system

Abstract

We provide the system. [Solution] Means of acquiring conversation data, A method for analyzing acquired conversation data to estimate participants' interests, personalities, and emotions, A means for generating activity proposals based on estimation results, A means of presenting activity proposals and supporting decision-making, A system that includes means for making reservations and payments for selected activities.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need to solve the difficulties faced by busy working people when determining common free time and activity content. Specifically, since it is difficult to make a quick and satisfactory decision considering the interests and moods of each participant, a mechanism is required to enable efficient planning and smooth execution of group activities.

Means for Solving the Problems

[0005] This invention provides a technology for acquiring and analyzing conversation data to estimate participants' interests, personalities, and emotions. This technology supports efficient decision-making by generating and presenting activity suggestions based on the estimation results. Furthermore, by providing a system that allows for the booking and payment of selected activities, it facilitates the planning and execution of group activities.

[0006] "Conversation data" refers to the collection of text and message content exchanged during communication between users.

[0007] "Means of acquisition" refers to the processes and methods for collecting necessary data from external systems and devices.

[0008] "Means of analysis" refer to methods and techniques for analyzing collected data and extracting useful information.

[0009] "Participants" refers to individuals or users who belong to group activities or chats and participate in the decision-making process.

[0010] "Interest" is a concept that indicates the degree to which one is concerned with or pays attention to a particular activity or object.

[0011] "Personality" refers to psychological characteristics that describe an individual's unique thought patterns and behavioral tendencies.

[0012] "Emotions" are internal experiences that represent an individual's psychological state or mood.

[0013] "Means of estimation" refers to techniques and approaches that predict unknown information or states based on data analysis.

[0014] An "activity proposal" is a set of specific actions recommended based on the proposed schedule and plan.

[0015] "Means of supporting decision-making" refers to support methods and systems that assist in evaluating options and the selection process.

[0016] "Reservation" is a procedure for securing in advance the planned use of services and resources.

[0017] "Settlement" is the process of a transaction in which payment of money is made as the consideration for the purchase of goods or the provision of services.

Brief Explanation of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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 device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Exemplary 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system which is an application example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0021] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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.

[0022] 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.

[0023] 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.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

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

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] The embodiments for carrying out the present invention are described below. This system provides technology for efficiently planning group activities by acquiring and analyzing conversation data. Specifically, it is implemented as a bot that can be used by users through messaging platforms such as LINE. This bot acquires data exchanged by participants in their everyday conversations in real time and analyzes its content to accurately estimate the interests, personalities, and emotions of the participants.

[0040] Based on this analysis, the server generates and proposes an appropriate activity plan to the user. For example, if participant A prefers relaxing activities and participant B prefers active outdoor activities, the bot will present a balanced activity plan that takes both of their interests into account. This proposal also includes detailed information such as specific dates and times, locations, and necessary preparations, to support the user's decision-making.

[0041] Once a decision is made based on the proposed activity plan, the reservation process begins on the terminal. The server works in conjunction with the reservation management system to provide the necessary information. Payments can also be processed securely, and settlement is possible in a simple manner, especially when multiple participants are involved.

[0042] As a concrete example, let's assume three users, X, Y, and Z, are planning a meal together. They add this bot to the group and begin planning. The server analyzes the users' preferences and budget from the conversation and makes suggestions such as, "X likes Japanese food, but Y tends to enjoy Italian food. I'll recommend some restaurants, so please specify a date and time." After the users accept the suggestions, they can make reservations and payments directly from their devices, completing the entire process efficiently.

[0043] Thus, the present invention is a system that enables quick and satisfactory decision-making while taking into account the diverse interests of participants, and facilitates planning in daily group activities.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users add the system's bot to a group chat within the LINE app. This action prepares the bot to participate in future conversations and collect data.

[0047] Step 2:

[0048] The server uses the LINE Messaging API to receive message content in real time to acquire conversation data within the group chat. At this stage, the text information of each message is obtained.

[0049] Step 3:

[0050] The server analyzes the acquired conversation data using natural language processing (NLP) techniques. Specifically, it performs text tokenization, contextual understanding, and sentiment analysis to identify participants' interests, personalities, and emotions.

[0051] Step 4:

[0052] The server generates an appropriate activity plan based on the analysis results. In this process, it utilizes machine learning models that reference historical data and external information sources to create suggestions that match the user's interests.

[0053] Step 5:

[0054] The server proposes the generated activity plan to the user. Specifically, it posts suggestion messages naturally within the conversation, presenting a range of activity options.

[0055] Step 6:

[0056] Users discuss the proposed activities within their group and make a final decision. If necessary, they can request additional information or alternative suggestions from the bot.

[0057] Step 7:

[0058] On your device, begin the booking process for your selected activity. Enter your details via the link or form within the LINE app to complete your booking.

[0059] Step 8:

[0060] The server works in conjunction with an external reservation system to secure reservation information. If payment is required, it accesses the payment system and executes the payment.

[0061] Step 9:

[0062] The user receives a message confirming that their reservation and payment are complete. They then receive a reminder notification for the day of the activity, allowing them to prepare for it.

[0063] (Example 1)

[0064] 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."

[0065] In modern social life, it is crucial to efficiently plan activities based on participants' interests and preferences through interpersonal communication. However, accurately understanding participants' hobbies and desires is difficult, and there is a need for a system that smoothly handles all procedures, from activity planning to reservations and payments. Furthermore, a system is needed that can reflect individual opinions and propose highly satisfying options.

[0066] 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.

[0067] In this invention, the server includes means for collecting information, means for analyzing the collected information to estimate the individual's interests, characteristics, and emotions, and means for generating choices based on the estimation results. This makes it possible to plan activities that take into account the diverse interests of the individual.

[0068] "Means of collecting information" refers to processing mechanisms that acquire data from communication between individuals and use it as the basis for analysis.

[0069] "Means for analyzing information and estimating an individual's interests, characteristics, and emotions" refers to a processing mechanism that uses acquired data to evaluate an individual's nature and emotions, and to help propose specific actions.

[0070] "Means for generating options based on estimation results" refers to a processing mechanism that, based on analyzed data, makes multiple suggestions that best reflect the diverse interests and desires of individuals.

[0071] "Means of presenting options and supporting decision-making" refers to processing mechanisms that communicate generated proposals to individuals in an easily understandable way and support them in making quick decisions.

[0072] "Means for processing and paying for selected items" refers to a procedural mechanism for automatically and securely processing reservations and payments related to actions chosen by an individual.

[0073] This section describes embodiments for carrying out this invention. The invention is constructed as a system that efficiently supports activity planning that takes into account the diverse interests of participants by utilizing interpersonal communication.

[0074] 1. Information gathering and analysis

[0075] The server collects and analyzes information from the messaging platform. Because advanced data analysis is required, a dedicated server machine is necessary. For software, an analysis toolkit strong in natural language processing (for example, using open-source natural language processing libraries or commercial language processing APIs in combination) is recommended.

[0076] 2. Estimation of interests, traits, and emotions

[0077] The server estimates the individual's interests, characteristics, and emotions from the collected information. For this purpose, a generative AI model could be used for analysis. This model is trained on a large dataset to improve the accuracy of the analysis.

[0078] 3. Generation and Proposal Generation

[0079] Based on the analysis results, the server generates the optimal choices for each individual and proposes them to the terminal. A dynamic choice generation algorithm is used in this proposal process. The generated choices are communicated to the individual via a specific platform.

[0080] 4. Specific Examples

[0081] For example, consider planning a weekend meal for a group. The user can enter a prompt and give instructions such as: "Please suggest a weekend meal plan for our group. Based on the conversation data, please generate a program that selects a restaurant considering each member's preferences and budget, and suggests a date, time, and location." This makes it possible to automatically suggest appropriate options based on data extracted from the conversation.

[0082] In this way, servers, terminals, and users cooperate to provide activity plans that meet the diverse needs of each individual. This method enables efficient decision-making that satisfies all participants.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server automatically collects communication data between users through the messaging platform API. This input data includes text messages, sender information, and transmission time. The server preprocesses this data, removes noise, and then stores it in a database for analysis. This prepares the data for efficient subsequent analysis.

[0086] Step 2:

[0087] The server analyzes the collected data using natural language processing technology. This process involves a generative AI model that estimates each user's interests, characteristics, and emotions as quantifiable indicators from the communication data. Preprocessed text data is taken as input, and individual profile information is generated as output and stored in a database. This allows for an understanding of individual characteristics and lays the foundation for optimal suggestions based on them.

[0088] Step 3:

[0089] The server generates activity options tailored to each individual based on the analysis results. Using the analyzed profile information as input, it creates activity suggestions that best suit each user through a selection generation algorithm. Specifically, it presents candidate dates, times, locations, and activities, taking into account the user's interests. This allows for suggestions that reflect the user's opinions.

[0090] Step 4:

[0091] The server presents the generated activity proposal to the user via the terminal. It receives the generated activity proposal as input and notifies the user's terminal as output. Specifically, it sends the details of the proposal (for example, "How about a picnic at City Park this Saturday at 3pm?") to the user via the messaging platform. At this stage, the user can accept or modify the proposal, or request a different proposal.

