

[0347] The server uses facial expression data received from the smart glasses to evaluate the user's emotional state in real time. This emotional data, along with the user's past event data, is sent to the server, and a generative AI model generates suggestions. For example, OpenAI's GPT series is used for this model. The server optimizes the generated suggestions to match the user's emotions and displays them on the smart glasses. This information includes product and event information relevant to the user at that time.

[0348] For example, if a customer feels stressed upon entering a store, the server will generate suggestions for relaxation products and services. Conversely, if positive emotions are detected, recommendations for products that promote creative activities will be made.

[0349] The following prompt statements are used when utilizing generative AI models.

[0350] Emotional state: Stress

[0351] Past purchase history: Scented candles, premium tea

[0352] Please generate recommendations.

[0353] Emotional state: positive

[0354] Past purchase history: DIY kits, handmade accessories

[0355] Please generate recommendations.

[0356] This invention makes it possible to provide emotion-based, real-time, personalized experiences even in physical stores.

[0357] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0358] Step 1:

[0359] The device uses the camera on smart glasses to capture the user's face and collect facial expression data in real time. This data is analyzed using emotion recognition technology to determine the user's emotional state (e.g., stressed, positive). The input is facial expression image data, and the output is the analyzed emotional state.

[0360] Step 2:

[0361] The user provides information about past events on their device. This includes a history of past purchases and events attended. This data is sent directly to the server and used for suggestion generation. The input is the user-provided historical data, and the output is structured event data.

[0362] Step 3:

[0363] The server integrates the emotional state and past event data received from the terminal. Based on this, it creates prompt sentences for the generative AI model to generate the optimal suggestion. The input is the emotional state and past event data, and the output is the prompt sentence. An example of a prompt sentence is, "Emotional state: Stress, Past purchase history: Aromatherapy candle, Premium tea."

[0364] Step 4:

[0365] The server uses a generative AI model to analyze the prompt text and generate personalized suggestions for the user. This process utilizes data processing and natural language generation technologies. The input is the prompt text, and the output is the generated suggestions. These suggestions may include relaxation products or event announcements.

[0366] Step 5:

[0367] The server sends the generated suggestions to the terminal and displays them on the smart glasses' screen. This allows the user to directly access the suggested items and make selections or purchases on the spot. The input is the generated suggestions, and the output is the visualized information.

[0368] 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.

[0369] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0370] 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.

[0371] [Third Embodiment]

[0372] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0373] 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.

[0374] 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).

[0375] 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.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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".

[0384] This invention automates the proposal of event content by appropriately coordinating the server, terminal, and generation engine of the proposed system. In this system, the user inputs past event data using a terminal and sends it to the server. The server receives this data and, using the generation engine, generates appropriate event proposals considering participant characteristics and past data.

[0385] The generated suggestions are sent from the server to the terminal and displayed to the user. The user reviews the suggested events and provides feedback as needed. This allows the system to incorporate user feedback and improve the accuracy of future suggestions.

[0386] As a concrete example, suppose a user inputs data stating, "I previously held cooking classes and workshops at local events, and the participants were mainly in their 30s to 50s." The server analyzes this information and, through its generation engine, suggests a "new workshop combining healthy cooking and community interaction." The user can then receive this suggestion, review its content, and provide feedback.

[0387] This invention makes it possible to quickly and effectively generate new ideas in event planning, break away from monotonous events, and achieve high participant satisfaction.

[0388] The following describes the processing flow.

[0389] Step 1:

[0390] Users input past data related to the event (e.g., event name, participant characteristics, satisfaction level, etc.) through the terminal interface.

[0391] Step 2:

[0392] The terminal formats the input data and sends it to the server. During transmission, it verifies data integrity as needed.

[0393] Step 3:

[0394] The server performs data analysis based on the received data. Specifically, it checks the type of event, the characteristics of the participants, and past satisfaction levels to understand the needs of the event.

[0395] Step 4:

[0396] The server uses the data analysis results to provide information to the generation engine and instructs it to generate event proposals. This generation engine has an algorithm that constructs the content of new events.

[0397] Step 5:

[0398] The generation engine generates several event suggestions based on historical data and market trends. It returns these suggested candidates to the server.

[0399] Step 6:

[0400] The server receives the generated event proposals and selects the most suitable one. If necessary, it adjusts multiple proposals to meet the user's needs.

[0401] Step 7:

[0402] The server sends the selected event proposals to the terminal.

[0403] Step 8:

[0404] The terminal receives proposals from the server and displays them in a user-friendly format. It also displays information explaining the details and benefits of the proposals.

[0405] Step 9:

[0406] Users review the proposals and provide feedback as needed. This feedback helps improve the accuracy of future proposals.

[0407] (Example 1)

[0408] 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."

[0409] Traditional event planning methods struggled to generate new ideas and quickly provide optimal proposals tailored to participant characteristics, resulting in a stagnation of events. Furthermore, participant feedback was not adequately utilized, hindering improvements in future event proposals. Additionally, the lack of a system to efficiently manage these processes created a need for increased efficiency in event planning.

[0410] 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.

[0411] In this invention, the server includes means for acquiring information about past events, means for inputting prompt sentences into a generation AI model to generate suggestions, and means for transferring the generated suggestion content to a terminal. This makes it possible to quickly and effectively create new event suggestions tailored to participant characteristics and to improve the accuracy of suggestions for future events by incorporating user feedback.

[0412] "Means for obtaining information on past events" refers to devices or software that have the function of collecting data such as the content, date and time, participant characteristics, and participant feedback of past events.

[0413] "Means for verifying generated proposals" refers to a process or system for evaluating the effectiveness and appropriateness of event proposals created by a generative AI model.

[0414] "Means of adjusting proposals based on participant characteristics" refers to methods or techniques for optimizing proposals by taking into account participants' age, interests, past participation history, etc.