[0092] Step 5:

[0093] The terminal initiates the process through the reservation management system once the user approves the proposal. It takes user approval information as input and receives confirmation of reservation completion as output. Using a reservation system such as the OpenTable API, it reserves the proposed activity and informs the user of the necessary details. This process is crucial to ensuring the overall feasibility of the proposal.

[0094] (Application Example 1)

[0095] 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."

[0096] Modern consumers are required to choose products and services that suit their interests from a wide variety of options, but this often takes time and effort due to the sheer number of choices. Furthermore, in group activities, it is difficult to propose activities that take into account the interests and preferences of all participants. In addition, there is a lack of effective means to present personalized information in real time using smart devices.

[0097] 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.

[0098] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of multiple participants, and means for generating activity suggestions based on the estimation results. This makes it possible to provide suggestions based on the characteristics of each participant in real time and support efficient decision-making.

[0099] "Conversation information" refers to communication data in audio or text format exchanged between participants.

[0100] "Analysis" is the process of processing acquired data to understand its meaning and trends.

[0101] "Interest" refers to the degree to which participants show interest in a particular theme or activity.

[0102] "Personality" refers to the characteristics that indicate the behavioral patterns and preference tendencies of individual participants.

[0103] "Emotion" refers to a psychological state inferred from the content of a conversation or from someone's actions.

[0104] An "activity suggestion" is a recommendation of behavior created based on analyzed interests, personality, and emotions.

[0105] "Reservation" refers to the process of securing selected activities or services in advance.

[0106] "Electronic payment" refers to a method of monetary transactions conducted using digital technology.

[0107] "Behavioral information" refers to data about participants' movements and choices within the environment.

[0108] "Product recommendations" refer to the act of recommending highly relevant products or services based on the participants' interests.

[0109] An "information infrastructure" is a system for collecting, storing, and accessing data.

[0110] A "smart device" is an electronic device equipped with internet connectivity that serves to provide information to users.

[0111] The system for implementing this invention mainly consists of a server, multiple smart devices, and a communication network. The server is responsible for receiving data from smart devices equipped with the ability to acquire conversational information and analyzing it. For analysis, Google® Cloud Speech-to-Text API and natural language processing libraries (such as NLTK and spaCy) can be used. The acquired conversational information is evaluated by a generative AI model (e.g., OpenAI® GPT-3®) to estimate the participants' interests, personalities, and emotions.

[0112] The server generates activity suggestions based on these estimation results. These activity suggestions include user-related content based on product and service data obtained from an external information infrastructure. This generates product suggestions and campaign information tailored to the user's characteristics, which are displayed on smart devices such as smart glasses and smartphones. This information provision aims to support the user's decision-making. It also includes functions to support reservation and electronic payment procedures.

[0113] As a concrete example, consider a user walking through a shopping mall wearing smart glasses. These glasses can analyze the user's conversation in real time, recognize their interest in pet-related products, and then display recommended products and discount information from pet shops on the screen.

[0114] An example of a prompt to input into a generative AI model is: "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data."

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The device acquires user conversation information as audio data. The acquired audio data is converted into text data by a speech recognition API (e.g., Google Cloud Speech-to-Text). In this conversion process, the audio waveform data is analyzed using a language model, and text data is output as a string.

[0118] Step 2:

[0119] The server analyzes the acquired text data using natural language processing libraries (e.g., NLTK and spaCy). This analysis identifies context, emotions, and interests. The text data is tokenized, tagged with parts of speech, and subjected to dependency analysis before being processed into a format that can be input into a generative AI model. Here, keywords and phrases that indicate the user's interests and personality are extracted.

[0120] Step 3:

[0121] The server uses a generative AI model (e.g., OpenAI GPT-3) to create prompt sentences based on the keywords extracted in step 2. The server receives a prompt in the format of, "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data." The generated text is then output as a product suggestion tailored to the user.

[0122] Step 4:

[0123] The server compares product suggestions and promotional information with data from an external information infrastructure to determine the final display content. Here, it searches the database for relevant product information and campaigns, filters them, and selects the information that best suits the user's interests.

[0124] Step 5:

[0125] The terminal transmits the final selected product suggestions and promotional information to the user's smart device, displaying them in real time. For example, it can display information on the display of smart glasses to support the user's decision-making. Links and QR codes (registered trademarks) can also be used in conjunction to allow the user to directly access products.

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

[0127] The embodiments for carrying out the present invention are described below. This system provides technology for effectively planning group activities by collecting and analyzing conversation data, recognizing user emotions using an emotion engine, and analyzing conversation data. The system operates on a messaging application and is integrated into an active group chat.

[0128] The server acquires conversation data in real time and uses an emotion engine to analyze users' emotions. This complements the results of analysis using conventional natural language processing techniques, enabling deeper level-based estimation of interests, personality, and emotions. Specifically, the emotion engine detects emotional tone and nuances from the user's text and determines the expectations and motivations that individual members have for the activity.

[0129] Based on these analysis results, the server generates and provides customized activity suggestions to the user. In particular, if the user is showing negative emotions, it will suggest activities that improve their mood, thus providing emotionally sensitive suggestions. In this way, flexible planning that takes into account the user's psychological state and group dynamics is promoted.

[0130] As a concrete example, consider a scenario where users A, B, and C get together and plan an activity for the weekend. The server uses its emotion engine to analyze the conversation and determine that user A is tired from work and needs to relax, and user B wants to try something new. Based on this, the server suggests options such as "a relaxing day at a nearby resort" or "a cooking class to try new dishes."

[0131] Once the user accepts the proposal, the terminal guides them through the booking process via text message. The server connects to the booking system to process the details and supports payment on the terminal. Furthermore, an emotional engine continuously monitors user feedback, enabling dynamic adjustments accordingly. This ensures a satisfactory plan for all participants.

[0132] This system, by incorporating features that take emotions into consideration, surpasses conventional activity planning systems and enables more adaptable action suggestions and decisions.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The user adds an emotion engine-enabled bot to a group chat within the LINE app. This action prepares the bot to begin monitoring all conversational interactions.

[0136] Step 2:

[0137] The server retrieves group chat conversation data in real time. The text of each message is sent to the server using the LINE Messaging API.

[0138] Step 3:

[0139] The server analyzes the conversation data obtained using natural language processing techniques. Natural language processing identifies each user's basic interests and topic priorities.

[0140] Step 4:

[0141] The server uses an emotion engine to recognize the user's emotions from the text. This engine detects emotion-specific keywords and phrases and determines the tone of the emotion, which is then classified into different emotion labels such as joy, anger, and sadness.

[0142] Step 5:

[0143] The server integrates data from both the emotion engine and natural language processing to generate customized activity suggestions based on each user's interests, personality, and emotions.

[0144] Step 6:

[0145] The server presents the generated activity suggestions to the user. It sends suggestions directly to the user using a message format, providing them with options.

[0146] Step 7:

[0147] The user selects and accepts the activity that interests them most from the presented suggestions. During this process, they can also ask the server any questions or inquire about other options.

[0148] Step 8:

[0149] On the device, the user starts the booking process for the selected activity. By clicking a link within the LINE app, the user enters the necessary details for the booking and completes the reservation.

[0150] Step 9:

[0151] After the reservation is complete, the server connects with an external payment system to execute a secure payment process. The user's payment information is verified, and the transaction is confirmed.

[0152] Step 10:

[0153] Users receive a final confirmation message regarding their planned activities. They can also receive reminder notifications as the activity date approaches.

[0154] (Example 2)

[0155] 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".

[0156] In modern society, there is a need to efficiently plan group activities while taking into account the psychological state and emotions of participants. However, conventional activity planning systems have the challenge of making proposals that adequately reflect the emotions and motivations of participants. Furthermore, these systems lack the flexibility to make adjustments based on post-activity feedback, so improvements are needed to increase participant satisfaction.

[0157] 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.

[0158] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of the participants, and means for utilizing a generative model that generates activity suggestions based on the estimation results. This makes it possible to generate activity suggestions that reflect the user's emotions and to dynamically adjust the suggestions based on subsequent feedback.

[0159] "Conversational information" refers to communication data such as text and audio exchanged between users.

[0160] "Analysis" refers to a series of processes that involve analyzing conversational information and extracting characteristics such as its content and emotional tone.

[0161] "Interest" refers to the degree to which participants show interest in a particular activity or topic.

[0162] "Personality" refers to the individual psychological characteristics that influence the behavior and reactions of participants.

[0163] "Emotion" refers to the emotional state that participants exhibit in response to a particular situation or stimulus.

[0164] A "generative model" refers to an algorithm or system for generating a new output from input data.

[0165] An "emotion engine" refers to a technology or system that can detect emotional tone and nuances from text data.

[0166] "Dynamic adjustment" refers to changing proposed content and system settings in real time based on analysis and feedback.

[0167] This invention is a system that supports the planning of group activities by comprehensively analyzing user emotions and proposing optimal activities based on those analyses. This system operates on a messaging platform and combines a server, terminals, and a generative AI model.

[0168] The server retrieves conversation information from messaging applications in real time. It connects to the platform using an API to collect communication data between users. This collected data is then analyzed using an emotion engine. This emotion engine utilizes the Google Cloud Natural Language API and general emotion analysis tools to detect emotional tone and nuances, thereby understanding the user's emotional state.

[0169] Based on the analysis results, the server generates activity suggestions using a generative AI model. This model considers the user's interests and emotional state, and creates suggestions using appropriate prompts. For example, a prompt might be "Use the user's conversation data to generate activity suggestions that take their mood into consideration."

[0170] The generated suggestions are presented to the user via the device. The device displays a notification on the messaging application, prompting the user to review the suggestions. If the suggestion is accepted, the device guides the user through the booking process, and the server connects to the booking system to process the necessary information. The server also analyzes the post-activity feedback again using the sentiment engine to help adjust future suggestions. This ensures that users can continue to experience satisfaction.

[0171] As a concrete example, when users A and B plan their weekend activities, the server analyzes their conversation to determine that user A needs relaxation and user B is seeking a new experience. Based on this analysis, the server provides activity suggestions that combine a "relaxing day for relaxation" with an "innovative cooking class," thereby creating a plan that meets the users' expectations.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server retrieves conversation information in real time from the messaging platform. The input is message data between users, and the output is conversation information in text format. This conversation information is obtained by the server connecting to the platform via an API. The server then sends the retrieved conversation information to the next parsing step.

[0175] Step 2:

[0176] The server analyzes conversational information acquired using an emotion engine. The input is conversational information in text format, and the output is each user's emotional state and characteristics. Specifically, the emotion engine uses natural language processing techniques to analyze the text content and identify emotions such as positive, negative, and neutral. This result is then used as input to a generative model.

[0177] Step 3:

[0178] The server generates activity suggestions using a generative AI model based on the analysis results. The input is data about the user's emotional state, interests, and personality, and the output is a customized activity suggestion. The prompt is "Construct an appropriate activity suggestion based on the user's emotions." The generative AI model devises specific activities that match the user's psychological state and creates them as activity suggestions.

[0179] Step 4:

[0180] The terminal presents the generated activity suggestions to the user. The input is the activity suggestions received from the server, and the output is the activity details presented to the user as a notification. The terminal uses an existing messaging application to have the user review the suggestions. The user can select activities of interest from the presented options.

[0181] Step 5:

[0182] When a user selects an activity, the terminal guides them through the booking process. The input is the activity information selected by the user, and the output is the booking procedure details. The terminal provides a specific link, and the server connects to the booking system and processes the necessary information, allowing the user to complete the booking smoothly.

[0183] Step 6:

[0184] The server collects user feedback after an activity and analyzes it again using the emotion engine. The input is user feedback data, and the output is information for adjusting future suggestions. Based on the analyzed feedback, the server adjusts the generative AI model and uses it to make future suggestions more personalized.

[0185] (Application Example 2)

[0186] 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".

[0187] Modern conversation analysis systems using information and communication technology do not adequately consider user emotions or personalities, making it impossible to fully personalize individual experiences and product recommendations. Furthermore, the lack of flexible suggestions linked to real-world experiences makes it difficult for users to make purchases and experience choices optimized for them.

[0188] 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.

[0189] In this invention, the server includes means for acquiring conversation information and estimating the participants' interests, personalities, and emotions; means for generating activity suggestions based on the estimation results; and means for making reservations and payments for selected activities. This enables appropriate in-store experience suggestions and product suggestions tailored to the user's emotional state.

[0190] "Conversation information" refers to information about the content of communications and messages exchanged between users.

[0191] "Interest" refers to the degree to which a user is interested in a particular field or activity.

[0192] "Personality" is a set of psychological characteristics that influence a user's decision-making and behavior.

[0193] "Emotion" refers to a temporary feeling or reaction that a user experiences in response to a particular situation or stimulus.

[0194] An "activity proposal" is a concrete plan that, based on user interests and emotions, promotes experiences at physical stores and services.

[0195] A "reservation" is a pre-arranged procedure undertaken by a user to secure the provision of a specific product or service.

[0196] "Payment" refers to the process of paying for goods or services provided.

[0197] A "physical store" refers to a facility where users can directly experience or purchase products or services in a physical location.

[0198] "Product suggestions" refer to presenting products as potential purchase options, selected based on the user's emotions and interests.

[0199] The system for implementing this invention primarily consists of data exchange between a server and a terminal. The server first acquires conversation information between users in real time and analyzes this information using natural language processing and sentiment analysis techniques. Specifically, the Python TextBlob library assists in this sentiment analysis, playing a role in estimating the user's interests, personality, and emotions.

[0200] Based on the estimation results obtained, the server generates activity suggestions that correspond to the user's emotional state and interests. These activity suggestions include specific suggestions such as in-store experiences and products designed to improve the user's psychological state. Furthermore, the terminal presents the suggested information to the user and plays a role in supporting decision-making.

[0201] When a user selects a specific suggestion, the terminal assists with the booking and payment process. The server collaborates with external booking databases and payment systems to complete transactions quickly and securely. Furthermore, a generative AI model is used to continuously analyze user sentiment and feedback, collecting data to provide better activity suggestions.

[0202] For example, if a user mentions feeling tired, the system can suggest a relaxing experience. A possible prompt might be: "Generate a message suggesting an effective relaxation experience when the user is seeking relaxation."

[0203] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0204] Step 1:

[0205] The server obtains conversation information between users via a messaging application. In this step, raw data in text format is input and stored on the server as conversation data.

[0206] Step 2:

[0207] The server analyzes the acquired conversational information using natural language processing and sentiment analysis techniques. Here, the Python TextBlob library is used to detect the emotional tone of the text and estimate the user's interests and emotions. This process yields emotion and interest metrics extracted from the conversation as output.

[0208] Step 3:

[0209] The server generates activity suggestions tailored to the user based on the analysis results. Using sentiment analysis data as input, the generation AI model generates suggestions and prompts. For example, it might create prompts such as, "Generate prompts for experiences that provide relaxation."

[0210] Step 4:

[0211] The terminal presents activity suggestions received from the server to the user, supporting decision-making. The user interface includes notifications and a dashboard displaying the suggested content. It also provides a user feedback function, recording user responses as input.

[0212] Step 5:

[0213] When a user selects a specific suggestion, the terminal guides them through the booking and payment process. This process uses the user's selected activity as input to call the booking system and payment API, and outputs booking confirmation and payment information.

[0214] Step 6:

[0215] The server continuously monitors and analyzes user feedback using a generative AI model, and utilizes this feedback to improve the suggestions. This results in more personalized activity suggestions for the future, enhancing the user experience. Feedback data is input, and adjustment data for generating the next activity suggestion is output.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] The embodiments for carrying out the present invention are described below. This system provides technology for efficiently planning group activities by acquiring and analyzing conversation data. Specifically, it is implemented as a bot that can be used by users through messaging platforms such as LINE. This bot acquires data exchanged by participants in their everyday conversations in real time and analyzes its content to accurately estimate the interests, personalities, and emotions of the participants.

[0233] Based on this analysis, the server generates and proposes an appropriate activity plan to the user. For example, if participant A prefers relaxing activities and participant B prefers active outdoor activities, the bot will present a balanced activity plan that takes both of their interests into account. This proposal also includes detailed information such as specific dates and times, locations, and necessary preparations, to support the user's decision-making.

[0234] Once a decision is made based on the proposed activity plan, the reservation process begins on the terminal. The server works in conjunction with the reservation management system to provide the necessary information. Payments can also be processed securely, and settlement is possible in a simple manner, especially when multiple participants are involved.

[0235] As a concrete example, let's assume three users, X, Y, and Z, are planning a meal together. They add this bot to the group and begin planning. The server analyzes the users' preferences and budget from the conversation and makes suggestions such as, "X likes Japanese food, but Y tends to enjoy Italian food. I'll recommend some restaurants, so please specify a date and time." After the users accept the suggestions, they can make reservations and payments directly from their devices, completing the entire process efficiently.

[0236] Thus, the present invention is a system that enables quick and satisfactory decision-making while taking into account the diverse interests of participants, and facilitates planning in daily group activities.

[0237] The following describes the processing flow.

[0238] Step 1:

[0239] Users add the system's bot to a group chat within the LINE app. This action prepares the bot to participate in future conversations and collect data.

[0240] Step 2:

[0241] The server uses the LINE Messaging API to receive message content in real time to acquire conversation data within the group chat. At this stage, the text information of each message is obtained.

[0242] Step 3:

[0243] The server analyzes the acquired conversation data using natural language processing (NLP) techniques. Specifically, it performs text tokenization, contextual understanding, and sentiment analysis to identify participants' interests, personalities, and emotions.

[0244] Step 4:

[0245] The server generates an appropriate activity plan based on the analysis results. In this process, it utilizes machine learning models that reference historical data and external information sources to create suggestions that match the user's interests.

[0246] Step 5:

[0247] The server proposes the generated activity plan to the user. Specifically, it posts suggestion messages naturally within the conversation, presenting a range of activity options.

[0248] Step 6:

[0249] Users discuss the proposed activities within their group and make a final decision. If necessary, they can request additional information or alternative suggestions from the bot.