[0415] "Means using a generation processing device that automatically generates event content" refers to a device or system that uses AI models or algorithms to automatically create event proposals.

[0416] "Means for transferring generated proposal content to a terminal" refers to a technology or device for transferring event proposals generated from a server to a terminal used by a user via digital communication.

[0417] "A means of inputting prompt sentences into a generative AI model to generate suggestions" refers to a process that uses natural language processing technology to input text containing specific instructions (prompt sentences) into an AI model and creates event suggestions based on that input.

[0418] This invention relates to a system for automating the generation of new proposals in event planning. The system primarily involves the collaboration of a server, terminals, and a generation engine to generate new proposals based on past event data.

[0419] The user first uses a terminal to enter information about past events. This information includes the type of event, the age range of participants, and feedback from past participants. This data is entered on the terminal and sent to the server by executing the data transmission command.

[0420] The server analyzes the received data. This analysis can utilize data analysis libraries such as Python or R. Based on the analyzed data, the server generates new event suggestions using a generative AI model (e.g., GPT-4). During this process, prompts are input to the generation engine, which then returns appropriate suggestions.

[0421] The generated suggestions are transferred from the server to the terminal and displayed visually to the user on the terminal. The user reviews the displayed suggestions and provides feedback on their satisfaction level and areas for improvement. This feedback is sent back to the server and used to improve future suggestions.

[0422] As a concrete example, consider a scenario where a user inputs the following prompt into the generation engine: "I previously held cooking classes and workshops for participants aged 30-50. Please suggest ideas for the next event. I would like suggestions that consider new elements and combinations with other activities." Based on this prompt, the AI ​​model suggests "a new workshop combining healthy cooking and community interaction," and the server forwards this suggestion to the user's device. The user receives and reviews this suggestion, enabling them to implement the new event.

[0423] This system allows users to plan new events quickly and effectively, improving participant satisfaction and streamlining operations.

[0424] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0425] Step 1:

[0426] The user uses a device to input information about past events. This includes the event name, date and time, age range of participants, and feedback. This data is entered into a form on the device. When the user presses the "Submit" button, the input is converted into a digital data format for transmission to the server.

[0427] Step 2:

[0428] The server receives data sent from the terminal. The received data is first categorized and divided into items such as event name, date and time, age group, and feedback. In this process, data analysis libraries (e.g., Pandas) are used to organize the data. After analysis, the server converts the data into an input format for the generating AI model.

[0429] Step 3:

[0430] The server generates and inputs a prompt message to the AI ​​model. This prompt message includes instructions such as "Generate new suggestions based on past event data." The AI ​​model uses natural language processing techniques to generate new event suggestions based on the input prompt message and data. The output suggestions are temporarily stored on the server as text data.

[0431] Step 4:

[0432] The generated event proposals are transferred from the server to the terminal. The terminal visually displays the received proposals to the user. HTML and CSS are used to ensure that the proposals are displayed in a clear and easy-to-understand format for the user. The user can review the proposals on the terminal and read the specific details.

[0433] Step 5:

[0434] Users provide feedback on the displayed suggestions. They use a feedback form on their device to input information such as the suitability of the suggestion and suggestions for improvement. When the user presses the "Submit Feedback" button, the information is sent to the server. This feedback provides the server with data to improve the accuracy of future suggestion generation.

[0435] (Application Example 1)

[0436] 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."

[0437] In event planning for physical stores, it is crucial to streamline planning operations and improve participant satisfaction by automatically generating efficient and innovative proposals based on past event information and participant characteristics, and evaluating the effectiveness of these proposals. Traditional methods have not adequately utilized information, making it difficult to break away from monotonous event planning.

[0438] 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.

[0439] In this invention, the server includes a device for receiving past event information, a device for evaluating the effectiveness of generated event proposals, and a device for adjusting proposals based on user characteristics. This enables the efficient generation of new event plans for physical stores and allows for optimal event proposals tailored to the needs of participants.

[0440] "Past event information" is a general term for data related to events held in the past, and includes information such as the event content, participant characteristics, venue, and dates.

[0441] "Device" refers to a hardware or software component for performing a specific function, and in this invention, it refers to a device for receiving, analyzing, and displaying information.

[0442] A "generation mechanism" is a part of a system that uses algorithms and AI technology to create new event suggestions based on input data.

[0443] "User characteristics" refer to attribute information about event participants, including parameters such as age group, hobbies, interests, and regional background.

[0444] "Adjusting the proposal" refers to the process of optimizing the generated event plan by taking into account user characteristics and past feedback.

[0445] "Feedback" refers to evaluations and opinions provided by users, and is used to improve generated proposals and enhance the accuracy of future proposals.

[0446] The "function to optimize event planning proposals for administrators" is a function that assists those who manage physical stores in coordinating and planning the most suitable event content based on user needs and past event results.

[0447] In this embodiment, a server, terminal, and generation engine work together to form a system that supports event planning at physical stores. The server first receives past event information sent from the terminal. This includes data such as the event content, participant characteristics, date and time, and location. Based on this data, the server uses the generation engine to generate new event proposals. This generation engine employs Python algorithms and AI technology to automatically create event planning proposals.

[0448] Users can receive and review event proposals generated from the server using devices such as smartphones and tablets. Providing feedback on the proposals helps improve the accuracy of future proposals. This feedback, including user ratings and comments, is sent to the server and incorporated into future event proposals.

[0449] As a concrete example, a certain cafe sends information from a terminal to a server stating, "We held a picture book reading event last Christmas, and the participants were very satisfied." The server analyzes this information, and a generation engine generates new project proposals, such as "a picture book exhibition in collaboration with local authors," and proposes them to the store manager.

[0450] An example of a prompt to input into the generating AI model is, "Based on information from past 'AA events,' please propose a new event plan." This makes it possible to generate more specific and practical event plans.