[0250] Step 7:

[0251] On your device, begin the booking process for your selected activity. Enter your details via the link or form within the LINE app to complete your booking.

[0252] Step 8:

[0253] The server works in conjunction with an external reservation system to secure reservation information. If payment is required, it accesses the payment system and executes the payment.

[0254] Step 9:

[0255] The user receives a message confirming that their reservation and payment are complete. They then receive a reminder notification for the day of the activity, allowing them to prepare for it.

[0256] (Example 1)

[0257] 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."

[0258] In modern social life, it is crucial to efficiently plan activities based on participants' interests and preferences through interpersonal communication. However, accurately understanding participants' hobbies and desires is difficult, and there is a need for a system that smoothly handles all procedures, from activity planning to reservations and payments. Furthermore, a system is needed that can reflect individual opinions and propose highly satisfying options.

[0259] 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.

[0260] In this invention, the server includes means for collecting information, means for analyzing the collected information to estimate the individual's interests, characteristics, and emotions, and means for generating choices based on the estimation results. This makes it possible to plan activities that take into account the diverse interests of the individual.

[0261] "Means of collecting information" refers to processing mechanisms that acquire data from communication between individuals and use it as the basis for analysis.

[0262] "Means for analyzing information and estimating an individual's interests, characteristics, and emotions" refers to a processing mechanism that uses acquired data to evaluate an individual's nature and emotions, and to help propose specific actions.

[0263] "Means for generating options based on estimation results" refers to a processing mechanism that, based on analyzed data, makes multiple suggestions that best reflect the diverse interests and desires of individuals.

[0264] "Means of presenting options and supporting decision-making" refers to processing mechanisms that communicate generated proposals to individuals in an easily understandable way and support them in making quick decisions.

[0265] "Means for processing and paying for selected items" refers to a procedural mechanism for automatically and securely processing reservations and payments related to actions chosen by an individual.

[0266] This section describes embodiments for carrying out this invention. The invention is constructed as a system that efficiently supports activity planning that takes into account the diverse interests of participants by utilizing interpersonal communication.

[0267] 1. Information gathering and analysis

[0268] The server collects and analyzes information from the messaging platform. Because advanced data analysis is required, a dedicated server machine is necessary. For software, an analysis toolkit strong in natural language processing (for example, using open-source natural language processing libraries or commercial language processing APIs in combination) is recommended.

[0269] 2. Estimation of interests, traits, and emotions

[0270] The server estimates the individual's interests, characteristics, and emotions from the collected information. For this purpose, a generative AI model could be used for analysis. This model is trained on a large dataset to improve the accuracy of the analysis.

[0271] 3. Generation and Proposal Generation

[0272] Based on the analysis results, the server generates the optimal choices for each individual and proposes them to the terminal. A dynamic choice generation algorithm is used in this proposal process. The generated choices are communicated to the individual via a specific platform.

[0273] 4. Specific Examples

[0274] For example, consider planning a weekend meal for a group. The user can enter a prompt and give instructions such as: "Please suggest a weekend meal plan for our group. Based on the conversation data, please generate a program that selects a restaurant considering each member's preferences and budget, and suggests a date, time, and location." This makes it possible to automatically suggest appropriate options based on data extracted from the conversation.

[0275] In this way, servers, terminals, and users cooperate to provide activity plans that meet the diverse needs of each individual. This method enables efficient decision-making that satisfies all participants.

[0276] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0277] Step 1:

[0278] The server automatically collects communication data between users through the messaging platform API. This input data includes text messages, sender information, and transmission time. The server preprocesses this data, removes noise, and then stores it in a database for analysis. This prepares the data for efficient subsequent analysis.

[0279] Step 2:

[0280] The server analyzes the collected data using natural language processing technology. This process involves a generative AI model that estimates each user's interests, characteristics, and emotions from communication data as quantified indicators. It obtains preprocessed text data as input, generates profile information for each individual as output, and stores it in a database. This enables understanding of an individual's characteristics and forms the basis for optimal proposals based on them.

[0281] Step 3:

[0282] Based on the analysis results, the server generates activity options suitable for the individual. Using the analyzed profile information as input, it creates activity proposals most suitable for each user through a selection algorithm. Specifically, it presents candidates for date, time, location, and activity while considering the user's interests. This enables proposals that reflect the user's opinions.

[0283] Step 4:

[0284] The server presents the generated activity proposals to the user through the terminal. It receives the generated activity proposals as input and notifies the user's terminal as output. As a specific operation, it sends the details of the proposal (e.g., "How about having a picnic at City Park this Saturday at 3 pm?") to the user via a messaging platform. At this stage, the user can accept, modify the proposal, or request another proposal.

[0285] Step 5:

[0286] When the user approves the proposal, the terminal starts the procedure through a reservation management system. It obtains the user's approval information as input and receives confirmation of reservation completion as output. It uses a reservation system such as the OpenTable API to reserve the proposed activity and informs the user of convenient details. This process is important to ensure the overall feasibility of the proposal.

[0287] (Application Example 1)

[0288] 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."

[0289] Modern consumers are required to choose products and services that suit their interests from a wide variety of options, but this often takes time and effort due to the sheer number of choices. Furthermore, in group activities, it is difficult to propose activities that take into account the interests and preferences of all participants. In addition, there is a lack of effective means to present personalized information in real time using smart devices.

[0290] 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.

[0291] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of multiple participants, and means for generating activity suggestions based on the estimation results. This makes it possible to provide suggestions based on the characteristics of each participant in real time and support efficient decision-making.

[0292] "Conversation information" refers to communication data in audio or text format exchanged between participants.

[0293] "Analysis" is the process of processing acquired data to understand its meaning and trends.

[0294] "Interest" refers to the degree to which participants show interest in a particular theme or activity.

[0295] "Personality" refers to the characteristics that indicate the behavioral patterns and preference tendencies of individual participants.

[0296] "Emotion" refers to a psychological state inferred from the content of a conversation or from someone's actions.

[0297] An "activity suggestion" is a recommendation of behavior created based on analyzed interests, personality, and emotions.

[0298] "Reservation" refers to the process of securing selected activities or services in advance.

[0299] "Electronic payment" refers to a method of monetary transactions conducted using digital technology.

[0300] "Behavioral information" refers to data about participants' movements and choices within the environment.

[0301] "Product recommendations" refer to the act of recommending highly relevant products or services based on the participants' interests.

[0302] An "information infrastructure" is a system for collecting, storing, and accessing data.

[0303] A "smart device" is an electronic device equipped with internet connectivity that serves to provide information to users.

[0304] The system for implementing this invention mainly consists of a server, multiple smart devices, and a communication network. The server is responsible for receiving data from smart devices equipped with the ability to acquire conversational information and analyzing it. For analysis, the Google Cloud Speech-to-Text API and natural language processing libraries (such as NLTK and spaCy) can be used. The acquired conversational information is evaluated by a generative AI model (e.g., OpenAI GPT-3) to estimate the participants' interests, personalities, and emotions.

[0305] The server generates activity proposals based on this estimation result. This activity proposal includes content relevant to the user, based on data of products and services obtained from an external information infrastructure. As a result, product proposals and campaign information suitable for the user's characteristics are generated and displayed on smart devices such as smart glasses and smartphones. This information provision aims to support the user's decision-making. It also has a function to support procedures such as reservation and electronic payment.

[0306] As a specific example, consider the case where a user walking inside a shopping mall is wearing smart glasses. After the glasses analyze the user's conversation in real time and recognize that the user shows interest in pet-related products, they can display recommended products and discount information of pet shops on the screen.

[0307] As an example of a prompt sentence input to the generation AI model, a format such as "Generate relevant product and promotion information within 100 characters based on the interests obtained from the user's conversation data." can be considered.

[0308] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0309] Step 1:

[0310] The terminal acquires the user's conversation information as voice data. The acquired voice data is converted into text data by a voice recognition API (e.g., Google Cloud Speech-to-Text). In this conversion process, the voice waveform data is analyzed using a language model, and text data as a character string is output.

[0311] Step 2:

[0312] The server analyzes the acquired text data using natural language processing libraries (e.g., NLTK and spaCy). This analysis identifies context, emotions, and interests. The text data is tokenized, tagged with parts of speech, and subjected to dependency analysis before being processed into a format that can be input into a generative AI model. Here, keywords and phrases that indicate the user's interests and personality are extracted.

[0313] Step 3:

[0314] The server uses a generative AI model (e.g., OpenAI GPT-3) to create prompt sentences based on the keywords extracted in step 2. The server receives a prompt in the format of, "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data." The generated text is then output as a product suggestion tailored to the user.

[0315] Step 4:

[0316] The server compares product suggestions and promotional information with data from an external information infrastructure to determine the final display content. Here, it searches the database for relevant product information and campaigns, filters them, and selects the information that best suits the user's interests.

[0317] Step 5:

[0318] The terminal transmits the final selected product suggestions and promotional information to the user's smart device, displaying them in real time. For example, it can display information on the screen of smart glasses to support the user's decision-making. Links and QR codes can also be used in conjunction with this, allowing the user to directly access the products.

[0319] 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.

[0320] The embodiments for carrying out the present invention are described below. This system provides technology for effectively planning group activities by collecting and analyzing conversation data, recognizing user emotions using an emotion engine, and analyzing conversation data. The system operates on a messaging application and is integrated into an active group chat.

[0321] The server acquires conversation data in real time and uses an emotion engine to analyze users' emotions. This complements the results of analysis using conventional natural language processing techniques, enabling deeper level-based estimation of interests, personality, and emotions. Specifically, the emotion engine detects emotional tone and nuances from the user's text and determines the expectations and motivations that individual members have for the activity.

[0322] Based on these analysis results, the server generates and provides customized activity suggestions to the user. In particular, if the user is showing negative emotions, it will suggest activities that improve their mood, thus providing emotionally sensitive suggestions. In this way, flexible planning that takes into account the user's psychological state and group dynamics is promoted.

[0323] As a concrete example, consider a scenario where users A, B, and C get together and plan an activity for the weekend. The server uses its emotion engine to analyze the conversation and determine that user A is tired from work and needs to relax, and user B wants to try something new. Based on this, the server suggests options such as "a relaxing day at a nearby resort" or "a cooking class to try new dishes."

[0324] Once the user accepts the proposal, the terminal guides them through the booking process via text message. The server connects to the booking system to process the details and supports payment on the terminal. Furthermore, an emotional engine continuously monitors user feedback, enabling dynamic adjustments accordingly. This ensures a satisfactory plan for all participants.

[0325] This system, by incorporating features that take emotions into consideration, surpasses conventional activity planning systems and enables more adaptable action suggestions and decisions.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The user adds an emotion engine-enabled bot to a group chat within the LINE app. This action prepares the bot to begin monitoring all conversational interactions.

[0329] Step 2:

[0330] The server retrieves group chat conversation data in real time. The text of each message is sent to the server using the LINE Messaging API.

[0331] Step 3:

[0332] The server analyzes the conversation data obtained using natural language processing techniques. Natural language processing identifies each user's basic interests and topic priorities.

[0333] Step 4:

[0334] The server uses an emotion engine to recognize the user's emotions from the text. This engine detects emotion-specific keywords and phrases and determines the tone of the emotion, which is then classified into different emotion labels such as joy, anger, and sadness.

[0335] Step 5:

[0336] The server integrates data from both the emotion engine and natural language processing to generate customized activity suggestions based on each user's interests, personality, and emotions.

[0337] Step 6:

[0338] The server presents the generated activity suggestions to the user. It sends suggestions directly to the user using a message format, providing them with options.

[0339] Step 7:

[0340] The user selects and accepts the activity that interests them most from the presented suggestions. During this process, they can also ask the server any questions or inquire about other options.

[0341] Step 8:

[0342] On the device, the user starts the booking process for the selected activity. By clicking a link within the LINE app, the user enters the necessary details for the booking and completes the reservation.

[0343] Step 9:

[0344] After the reservation is complete, the server connects with an external payment system to execute a secure payment process. The user's payment information is verified, and the transaction is confirmed.

[0345] Step 10:

[0346] Users receive a final confirmation message regarding their planned activities. They can also receive reminder notifications as the activity date approaches.

[0347] (Example 2)

[0348] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0349] In modern society, there is a need to efficiently plan group activities while taking into account the psychological state and emotions of participants. However, conventional activity planning systems have the challenge of making proposals that adequately reflect the emotions and motivations of participants. Furthermore, these systems lack the flexibility to make adjustments based on post-activity feedback, so improvements are needed to increase participant satisfaction.

[0350] 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.

[0351] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of the participants, and means for utilizing a generative model that generates activity suggestions based on the estimation results. This makes it possible to generate activity suggestions that reflect the user's emotions and to dynamically adjust the suggestions based on subsequent feedback.

[0352] "Conversational information" refers to communication data such as text and audio exchanged between users.

[0353] "Analysis" refers to a series of processes that involve analyzing conversational information and extracting characteristics such as its content and emotional tone.

[0354] "Interest" refers to the degree to which participants show interest in a particular activity or topic.

[0355] "Personality" refers to the individual psychological characteristics that influence the behavior and reactions of participants.

[0356] "Emotion" refers to the emotional state that participants exhibit in response to a particular situation or stimulus.

[0357] A "generative model" refers to an algorithm or system for generating a new output from input data.

[0358] An "emotion engine" refers to a technology or system that can detect emotional tone and nuances from text data.

[0359] "Dynamic adjustment" refers to changing proposed content and system settings in real time based on analysis and feedback.

[0360] This invention is a system that supports the planning of group activities by comprehensively analyzing user emotions and proposing optimal activities based on those analyses. This system operates on a messaging platform and combines a server, terminals, and a generative AI model.

[0361] The server retrieves conversation information from messaging applications in real time. It connects to the platform using an API to collect communication data between users. This collected data is then analyzed using an emotion engine. This emotion engine utilizes the Google Cloud Natural Language API and general emotion analysis tools to detect emotional tone and nuances, thereby understanding the user's emotional state.

[0362] Based on the analysis results, the server generates activity suggestions using a generative AI model. This model considers the user's interests and emotional state, and creates suggestions using appropriate prompts. For example, a prompt might be "Use the user's conversation data to generate activity suggestions that take their mood into consideration."

[0363] The generated suggestions are presented to the user via the device. The device displays a notification on the messaging application, prompting the user to review the suggestions. If the suggestion is accepted, the device guides the user through the booking process, and the server connects to the booking system to process the necessary information. The server also analyzes the post-activity feedback again using the sentiment engine to help adjust future suggestions. This ensures that users can continue to experience satisfaction.

[0364] As a concrete example, when users A and B plan their weekend activities, the server analyzes their conversation to determine that user A needs relaxation and user B is seeking a new experience. Based on this analysis, the server provides activity suggestions that combine a "relaxing day for relaxation" with an "innovative cooking class," thereby creating a plan that meets the users' expectations.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The server retrieves conversation information in real time from the messaging platform. The input is message data between users, and the output is conversation information in text format. This conversation information is obtained by the server connecting to the platform via an API. The server then sends the retrieved conversation information to the next parsing step.

[0368] Step 2:

[0369] The server analyzes conversational information acquired using an emotion engine. The input is conversational information in text format, and the output is each user's emotional state and characteristics. Specifically, the emotion engine uses natural language processing techniques to analyze the text content and identify emotions such as positive, negative, and neutral. This result is then used as input to a generative model.

[0370] Step 3:

[0371] The server generates activity suggestions using a generative AI model based on the analysis results. The input is data about the user's emotional state, interests, and personality, and the output is a customized activity suggestion. The prompt is "Construct an appropriate activity suggestion based on the user's emotions." The generative AI model devises specific activities that match the user's psychological state and creates them as activity suggestions.

[0372] Step 4:

[0373] The terminal presents the generated activity suggestions to the user. The input is the activity suggestions received from the server, and the output is the activity details presented to the user as a notification. The terminal uses an existing messaging application to have the user review the suggestions. The user can select activities of interest from the presented options.

[0374] Step 5:

[0375] When a user selects an activity, the terminal guides them through the booking process. The input is the activity information selected by the user, and the output is the booking procedure details. The terminal provides a specific link, and the server connects to the booking system and processes the necessary information, allowing the user to complete the booking smoothly.

[0376] Step 6:

[0377] The server collects user feedback after an activity and analyzes it again using the emotion engine. The input is user feedback data, and the output is information for adjusting future suggestions. Based on the analyzed feedback, the server adjusts the generative AI model and uses it to make future suggestions more personalized.

[0378] (Application Example 2)

[0379] 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."

[0380] Modern conversation analysis systems using information and communication technology do not adequately consider user emotions or personalities, making it impossible to fully personalize individual experiences and product recommendations. Furthermore, the lack of flexible suggestions linked to real-world experiences makes it difficult for users to make purchases and experience choices optimized for them.

[0381] 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.

[0382] In this invention, the server includes means for acquiring conversation information and estimating the participants' interests, personalities, and emotions; means for generating activity suggestions based on the estimation results; and means for making reservations and payments for selected activities. This enables appropriate in-store experience suggestions and product suggestions tailored to the user's emotional state.

[0383] "Conversation information" refers to information about the content of communications and messages exchanged between users.

[0384] "Interest" refers to the degree to which a user is interested in a particular field or activity.

[0385] "Personality" is a set of psychological characteristics that influence a user's decision-making and behavior.

[0386] "Emotion" refers to a temporary feeling or reaction that a user experiences in response to a particular situation or stimulus.

[0387] An "activity proposal" is a concrete plan that, based on user interests and emotions, promotes experiences at physical stores and services.

[0388] A "reservation" is a pre-arranged procedure undertaken by a user to secure the provision of a specific product or service.

[0389] "Payment" refers to the process of paying for goods or services provided.

[0390] A "physical store" refers to a facility where users can directly experience or purchase products or services in a physical location.

[0391] "Product suggestions" refer to presenting products as potential purchase options, selected based on the user's emotions and interests.