[0451] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0452] Step 1:

[0453] The device collects past event information and sends it to the server. It takes information such as the content of past events, participant characteristics, date, time, and location as input. The device then compiles this information into JSON format and sends it to the server via an HTTP request. The output is a confirmation response indicating that the information was received correctly by the server.

[0454] Step 2:

[0455] The server analyzes the event information received from the terminal and inputs it into the generation engine. The input is event information from the terminal, and the server uses this information to convert it into a format suitable for the generation engine. By performing data analysis, the server prepares to organize the event type and participant characteristics. The output is the correct data input to the generation engine.

[0456] Step 3:

[0457] The generation engine generates new event proposals based on the data. The input is organized event data provided by the server. The generation engine uses an AI algorithm to create new event plans, taking into account past data and participant characteristics. The output is the proposed content to be sent to the server.

[0458] Step 4:

[0459] The server receives event proposals from the generation engine and sends them to the terminal. The input is the proposal from the generation engine, and the server converts this content into a format that can be displayed on the terminal. The output is the event proposal received by the terminal.

[0460] Step 5:

[0461] Users review proposed event plans and send feedback to the server via their terminal as needed. The input is the proposal from the server, which the user evaluates and creates feedback. The output is the feedback sent back to the server. This feedback helps improve the system.

[0462] 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.

[0463] This invention combines an emotion engine with an event content suggestion system to enable dynamic suggestions that take into account the user's emotional state. First, the user inputs past event data and their own basic emotional data via a terminal. The terminal then sends this data to the server.

[0464] The server generates event suggestions using a generation engine based on the received event data, and simultaneously analyzes the user's emotional state using an emotion engine. By considering this emotion data and past event data, the suggestions are adjusted to be more meaningful and interesting to the user.

[0465] The generated suggestions are further customized based on the emotional data recognized by the emotion engine and sent from the server to the terminal as final suggestions. This allows the user to intuitively understand whether the event content is appropriate for their emotions.

[0466] For example, if a user provides emotional data indicating they have been feeling stressed recently, the server will take this into consideration and suggest activities specifically focused on relaxation. Conversely, if the user indicates positive emotions, the server will suggest activities that include more challenging and creative pursuits.

[0467] This system makes it possible to offer more personalized experiences by suggesting events and activities that go beyond simply providing information, and instead directly appeal to the emotions of participants.

[0468] The following describes the processing flow.

[0469] Step 1:

[0470] Users input past event data and self-assessed emotional information via their device. This emotional information includes moods during specific periods and emotional responses to recent events.

[0471] Step 2:

[0472] The terminal sends the input data to the server in a standardized format. A brief check is performed before transmission to ensure there are no data errors.

[0473] Step 3:

[0474] The server analyzes the received event data and uses a generation engine to generate basic event suggestions based on past trends and evaluations.

[0475] Step 4:

[0476] The emotion engine analyzes the user's emotional information and evaluates their current emotional state. This evaluation result has characteristics that influence the generated event suggestions.

[0477] Step 5:

[0478] The server integrates the results from the generation engine and the emotion engine, makes adjustments to adapt to the user's emotional state, and derives the most suitable event suggestions.

[0479] Step 6:

[0480] The server sends a coordinated event proposal to the terminal. This proposal includes information on the reasons for the recommendation and the expected emotional benefits for participants.

[0481] Step 7:

[0482] The device presents suggestions received from the server to the user, clearly displaying their content and reasons. The user can then provide feedback based on their emotional response.

[0483] (Example 2)

[0484] 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."

[0485] Conventional event suggestion systems often fail to consider the user's emotional state, resulting in suggestions that are not optimal for the user. Furthermore, if the suggested results do not meet the user's expectations, the user experience suffers.

[0486] 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.

[0487] In this invention, the server includes means for receiving past event data and sentiment data, means for generating event suggestions using a generation engine, and means for evaluating the user's emotional state using a sentiment analysis engine. This enables personalized event suggestions that take the user's emotional state into consideration.

[0488] "Past event data" refers to information about events and activities that a user has participated in in the past, including the date, time, location, and details of the activities.

[0489] "Emotional data" refers to information that indicates a user's mood and emotional state, expressing emotional conditions such as positive, negative, relaxed, and stressed.

[0490] A "generative engine" is an algorithm or system that generates appropriate event suggestions based on received input data, and utilizes machine learning and inference techniques.

[0491] A "sentiment analysis engine" is a system that analyzes emotional data provided by the user and evaluates and classifies the user's current emotional state, using natural language processing technology.

[0492] "Means for adjusting proposals" refers to a system that modifies or changes generated event proposals to match the user's emotional state and characteristics.

[0493] "User characteristics" refer to the individual attributes, hobbies, interests, and past behavioral history of users, and are used to optimize suggestions.

[0494] This system is designed to provide personalized event suggestions based on the user's emotional state. Users input past event data and emotional data via a terminal. The terminal then sends this data to a server.

[0495] When the server receives data, it uses a generation engine to create event suggestions tailored to the user. The generation engine utilizes a machine learning platform, specifically applying technologies from previous cloud platforms. Simultaneously, the server uses a sentiment analysis engine to analyze the emotional data entered by the user. For example, it leverages natural language processing techniques to analyze emotional elements within the text and classify the user's emotional state based on that analysis.

[0496] The suggestions generated by the generation engine are further refined based on the sentiment analysis results. In this refinement, if the user is in a state of emotional state where they desire relaxation, suggestions specifically focused on relaxation will be prioritized. Conversely, if the user is in an emotional state where they desire challenging activities, events that allow them to learn new skills will be suggested.

[0497] The completed proposal is sent from the server to the terminal and displayed to the user. The user can review the received proposal and participate in events that match their interests and current feelings.

[0498] For example, if a user inputs a feeling like "I want to relax lately," the system will suggest options such as yoga classes or relaxation workshops. An example of a prompt for the generative AI model might be, "What kind of event are you looking for? Are you looking for relaxation or adventure?" This allows for suggestions that meet the user's expectations.

[0499] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0500] Step 1:

[0501] Users input past event data and emotional data through their device. Specifically, they enter details of events they attended (e.g., event name, date, time, location) and their mood or emotional state (e.g., "I want to relax," "I'm craving stimulation") on the input screen. The device collects this input data and sends it to the server as data packets.

[0502] Step 2:

[0503] The server processes data packets received from the terminal and inputs them into the generation engine. The generation engine analyzes this data and suggests highly relevant events based on trends from past events. Data processing includes calculating event similarity and weighting past participation history. The output is multiple event suggestions.

[0504] Step 3:

[0505] The server evaluates the user's emotional data using an emotion analysis engine. This step employs natural language processing algorithms to extract emotions from text data and classify them into positive, negative, or neutral states. The output is result data indicating the user's emotional state.

[0506] Step 4:

[0507] The server integrates the generated event suggestions with the sentiment analysis results to provide suggestions optimized for the user's emotions. The suggestions are adjusted to the user's current emotional state; for example, events that are effective in reducing stress or events that include challenging activities are selected. The output is the optimized event suggestions.

[0508] Step 5:

[0509] The server sends the final proposal to the terminal and displays it to the user. The user can review the details of the proposed events and decide whether to participate in events that align with their interests and feelings. The input here is the final proposal, and the output is the presentation of event information to the user.

[0510] (Application Example 2)

[0511] 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."

[0512] Conventional event suggestion systems have a problem in that they do not adequately consider the user's emotional state, and therefore the suggested content may not be suitable for the user's current situation. Furthermore, especially in physical stores, providing services that respond to the customer's emotional state in real time is a challenge.

[0513] 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.

[0514] In this invention, the server includes a component that receives past event data, a component that combines emotion recognition technology for analyzing emotional states, and a component that optimizes the information displayed on the device based on the customer's emotions. This enables personalized suggestions that are appropriate to the user's emotional state.

[0515] "Past event data" refers to information about events and activities that the user has previously participated in.

[0516] "Proposal efficiency" refers to the degree to which the generated proposals align with the user's needs and emotions.

[0517] "Participant characteristics" refer to the individual characteristics of each user, such as their age, gender, and hobbies.

[0518] A "generative mechanism" refers to an algorithm or platform used to generate proposals.

[0519] "Emotion recognition technology" refers to technology that analyzes a user's facial expressions and voice to determine their emotional state.

[0520] "Information displayed on the device" refers to the content of suggestions provided to the user through devices such as smart glasses.

[0521] The system for carrying out this invention consists of using smart glasses as hardware and implementing emotion recognition and suggestion generation software. The smart glasses are equipped with a camera to capture the user's facial expressions and emotion recognition technology to analyze emotions. This technology can be implemented, for example, using the Affectiva SDK.

[0522] The server uses facial expression data received from the smart glasses to evaluate the user's emotional state in real time. This emotional data, along with the user's past event data, is sent to the server, and a generative AI model generates suggestions. For example, OpenAI's GPT series is used for this model. The server optimizes the generated suggestions to match the user's emotions and displays them on the smart glasses. This information includes product and event information relevant to the user at that time.

[0523] For example, if a customer feels stressed upon entering a store, the server will generate suggestions for relaxation products and services. Conversely, if positive emotions are detected, recommendations for products that promote creative activities will be made.

[0524] The following prompt statements are used when utilizing generative AI models.

[0525] Emotional state: Stress

[0526] Past purchase history: Scented candles, premium tea

[0527] Please generate recommendations.

[0528] Emotional state: positive

[0529] Past purchase history: DIY kits, handmade accessories

[0530] Please generate recommendations.

[0531] This invention makes it possible to provide emotion-based, real-time, personalized experiences even in physical stores.

[0532] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0533] Step 1:

[0534] The device uses the camera on smart glasses to capture the user's face and collect facial expression data in real time. This data is analyzed using emotion recognition technology to determine the user's emotional state (e.g., stressed, positive). The input is facial expression image data, and the output is the analyzed emotional state.

[0535] Step 2:

[0536] The user provides information about past events on their device. This includes a history of past purchases and events attended. This data is sent directly to the server and used for suggestion generation. The input is the user-provided historical data, and the output is structured event data.

[0537] Step 3:

[0538] The server integrates the emotional state and past event data received from the terminal. Based on this, it creates prompt sentences for the generative AI model to generate the optimal suggestion. The input is the emotional state and past event data, and the output is the prompt sentence. An example of a prompt sentence is, "Emotional state: Stress, Past purchase history: Aromatherapy candle, Premium tea."

[0539] Step 4:

[0540] The server uses a generative AI model to analyze the prompt text and generate personalized suggestions for the user. This process utilizes data processing and natural language generation technologies. The input is the prompt text, and the output is the generated suggestions. These suggestions may include relaxation products or event announcements.

[0541] Step 5:

[0542] The server sends the generated suggestions to the terminal and displays them on the smart glasses' screen. This allows the user to directly access the suggested items and make selections or purchases on the spot. The input is the generated suggestions, and the output is the visualized information.

[0543] 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.

[0544] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0545] 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.

[0546] [Fourth Embodiment]

[0547] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0548] 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.

[0549] 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).

[0550] 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.

[0551] 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.

[0552] 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).

[0553] 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.

[0554] 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.

[0555] 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.

[0556] 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.

[0557] 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.

[0558] 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.

[0559] 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".

[0560] This invention automates the proposal of event content by appropriately coordinating the server, terminal, and generation engine of the proposed system. In this system, the user inputs past event data using a terminal and sends it to the server. The server receives this data and, using the generation engine, generates appropriate event proposals considering participant characteristics and past data.

[0561] The generated suggestions are sent from the server to the terminal and displayed to the user. The user reviews the suggested events and provides feedback as needed. This allows the system to incorporate user feedback and improve the accuracy of future suggestions.