[0392] The system for implementing this invention primarily consists of data exchange between a server and a terminal. The server first acquires conversation information between users in real time and analyzes this information using natural language processing and sentiment analysis techniques. Specifically, the Python TextBlob library assists in this sentiment analysis, playing a role in estimating the user's interests, personality, and emotions.

[0393] Based on the estimation results obtained, the server generates activity suggestions that correspond to the user's emotional state and interests. These activity suggestions include specific suggestions such as in-store experiences and products designed to improve the user's psychological state. Furthermore, the terminal presents the suggested information to the user and plays a role in supporting decision-making.

[0394] When a user selects a specific suggestion, the terminal assists with the booking and payment process. The server collaborates with external booking databases and payment systems to complete transactions quickly and securely. Furthermore, a generative AI model is used to continuously analyze user sentiment and feedback, collecting data to provide better activity suggestions.

[0395] For example, if a user mentions feeling tired, the system can suggest a relaxing experience. A possible prompt might be: "Generate a message suggesting an effective relaxation experience when the user is seeking relaxation."

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The server obtains conversation information between users via a messaging application. In this step, raw data in text format is input and stored on the server as conversation data.

[0399] Step 2:

[0400] The server analyzes the acquired conversational information using natural language processing and sentiment analysis techniques. Here, the Python TextBlob library is used to detect the emotional tone of the text and estimate the user's interests and emotions. This process yields emotion and interest metrics extracted from the conversation as output.

[0401] Step 3:

[0402] The server generates activity suggestions tailored to the user based on the analysis results. Using sentiment analysis data as input, the generation AI model generates suggestions and prompts. For example, it might create prompts such as, "Generate prompts for experiences that provide relaxation."

[0403] Step 4:

[0404] The terminal presents activity suggestions received from the server to the user, supporting decision-making. The user interface includes notifications and a dashboard displaying the suggested content. It also provides a user feedback function, recording user responses as input.

[0405] Step 5:

[0406] When a user selects a specific suggestion, the terminal guides them through the booking and payment process. This process uses the user's selected activity as input to call the booking system and payment API, and outputs booking confirmation and payment information.

[0407] Step 6:

[0408] The server continuously monitors and analyzes user feedback using a generative AI model, and utilizes this feedback to improve the suggestions. This results in more personalized activity suggestions for the future, enhancing the user experience. Feedback data is input, and adjustment data for generating the next activity suggestion is output.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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".

[0425] The embodiments for carrying out the present invention are described below. This system provides technology for efficiently planning group activities by acquiring and analyzing conversation data. Specifically, it is implemented as a bot that can be used by users through messaging platforms such as LINE. This bot acquires data exchanged by participants in their everyday conversations in real time and analyzes its content to accurately estimate the interests, personalities, and emotions of the participants.

[0426] Based on this analysis, the server generates and proposes an appropriate activity plan to the user. For example, if participant A prefers relaxing activities and participant B prefers active outdoor activities, the bot will present a balanced activity plan that takes both of their interests into account. This proposal also includes detailed information such as specific dates and times, locations, and necessary preparations, to support the user's decision-making.

[0427] Once a decision is made based on the proposed activity plan, the reservation process begins on the terminal. The server works in conjunction with the reservation management system to provide the necessary information. Payments can also be processed securely, and settlement is possible in a simple manner, especially when multiple participants are involved.

[0428] As a concrete example, let's assume three users, X, Y, and Z, are planning a meal together. They add this bot to the group and begin planning. The server analyzes the users' preferences and budget from the conversation and makes suggestions such as, "X likes Japanese food, but Y tends to enjoy Italian food. I'll recommend some restaurants, so please specify a date and time." After the users accept the suggestions, they can make reservations and payments directly from their devices, completing the entire process efficiently.

[0429] Thus, the present invention is a system that enables quick and satisfactory decision-making while taking into account the diverse interests of participants, and facilitates planning in daily group activities.

[0430] The following describes the processing flow.

[0431] Step 1:

[0432] Users add the system's bot to a group chat within the LINE app. This action prepares the bot to participate in future conversations and collect data.

[0433] Step 2:

[0434] The server uses the LINE Messaging API to receive message content in real time to acquire conversation data within the group chat. At this stage, the text information of each message is obtained.

[0435] Step 3:

[0436] The server analyzes the acquired conversation data using natural language processing (NLP) techniques. Specifically, it performs text tokenization, contextual understanding, and sentiment analysis to identify participants' interests, personalities, and emotions.

[0437] Step 4:

[0438] The server generates an appropriate activity plan based on the analysis results. In this process, it utilizes machine learning models that reference historical data and external information sources to create suggestions that match the user's interests.

[0439] Step 5:

[0440] The server proposes the generated activity plan to the user. Specifically, it posts suggestion messages naturally within the conversation, presenting a range of activity options.

[0441] Step 6:

[0442] Users discuss the proposed activities within their group and make a final decision. If necessary, they can request additional information or alternative suggestions from the bot.

[0443] Step 7:

[0444] On your device, begin the booking process for your selected activity. Enter your details via the link or form within the LINE app to complete your booking.

[0445] Step 8:

[0446] The server works in conjunction with an external reservation system to secure reservation information. If payment is required, it accesses the payment system and executes the payment.

[0447] Step 9:

[0448] The user receives a message confirming that their reservation and payment are complete. They then receive a reminder notification for the day of the activity, allowing them to prepare for it.

[0449] (Example 1)

[0450] 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."

[0451] In modern social life, it is crucial to efficiently plan activities based on participants' interests and preferences through interpersonal communication. However, accurately understanding participants' hobbies and desires is difficult, and there is a need for a system that smoothly handles all procedures, from activity planning to reservations and payments. Furthermore, a system is needed that can reflect individual opinions and propose highly satisfying options.

[0452] 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.

[0453] In this invention, the server includes means for collecting information, means for analyzing the collected information to estimate the individual's interests, characteristics, and emotions, and means for generating choices based on the estimation results. This makes it possible to plan activities that take into account the diverse interests of the individual.

[0454] "Means of collecting information" refers to processing mechanisms that acquire data from communication between individuals and use it as the basis for analysis.

[0455] "Means for analyzing information and estimating an individual's interests, characteristics, and emotions" refers to a processing mechanism that uses acquired data to evaluate an individual's nature and emotions, and to help propose specific actions.

[0456] "Means for generating options based on estimation results" refers to a processing mechanism that, based on analyzed data, makes multiple suggestions that best reflect the diverse interests and desires of individuals.

[0457] "Means of presenting options and supporting decision-making" refers to processing mechanisms that communicate generated proposals to individuals in an easily understandable way and support them in making quick decisions.

[0458] "Means for processing and paying for selected items" refers to a procedural mechanism for automatically and securely processing reservations and payments related to actions chosen by an individual.

[0459] This section describes embodiments for carrying out this invention. The invention is constructed as a system that efficiently supports activity planning that takes into account the diverse interests of participants by utilizing interpersonal communication.

[0460] 1. Information gathering and analysis

[0461] The server collects and analyzes information from the messaging platform. Because advanced data analysis is required, a dedicated server machine is necessary. For software, an analysis toolkit strong in natural language processing (for example, using open-source natural language processing libraries or commercial language processing APIs in combination) is recommended.

[0462] 2. Estimation of interests, traits, and emotions

[0463] The server estimates the individual's interests, characteristics, and emotions from the collected information. For this purpose, a generative AI model could be used for analysis. This model is trained on a large dataset to improve the accuracy of the analysis.

[0464] 3. Generation and Proposal Generation

[0465] Based on the analysis results, the server generates the optimal choices for each individual and proposes them to the terminal. A dynamic choice generation algorithm is used in this proposal process. The generated choices are communicated to the individual via a specific platform.

[0466] 4. Specific Examples

[0467] For example, consider planning a weekend meal for a group. The user can enter a prompt and give instructions such as: "Please suggest a weekend meal plan for our group. Based on the conversation data, please generate a program that selects a restaurant considering each member's preferences and budget, and suggests a date, time, and location." This makes it possible to automatically suggest appropriate options based on data extracted from the conversation.

[0468] In this way, servers, terminals, and users cooperate to provide activity plans that meet the diverse needs of each individual. This method enables efficient decision-making that satisfies all participants.

[0469] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0470] Step 1:

[0471] The server automatically collects communication data between users through the messaging platform API. This input data includes text messages, sender information, and transmission time. The server preprocesses this data, removes noise, and then stores it in a database for analysis. This prepares the data for efficient subsequent analysis.

[0472] Step 2:

[0473] The server analyzes the collected data using natural language processing technology. This process involves a generative AI model that estimates each user's interests, characteristics, and emotions as quantifiable indicators from the communication data. Preprocessed text data is taken as input, and individual profile information is generated as output and stored in a database. This allows for an understanding of individual characteristics and lays the foundation for optimal suggestions based on them.

[0474] Step 3:

[0475] The server generates activity options tailored to each individual based on the analysis results. Using the analyzed profile information as input, it creates activity suggestions that best suit each user through a selection generation algorithm. Specifically, it presents candidate dates, times, locations, and activities, taking into account the user's interests. This allows for suggestions that reflect the user's opinions.