[0562] As a concrete example, suppose a user inputs data stating, "I previously held cooking classes and workshops at local events, and the participants were mainly in their 30s to 50s." The server analyzes this information and, through its generation engine, suggests a "new workshop combining healthy cooking and community interaction." The user can then receive this suggestion, review its content, and provide feedback.

[0563] This invention makes it possible to quickly and effectively generate new ideas in event planning, break away from monotonous events, and achieve high participant satisfaction.

[0564] The following describes the processing flow.

[0565] Step 1:

[0566] Users input past data related to the event (e.g., event name, participant characteristics, satisfaction level, etc.) through the terminal interface.

[0567] Step 2:

[0568] The terminal formats the input data and sends it to the server. During transmission, it verifies data integrity as needed.

[0569] Step 3:

[0570] The server performs data analysis based on the received data. Specifically, it checks the type of event, the characteristics of the participants, and past satisfaction levels to understand the needs of the event.

[0571] Step 4:

[0572] The server uses the data analysis results to provide information to the generation engine and instructs it to generate event proposals. This generation engine has an algorithm that constructs the content of new events.

[0573] Step 5:

[0574] The generation engine generates several event suggestions based on historical data and market trends. It returns these suggested candidates to the server.

[0575] Step 6:

[0576] The server receives the generated event proposals and selects the most suitable one. If necessary, it adjusts multiple proposals to meet the user's needs.

[0577] Step 7:

[0578] The server sends the selected event proposals to the terminal.

[0579] Step 8:

[0580] The terminal receives proposals from the server and displays them in a user-friendly format. It also displays information explaining the details and benefits of the proposals.

[0581] Step 9:

[0582] Users review the proposals and provide feedback as needed. This feedback helps improve the accuracy of future proposals.

[0583] (Example 1)

[0584] 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".

[0585] Traditional event planning methods struggled to generate new ideas and quickly provide optimal proposals tailored to participant characteristics, resulting in a stagnation of events. Furthermore, participant feedback was not adequately utilized, hindering improvements in future event proposals. Additionally, the lack of a system to efficiently manage these processes created a need for increased efficiency in event planning.

[0586] 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.

[0587] In this invention, the server includes means for acquiring information about past events, means for inputting prompt sentences into a generation AI model to generate suggestions, and means for transferring the generated suggestion content to a terminal. This makes it possible to quickly and effectively create new event suggestions tailored to participant characteristics and to improve the accuracy of suggestions for future events by incorporating user feedback.

[0588] "Means for obtaining information on past events" refers to devices or software that have the function of collecting data such as the content, date and time, participant characteristics, and participant feedback of past events.

[0589] "Means for verifying generated proposals" refers to a process or system for evaluating the effectiveness and appropriateness of event proposals created by a generative AI model.

[0590] "Means of adjusting proposals based on participant characteristics" refers to methods or techniques for optimizing proposals by taking into account participants' age, interests, past participation history, etc.

[0591] "Means using a generation processing device that automatically generates event content" refers to a device or system that uses AI models or algorithms to automatically create event proposals.

[0592] "Means for transferring generated proposal content to a terminal" refers to a technology or device for transferring event proposals generated from a server to a terminal used by a user via digital communication.

[0593] "A means of inputting prompt sentences into a generative AI model to generate suggestions" refers to a process that uses natural language processing technology to input text containing specific instructions (prompt sentences) into an AI model and creates event suggestions based on that input.

[0594] This invention relates to a system for automating the generation of new proposals in event planning. The system primarily involves the collaboration of a server, terminals, and a generation engine to generate new proposals based on past event data.

[0595] The user first uses a terminal to enter information about past events. This information includes the type of event, the age range of participants, and feedback from past participants. This data is entered on the terminal and sent to the server by executing the data transmission command.

[0596] The server analyzes the received data. This analysis can utilize data analysis libraries such as Python or R. Based on the analyzed data, the server generates new event suggestions using a generative AI model (e.g., GPT-4). During this process, prompts are input to the generation engine, which then returns appropriate suggestions.

[0597] The generated suggestions are transferred from the server to the terminal and displayed visually to the user on the terminal. The user reviews the displayed suggestions and provides feedback on their satisfaction level and areas for improvement. This feedback is sent back to the server and used to improve future suggestions.

[0598] As a concrete example, consider a scenario where a user inputs the following prompt into the generation engine: "I previously held cooking classes and workshops for participants aged 30-50. Please suggest ideas for the next event. I would like suggestions that consider new elements and combinations with other activities." Based on this prompt, the AI ​​model suggests "a new workshop combining healthy cooking and community interaction," and the server forwards this suggestion to the user's device. The user receives and reviews this suggestion, enabling them to implement the new event.

[0599] This system allows users to plan new events quickly and effectively, improving participant satisfaction and streamlining operations.

[0600] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0601] Step 1:

[0602] The user uses a device to input information about past events. This includes the event name, date and time, age range of participants, and feedback. This data is entered into a form on the device. When the user presses the "Submit" button, the input is converted into a digital data format for transmission to the server.

[0603] Step 2:

[0604] The server receives data sent from the terminal. The received data is first categorized and divided into items such as event name, date and time, age group, and feedback. In this process, data analysis libraries (e.g., Pandas) are used to organize the data. After analysis, the server converts the data into an input format for the generating AI model.

[0605] Step 3:

[0606] The server generates and inputs a prompt message to the AI ​​model. This prompt message includes instructions such as "Generate new suggestions based on past event data." The AI ​​model uses natural language processing techniques to generate new event suggestions based on the input prompt message and data. The output suggestions are temporarily stored on the server as text data.

[0607] Step 4:

[0608] The generated event proposals are transferred from the server to the terminal. The terminal visually displays the received proposals to the user. HTML and CSS are used to ensure that the proposals are displayed in a clear and easy-to-understand format for the user. The user can review the proposals on the terminal and read the specific details.

[0609] Step 5:

[0610] Users provide feedback on the displayed suggestions. They use a feedback form on their device to input information such as the suitability of the suggestion and suggestions for improvement. When the user presses the "Submit Feedback" button, the information is sent to the server. This feedback provides the server with data to improve the accuracy of future suggestion generation.

[0611] (Application Example 1)

[0612] 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".

[0613] In event planning for physical stores, it is crucial to streamline planning operations and improve participant satisfaction by automatically generating efficient and innovative proposals based on past event information and participant characteristics, and evaluating the effectiveness of these proposals. Traditional methods have not adequately utilized information, making it difficult to break away from monotonous event planning.

[0614] 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.

[0615] In this invention, the server includes a device for receiving past event information, a device for evaluating the effectiveness of generated event proposals, and a device for adjusting proposals based on user characteristics. This enables the efficient generation of new event plans for physical stores and allows for optimal event proposals tailored to the needs of participants.

[0616] "Past event information" is a general term for data related to events held in the past, and includes information such as the event content, participant characteristics, venue, and dates.

[0617] "Device" refers to a hardware or software component for performing a specific function, and in this invention, it refers to a device for receiving, analyzing, and displaying information.

[0618] A "generation mechanism" is a part of a system that uses algorithms and AI technology to create new event suggestions based on input data.

[0619] "User characteristics" refer to attribute information about event participants, including parameters such as age group, hobbies, interests, and regional background.

[0620] "Adjusting the proposal" refers to the process of optimizing the generated event plan by taking into account user characteristics and past feedback.

[0621] "Feedback" refers to evaluations and opinions provided by users, and is used to improve generated proposals and enhance the accuracy of future proposals.

[0622] The "function to optimize event planning proposals for administrators" is a function that assists those who manage physical stores in coordinating and planning the most suitable event content based on user needs and past event results.

[0623] In this embodiment, a server, terminal, and generation engine work together to form a system that supports event planning at physical stores. The server first receives past event information sent from the terminal. This includes data such as the event content, participant characteristics, date and time, and location. Based on this data, the server uses the generation engine to generate new event proposals. This generation engine employs Python algorithms and AI technology to automatically create event planning proposals.

[0624] Users can receive and review event proposals generated from the server using devices such as smartphones and tablets. Providing feedback on the proposals helps improve the accuracy of future proposals. This feedback, including user ratings and comments, is sent to the server and incorporated into future event proposals.

[0625] As a concrete example, a certain cafe sends information from a terminal to a server stating, "We held a picture book reading event last Christmas, and the participants were very satisfied." The server analyzes this information, and a generation engine generates new project proposals, such as "a picture book exhibition in collaboration with local authors," and proposes them to the store manager.

[0626] An example of a prompt to input into the generating AI model is, "Based on information from past 'AA events,' please propose a new event plan." This makes it possible to generate more specific and practical event plans.

[0627] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0628] Step 1:

[0629] The device collects past event information and sends it to the server. It takes information such as the content of past events, participant characteristics, date, time, and location as input. The device then compiles this information into JSON format and sends it to the server via an HTTP request. The output is a confirmation response indicating that the information was received correctly by the server.

[0630] Step 2:

[0631] The server analyzes the event information received from the terminal and inputs it into the generation engine. The input is event information from the terminal, and the server uses this information to convert it into a format suitable for the generation engine. By performing data analysis, the server prepares to organize the event type and participant characteristics. The output is the correct data input to the generation engine.

[0632] Step 3:

[0633] The generation engine generates new event proposals based on the data. The input is organized event data provided by the server. The generation engine uses an AI algorithm to create new event plans, taking into account past data and participant characteristics. The output is the proposed content to be sent to the server.

[0634] Step 4:

[0635] The server receives event proposals from the generation engine and sends them to the terminal. The input is the proposal from the generation engine, and the server converts this content into a format that can be displayed on the terminal. The output is the event proposal received by the terminal.

[0636] Step 5:

[0637] Users review proposed event plans and send feedback to the server via their terminal as needed. The input is the proposal from the server, which the user evaluates and creates feedback. The output is the feedback sent back to the server. This feedback helps improve the system.

[0638] 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.

[0639] This invention combines an emotion engine with an event content suggestion system to enable dynamic suggestions that take into account the user's emotional state. First, the user inputs past event data and their own basic emotional data via a terminal. The terminal then sends this data to the server.

[0640] The server generates event suggestions using a generation engine based on the received event data, and simultaneously analyzes the user's emotional state using an emotion engine. By considering this emotion data and past event data, the suggestions are adjusted to be more meaningful and interesting to the user.

[0641] The generated suggestions are further customized based on the emotional data recognized by the emotion engine and sent from the server to the terminal as final suggestions. This allows the user to intuitively understand whether the event content is appropriate for their emotions.

[0642] For example, if a user provides emotional data indicating they have been feeling stressed recently, the server will take this into consideration and suggest activities specifically focused on relaxation. Conversely, if the user indicates positive emotions, the server will suggest activities that include more challenging and creative pursuits.

[0643] This system makes it possible to offer more personalized experiences by suggesting events and activities that go beyond simply providing information, and instead directly appeal to the emotions of participants.

[0644] The following describes the processing flow.

[0645] Step 1:

[0646] Users input past event data and self-assessed emotional information via their device. This emotional information includes moods during specific periods and emotional responses to recent events.

[0647] Step 2:

[0648] The terminal sends the input data to the server in a standardized format. A brief check is performed before transmission to ensure there are no data errors.

[0649] Step 3:

[0650] The server analyzes the received event data and uses a generation engine to generate basic event suggestions based on past trends and evaluations.

[0651] Step 4:

[0652] The emotion engine analyzes the user's emotional information and evaluates their current emotional state. This evaluation result has characteristics that influence the generated event suggestions.