[0476] Step 4:

[0477] The server presents the generated activity proposal to the user via the terminal. It receives the generated activity proposal as input and notifies the user's terminal as output. Specifically, it sends the details of the proposal (for example, "How about a picnic at City Park this Saturday at 3pm?") to the user via the messaging platform. At this stage, the user can accept or modify the proposal, or request a different proposal.

[0478] Step 5:

[0479] The terminal initiates the process through the reservation management system once the user approves the proposal. It takes user approval information as input and receives confirmation of reservation completion as output. Using a reservation system such as the OpenTable API, it reserves the proposed activity and informs the user of the necessary details. This process is crucial to ensuring the overall feasibility of the proposal.

[0480] (Application Example 1)

[0481] 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."

[0482] Modern consumers are required to choose products and services that suit their interests from a wide variety of options, but this often takes time and effort due to the sheer number of choices. Furthermore, in group activities, it is difficult to propose activities that take into account the interests and preferences of all participants. In addition, there is a lack of effective means to present personalized information in real time using smart devices.

[0483] 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.

[0484] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of multiple participants, and means for generating activity suggestions based on the estimation results. This makes it possible to provide suggestions based on the characteristics of each participant in real time and support efficient decision-making.

[0485] "Conversation information" refers to communication data in audio or text format exchanged between participants.

[0486] "Analysis" is the process of processing acquired data to understand its meaning and trends.

[0487] "Interest" refers to the degree to which participants show interest in a particular theme or activity.

[0488] "Personality" refers to the characteristics that indicate the behavioral patterns and preference tendencies of individual participants.

[0489] "Emotion" refers to a psychological state inferred from the content of a conversation or from someone's actions.

[0490] An "activity suggestion" is a recommendation of behavior created based on analyzed interests, personality, and emotions.

[0491] "Reservation" refers to the process of securing selected activities or services in advance.

[0492] "Electronic payment" refers to a method of monetary transactions conducted using digital technology.

[0493] "Behavioral information" refers to data about participants' movements and choices within the environment.

[0494] "Product recommendations" refer to the act of recommending highly relevant products or services based on the participants' interests.

[0495] An "information infrastructure" is a system for collecting, storing, and accessing data.

[0496] A "smart device" is an electronic device equipped with internet connectivity that serves to provide information to users.

[0497] The system for implementing this invention mainly consists of a server, multiple smart devices, and a communication network. The server is responsible for receiving data from smart devices equipped with the ability to acquire conversational information and analyzing it. For analysis, the Google Cloud Speech-to-Text API and natural language processing libraries (such as NLTK and spaCy) can be used. The acquired conversational information is evaluated by a generative AI model (e.g., OpenAI GPT-3) to estimate the participants' interests, personalities, and emotions.

[0498] The server generates activity suggestions based on these estimation results. These activity suggestions include user-related content based on product and service data obtained from an external information infrastructure. This generates product suggestions and campaign information tailored to the user's characteristics, which are displayed on smart devices such as smart glasses and smartphones. This information provision aims to support the user's decision-making. It also includes functions to support reservation and electronic payment procedures.

[0499] As a concrete example, consider a user walking through a shopping mall wearing smart glasses. These glasses can analyze the user's conversation in real time, recognize their interest in pet-related products, and then display recommended products and discount information from pet shops on the screen.

[0500] An example of a prompt to input into a generative AI model is: "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data."

[0501] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0502] Step 1:

[0503] The device acquires user conversation information as audio data. The acquired audio data is converted into text data by a speech recognition API (e.g., Google Cloud Speech-to-Text). In this conversion process, the audio waveform data is analyzed using a language model, and text data is output as a string.

[0504] Step 2:

[0505] The server analyzes the acquired text data using natural language processing libraries (e.g., NLTK and spaCy). This analysis identifies context, emotions, and interests. The text data is tokenized, tagged with parts of speech, and subjected to dependency analysis before being processed into a format that can be input into a generative AI model. Here, keywords and phrases that indicate the user's interests and personality are extracted.

[0506] Step 3:

[0507] The server uses a generative AI model (e.g., OpenAI GPT-3) to create prompt sentences based on the keywords extracted in step 2. The server receives a prompt in the format of, "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data." The generated text is then output as a product suggestion tailored to the user.

[0508] Step 4:

[0509] The server compares product suggestions and promotional information with data from an external information infrastructure to determine the final display content. Here, it searches the database for relevant product information and campaigns, filters them, and selects the information that best suits the user's interests.

[0510] Step 5:

[0511] The terminal transmits the final selected product suggestions and promotional information to the user's smart device, displaying them in real time. For example, it can display information on the screen of smart glasses to support the user's decision-making. Links and QR codes can also be used in conjunction with this, allowing the user to directly access the products.

[0512] 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.

[0513] The embodiments for carrying out the present invention are described below. This system provides technology for effectively planning group activities by collecting and analyzing conversation data, recognizing user emotions using an emotion engine, and analyzing conversation data. The system operates on a messaging application and is integrated into an active group chat.

[0514] The server acquires conversation data in real time and uses an emotion engine to analyze users' emotions. This complements the results of analysis using conventional natural language processing techniques, enabling deeper level-based estimation of interests, personality, and emotions. Specifically, the emotion engine detects emotional tone and nuances from the user's text and determines the expectations and motivations that individual members have for the activity.

[0515] Based on these analysis results, the server generates and provides customized activity suggestions to the user. In particular, if the user is showing negative emotions, it will suggest activities that improve their mood, thus providing emotionally sensitive suggestions. In this way, flexible planning that takes into account the user's psychological state and group dynamics is promoted.

[0516] As a concrete example, consider a scenario where users A, B, and C get together and plan an activity for the weekend. The server uses its emotion engine to analyze the conversation and determine that user A is tired from work and needs to relax, and user B wants to try something new. Based on this, the server suggests options such as "a relaxing day at a nearby resort" or "a cooking class to try new dishes."

[0517] Once the user accepts the proposal, the terminal guides them through the booking process via text message. The server connects to the booking system to process the details and supports payment on the terminal. Furthermore, an emotional engine continuously monitors user feedback, enabling dynamic adjustments accordingly. This ensures a satisfactory plan for all participants.

[0518] This system, by incorporating features that take emotions into consideration, surpasses conventional activity planning systems and enables more adaptable action suggestions and decisions.

[0519] The following describes the processing flow.

[0520] Step 1:

[0521] The user adds an emotion engine-enabled bot to a group chat within the LINE app. This action prepares the bot to begin monitoring all conversational interactions.

[0522] Step 2:

[0523] The server retrieves group chat conversation data in real time. The text of each message is sent to the server using the LINE Messaging API.

[0524] Step 3:

[0525] The server analyzes the conversation data obtained using natural language processing techniques. Natural language processing identifies each user's basic interests and topic priorities.

[0526] Step 4:

[0527] The server uses an emotion engine to recognize the user's emotions from the text. This engine detects emotion-specific keywords and phrases and determines the tone of the emotion, which is then classified into different emotion labels such as joy, anger, and sadness.

[0528] Step 5:

[0529] The server integrates data from both the emotion engine and natural language processing to generate customized activity suggestions based on each user's interests, personality, and emotions.

[0530] Step 6:

[0531] The server presents the generated activity suggestions to the user. It sends suggestions directly to the user using a message format, providing them with options.

[0532] Step 7:

[0533] The user selects and accepts the activity that interests them most from the presented suggestions. During this process, they can also ask the server any questions or inquire about other options.

[0534] Step 8:

[0535] On the device, the user starts the booking process for the selected activity. By clicking a link within the LINE app, the user enters the necessary details for the booking and completes the reservation.

[0536] Step 9:

[0537] After the reservation is complete, the server connects with an external payment system to execute a secure payment process. The user's payment information is verified, and the transaction is confirmed.

[0538] Step 10:

[0539] Users receive a final confirmation message regarding their planned activities. They can also receive reminder notifications as the activity date approaches.

[0540] (Example 2)

[0541] 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."

[0542] In modern society, there is a need to efficiently plan group activities while taking into account the psychological state and emotions of participants. However, conventional activity planning systems have the challenge of making proposals that adequately reflect the emotions and motivations of participants. Furthermore, these systems lack the flexibility to make adjustments based on post-activity feedback, so improvements are needed to increase participant satisfaction.

[0543] 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.

[0544] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of the participants, and means for utilizing a generative model that generates activity suggestions based on the estimation results. This makes it possible to generate activity suggestions that reflect the user's emotions and to dynamically adjust the suggestions based on subsequent feedback.

[0545] "Conversational information" refers to communication data such as text and audio exchanged between users.

[0546] "Analysis" refers to a series of processes that involve analyzing conversational information and extracting characteristics such as its content and emotional tone.

[0547] "Interest" refers to the degree to which participants show interest in a particular activity or topic.

[0548] "Personality" refers to the individual psychological characteristics that influence the behavior and reactions of participants.

[0549] "Emotion" refers to the emotional state that participants exhibit in response to a particular situation or stimulus.

[0550] A "generative model" refers to an algorithm or system for generating a new output from input data.

[0551] An "emotion engine" refers to a technology or system that can detect emotional tone and nuances from text data.