[0653] Step 5:

[0654] The server integrates the results from the generation engine and the emotion engine, makes adjustments to adapt to the user's emotional state, and derives the most suitable event suggestions.

[0655] Step 6:

[0656] The server sends a coordinated event proposal to the terminal. This proposal includes information on the reasons for the recommendation and the expected emotional benefits for participants.

[0657] Step 7:

[0658] The device presents suggestions received from the server to the user, clearly displaying their content and reasons. The user can then provide feedback based on their emotional response.

[0659] (Example 2)

[0660] 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".

[0661] Conventional event suggestion systems often fail to consider the user's emotional state, resulting in suggestions that are not optimal for the user. Furthermore, if the suggested results do not meet the user's expectations, the user experience suffers.

[0662] 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.

[0663] In this invention, the server includes means for receiving past event data and sentiment data, means for generating event suggestions using a generation engine, and means for evaluating the user's emotional state using a sentiment analysis engine. This enables personalized event suggestions that take the user's emotional state into consideration.

[0664] "Past event data" refers to information about events and activities that a user has participated in in the past, including the date, time, location, and details of the activities.

[0665] "Emotional data" refers to information that indicates a user's mood and emotional state, expressing emotional conditions such as positive, negative, relaxed, and stressed.

[0666] A "generative engine" is an algorithm or system that generates appropriate event suggestions based on received input data, and utilizes machine learning and inference techniques.

[0667] A "sentiment analysis engine" is a system that analyzes emotional data provided by the user and evaluates and classifies the user's current emotional state, using natural language processing technology.

[0668] "Means for adjusting proposals" refers to a system that modifies or changes generated event proposals to match the user's emotional state and characteristics.

[0669] "User characteristics" refer to the individual attributes, hobbies, interests, and past behavioral history of users, and are used to optimize suggestions.

[0670] This system is designed to provide personalized event suggestions based on the user's emotional state. Users input past event data and emotional data via a terminal. The terminal then sends this data to a server.

[0671] When the server receives data, it uses a generation engine to create event suggestions tailored to the user. The generation engine utilizes a machine learning platform, specifically applying technologies from previous cloud platforms. Simultaneously, the server uses a sentiment analysis engine to analyze the emotional data entered by the user. For example, it leverages natural language processing techniques to analyze emotional elements within the text and classify the user's emotional state based on that analysis.

[0672] The suggestions generated by the generation engine are further refined based on the sentiment analysis results. In this refinement, if the user is in a state of emotional state where they desire relaxation, suggestions specifically focused on relaxation will be prioritized. Conversely, if the user is in an emotional state where they desire challenging activities, events that allow them to learn new skills will be suggested.

[0673] The completed proposal is sent from the server to the terminal and displayed to the user. The user can review the received proposal and participate in events that match their interests and current feelings.

[0674] For example, if a user inputs a feeling like "I want to relax lately," the system will suggest options such as yoga classes or relaxation workshops. An example of a prompt for the generative AI model might be, "What kind of event are you looking for? Are you looking for relaxation or adventure?" This allows for suggestions that meet the user's expectations.

[0675] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0676] Step 1:

[0677] Users input past event data and emotional data through their device. Specifically, they enter details of events they attended (e.g., event name, date, time, location) and their mood or emotional state (e.g., "I want to relax," "I'm craving stimulation") on the input screen. The device collects this input data and sends it to the server as data packets.

[0678] Step 2:

[0679] The server processes data packets received from the terminal and inputs them into the generation engine. The generation engine analyzes this data and suggests highly relevant events based on trends from past events. Data processing includes calculating event similarity and weighting past participation history. The output is multiple event suggestions.

[0680] Step 3:

[0681] The server evaluates the user's emotional data using an emotion analysis engine. This step employs natural language processing algorithms to extract emotions from text data and classify them into positive, negative, or neutral states. The output is result data indicating the user's emotional state.

[0682] Step 4:

[0683] The server integrates the generated event suggestions with the sentiment analysis results to provide suggestions optimized for the user's emotions. The suggestions are adjusted to the user's current emotional state; for example, events that are effective in reducing stress or events that include challenging activities are selected. The output is the optimized event suggestions.

[0684] Step 5:

[0685] The server sends the final proposal to the terminal and displays it to the user. The user can review the details of the proposed events and decide whether to participate in events that align with their interests and feelings. The input here is the final proposal, and the output is the presentation of event information to the user.

[0686] (Application Example 2)

[0687] 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".

[0688] Conventional event suggestion systems have a problem in that they do not adequately consider the user's emotional state, and therefore the suggested content may not be suitable for the user's current situation. Furthermore, especially in physical stores, providing services that respond to the customer's emotional state in real time is a challenge.

[0689] 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.

[0690] In this invention, the server includes a component that receives past event data, a component that combines emotion recognition technology for analyzing emotional states, and a component that optimizes the information displayed on the device based on the customer's emotions. This enables personalized suggestions that are appropriate to the user's emotional state.

[0691] "Past event data" refers to information about events and activities that the user has previously participated in.

[0692] "Proposal efficiency" refers to the degree to which the generated proposals align with the user's needs and emotions.

[0693] "Participant characteristics" refer to the individual characteristics of each user, such as their age, gender, and hobbies.

[0694] A "generative mechanism" refers to an algorithm or platform used to generate proposals.

[0695] "Emotion recognition technology" refers to technology that analyzes a user's facial expressions and voice to determine their emotional state.

[0696] "Information displayed on the device" refers to the content of suggestions provided to the user through devices such as smart glasses.

[0697] The system for carrying out this invention consists of using smart glasses as hardware and implementing emotion recognition and suggestion generation software. The smart glasses are equipped with a camera to capture the user's facial expressions and emotion recognition technology to analyze emotions. This technology can be implemented, for example, using the Affectiva SDK.

[0698] The server uses facial expression data received from the smart glasses to evaluate the user's emotional state in real time. This emotional data, along with the user's past event data, is sent to the server, and a generative AI model generates suggestions. For example, OpenAI's GPT series is used for this model. The server optimizes the generated suggestions to match the user's emotions and displays them on the smart glasses. This information includes product and event information relevant to the user at that time.

[0699] For example, if a customer feels stressed upon entering a store, the server will generate suggestions for relaxation products and services. Conversely, if positive emotions are detected, recommendations for products that promote creative activities will be made.

[0700] The following prompt statements are used when utilizing generative AI models.

[0701] Emotional state: Stress

[0702] Past purchase history: Scented candles, premium tea

[0703] Please generate recommendations.

[0704] Emotional state: positive

[0705] Past purchase history: DIY kits, handmade accessories

[0706] Please generate recommendations.

[0707] This invention makes it possible to provide emotion-based, real-time, personalized experiences even in physical stores.

[0708] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0709] Step 1:

[0710] The device uses the camera on smart glasses to capture the user's face and collect facial expression data in real time. This data is analyzed using emotion recognition technology to determine the user's emotional state (e.g., stressed, positive). The input is facial expression image data, and the output is the analyzed emotional state.

[0711] Step 2:

[0712] The user provides information about past events on their device. This includes a history of past purchases and events attended. This data is sent directly to the server and used for suggestion generation. The input is the user-provided historical data, and the output is structured event data.

[0713] Step 3:

[0714] The server integrates the emotional state and past event data received from the terminal. Based on this, it creates prompt sentences for the generative AI model to generate the optimal suggestion. The input is the emotional state and past event data, and the output is the prompt sentence. An example of a prompt sentence is, "Emotional state: Stress, Past purchase history: Aromatherapy candle, Premium tea."

[0715] Step 4:

[0716] The server uses a generative AI model to analyze the prompt text and generate personalized suggestions for the user. This process utilizes data processing and natural language generation technologies. The input is the prompt text, and the output is the generated suggestions. These suggestions may include relaxation products or event announcements.

[0717] Step 5:

[0718] The server sends the generated suggestions to the terminal and displays them on the smart glasses' screen. This allows the user to directly access the suggested items and make selections or purchases on the spot. The input is the generated suggestions, and the output is the visualized information.

[0719] 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.

[0720] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0721] 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.

[0722] 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.

[0723] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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."

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] The following is further disclosed regarding the embodiments described above.

[0741] (Claim 1)

[0742] Means of receiving past event data,

[0743] A means for evaluating the effectiveness of the generated proposals,

[0744] A means of adjusting proposals based on participant characteristics,

[0745] A method that utilizes a generation engine to propose the content of events,

[0746] A system that includes this.

[0747] (Claim 2)

[0748] The system according to claim 1, further comprising means for presenting the generated proposal results to the user.

[0749] (Claim 3)

[0750] The system according to claim 1, further comprising means for receiving user feedback on the proposed results.

[0751] "Example 1"

[0752] (Claim 1)

[0753] Means of obtaining information about past events,

[0754] A means of verifying the generated proposal,

[0755] A means of adjusting the proposal based on the characteristics of the participants,

[0756] A means of using a generation processing device that automatically generates event content,

[0757] A means for transferring the generated proposal content to the terminal,

[0758] A means of inputting prompt sentences into a generative AI model to generate suggestions,

[0759] A system that includes this.

[0760] (Claim 2)

[0761] The system according to claim 1, further comprising means for displaying the generated proposal content to the user.

[0762] (Claim 3)

[0763] The system according to claim 1, further comprising means for collecting user evaluations of the proposed content.

[0764] "Application Example 1"

[0765] (Claim 1)

[0766] A device for receiving past event information,

[0767] A device for evaluating the effectiveness of the generated project proposal,

[0768] A device that adjusts suggestions based on the user's characteristics,

[0769] A device that utilizes a generation mechanism to propose event content,

[0770] A device that displays suggestions on the user's device,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, further comprising a device for receiving feedback on the proposed results.

[0774] (Claim 3)

[0775] The system according to claim 1, which includes a function to optimize event proposals for administrators and update proposals according to user needs.

[0776] "Example 2 of combining an emotion engine"

[0777] (Claim 1)

[0778] A means of receiving past event data and sentiment data,

[0779] A means of generating event proposals using a generation engine,

[0780] A means of evaluating a user's emotional state using an emotion analysis engine,

[0781] A means of adjusting the proposal based on the evaluation results,

[0782] A means of optimizing the adjusted suggestions to suit the user's characteristics,

[0783] A system that includes this.

[0784] (Claim 2)

[0785] The system according to claim 1, further comprising means for displaying optimized suggestions.

[0786] (Claim 3)

[0787] The system according to claim 1, further comprising means for receiving user feedback on a proposal.

[0788] "Application example 2 when combining with an emotional engine"

[0789] (Claim 1)

[0790] Components that receive past event data,

[0791] Components for evaluating the efficiency of the generated proposals,

[0792] Components that adapt the proposal based on the characteristics of the participants,

[0793] Components that utilize a generation mechanism to propose the content of an event,

[0794] Components that combine emotion recognition technologies for analyzing emotional states,

[0795] Components that optimize the information displayed on the device based on customer emotions,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, comprising a device for presenting the generated proposal results to a user.

[0799] (Claim 3)

[0800] The system according to claim 1, comprising a component for receiving user feedback on the proposed results. [Explanation of Symbols]

[0801] 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 of receiving past event data, A means for evaluating the effectiveness of the generated proposals, A means of adjusting proposals based on participant characteristics, A method that utilizes a generation engine to propose the content of events, A system that includes this.

2. The system according to claim 1, further comprising means for presenting the generated proposal results to the user.

3. The system according to claim 1, further comprising means for receiving user feedback on the proposed results.

Images