[0552] "Dynamic adjustment" refers to changing proposed content and system settings in real time based on analysis and feedback.

[0553] This invention is a system that supports the planning of group activities by comprehensively analyzing user emotions and proposing optimal activities based on those analyses. This system operates on a messaging platform and combines a server, terminals, and a generative AI model.

[0554] The server retrieves conversation information from messaging applications in real time. It connects to the platform using an API to collect communication data between users. This collected data is then analyzed using an emotion engine. This emotion engine utilizes the Google Cloud Natural Language API and general emotion analysis tools to detect emotional tone and nuances, thereby understanding the user's emotional state.

[0555] Based on the analysis results, the server generates activity suggestions using a generative AI model. This model considers the user's interests and emotional state, and creates suggestions using appropriate prompts. For example, a prompt might be "Use the user's conversation data to generate activity suggestions that take their mood into consideration."

[0556] The generated suggestions are presented to the user via the device. The device displays a notification on the messaging application, prompting the user to review the suggestions. If the suggestion is accepted, the device guides the user through the booking process, and the server connects to the booking system to process the necessary information. The server also analyzes the post-activity feedback again using the sentiment engine to help adjust future suggestions. This ensures that users can continue to experience satisfaction.

[0557] As a concrete example, when users A and B plan their weekend activities, the server analyzes their conversation to determine that user A needs relaxation and user B is seeking a new experience. Based on this analysis, the server provides activity suggestions that combine a "relaxing day for relaxation" with an "innovative cooking class," thereby creating a plan that meets the users' expectations.

[0558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0559] Step 1:

[0560] The server retrieves conversation information in real time from the messaging platform. The input is message data between users, and the output is conversation information in text format. This conversation information is obtained by the server connecting to the platform via an API. The server then sends the retrieved conversation information to the next parsing step.

[0561] Step 2:

[0562] The server analyzes conversational information acquired using an emotion engine. The input is conversational information in text format, and the output is each user's emotional state and characteristics. Specifically, the emotion engine uses natural language processing techniques to analyze the text content and identify emotions such as positive, negative, and neutral. This result is then used as input to a generative model.

[0563] Step 3:

[0564] The server generates activity suggestions using a generative AI model based on the analysis results. The input is data about the user's emotional state, interests, and personality, and the output is a customized activity suggestion. The prompt is "Construct an appropriate activity suggestion based on the user's emotions." The generative AI model devises specific activities that match the user's psychological state and creates them as activity suggestions.

[0565] Step 4:

[0566] The terminal presents the generated activity suggestions to the user. The input is the activity suggestions received from the server, and the output is the activity details presented to the user as a notification. The terminal uses an existing messaging application to have the user review the suggestions. The user can select activities of interest from the presented options.

[0567] Step 5:

[0568] When a user selects an activity, the terminal guides them through the booking process. The input is the activity information selected by the user, and the output is the booking procedure details. The terminal provides a specific link, and the server connects to the booking system and processes the necessary information, allowing the user to complete the booking smoothly.

[0569] Step 6:

[0570] The server collects user feedback after an activity and analyzes it again using the emotion engine. The input is user feedback data, and the output is information for adjusting future suggestions. Based on the analyzed feedback, the server adjusts the generative AI model and uses it to make future suggestions more personalized.

[0571] (Application Example 2)

[0572] 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."

[0573] Modern conversation analysis systems using information and communication technology do not adequately consider user emotions or personalities, making it impossible to fully personalize individual experiences and product recommendations. Furthermore, the lack of flexible suggestions linked to real-world experiences makes it difficult for users to make purchases and experience choices optimized for them.

[0574] 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.

[0575] In this invention, the server includes means for acquiring conversation information and estimating the participants' interests, personalities, and emotions; means for generating activity suggestions based on the estimation results; and means for making reservations and payments for selected activities. This enables appropriate in-store experience suggestions and product suggestions tailored to the user's emotional state.

[0576] "Conversation information" refers to information about the content of communications and messages exchanged between users.

[0577] "Interest" refers to the degree to which a user is interested in a particular field or activity.

[0578] "Personality" is a set of psychological characteristics that influence a user's decision-making and behavior.

[0579] "Emotion" refers to a temporary feeling or reaction that a user experiences in response to a particular situation or stimulus.

[0580] An "activity proposal" is a concrete plan that, based on user interests and emotions, promotes experiences at physical stores and services.

[0581] A "reservation" is a pre-arranged procedure undertaken by a user to secure the provision of a specific product or service.

[0582] "Payment" refers to the process of paying for goods or services provided.

[0583] A "physical store" refers to a facility where users can directly experience or purchase products or services in a physical location.

[0584] "Product suggestions" refer to presenting products as potential purchase options, selected based on the user's emotions and interests.

[0585] The system for implementing this invention primarily consists of data exchange between a server and a terminal. The server first acquires conversation information between users in real time and analyzes this information using natural language processing and sentiment analysis techniques. Specifically, the Python TextBlob library assists in this sentiment analysis, playing a role in estimating the user's interests, personality, and emotions.

[0586] Based on the estimation results obtained, the server generates activity suggestions that correspond to the user's emotional state and interests. These activity suggestions include specific suggestions such as in-store experiences and products designed to improve the user's psychological state. Furthermore, the terminal presents the suggested information to the user and plays a role in supporting decision-making.

[0587] When a user selects a specific suggestion, the terminal assists with the booking and payment process. The server collaborates with external booking databases and payment systems to complete transactions quickly and securely. Furthermore, a generative AI model is used to continuously analyze user sentiment and feedback, collecting data to provide better activity suggestions.

[0588] For example, if a user mentions feeling tired, the system can suggest a relaxing experience. A possible prompt might be: "Generate a message suggesting an effective relaxation experience when the user is seeking relaxation."

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server obtains conversation information between users via a messaging application. In this step, raw data in text format is input and stored on the server as conversation data.

[0592] Step 2:

[0593] The server analyzes the acquired conversational information using natural language processing and sentiment analysis techniques. Here, the Python TextBlob library is used to detect the emotional tone of the text and estimate the user's interests and emotions. This process yields emotion and interest metrics extracted from the conversation as output.

[0594] Step 3:

[0595] The server generates activity suggestions tailored to the user based on the analysis results. Using sentiment analysis data as input, the generation AI model generates suggestions and prompts. For example, it might create prompts such as, "Generate prompts for experiences that provide relaxation."

[0596] Step 4:

[0597] The terminal presents activity suggestions received from the server to the user, supporting decision-making. The user interface includes notifications and a dashboard displaying the suggested content. It also provides a user feedback function, recording user responses as input.

[0598] Step 5:

[0599] When a user selects a specific suggestion, the terminal guides them through the booking and payment process. This process uses the user's selected activity as input to call the booking system and payment API, and outputs booking confirmation and payment information.

[0600] Step 6:

[0601] The server continuously monitors and analyzes user feedback using a generative AI model, and utilizes this feedback to improve the suggestions. This results in more personalized activity suggestions for the future, enhancing the user experience. Feedback data is input, and adjustment data for generating the next activity suggestion is output.

[0602] 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.

[0603] 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.

[0604] 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.

[0605] [Fourth Embodiment]

[0606] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0607] 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.

[0608] 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).

[0609] 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.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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.

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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".

[0619] The embodiments for carrying out the present invention are described below. This system provides technology for efficiently planning group activities by acquiring and analyzing conversation data. Specifically, it is implemented as a bot that can be used by users through messaging platforms such as LINE. This bot acquires data exchanged by participants in their everyday conversations in real time and analyzes its content to accurately estimate the interests, personalities, and emotions of the participants.

[0620] Based on this analysis, the server generates and proposes an appropriate activity plan to the user. For example, if participant A prefers relaxing activities and participant B prefers active outdoor activities, the bot will present a balanced activity plan that takes both of their interests into account. This proposal also includes detailed information such as specific dates and times, locations, and necessary preparations, to support the user's decision-making.

[0621] Once a decision is made based on the proposed activity plan, the reservation process begins on the terminal. The server works in conjunction with the reservation management system to provide the necessary information. Payments can also be processed securely, and settlement is possible in a simple manner, especially when multiple participants are involved.

[0622] As a concrete example, let's assume three users, X, Y, and Z, are planning a meal together. They add this bot to the group and begin planning. The server analyzes the users' preferences and budget from the conversation and makes suggestions such as, "X likes Japanese food, but Y tends to enjoy Italian food. I'll recommend some restaurants, so please specify a date and time." After the users accept the suggestions, they can make reservations and payments directly from their devices, completing the entire process efficiently.

[0623] Thus, the present invention is a system that enables quick and satisfactory decision-making while taking into account the diverse interests of participants, and facilitates planning in daily group activities.

[0624] The following describes the processing flow.

[0625] Step 1:

[0626] Users add the system's bot to a group chat within the LINE app. This action prepares the bot to participate in future conversations and collect data.

[0627] Step 2:

[0628] The server uses the LINE Messaging API to receive message content in real time to acquire conversation data within the group chat. At this stage, the text information of each message is obtained.

[0629] Step 3:

[0630] The server analyzes the acquired conversation data using natural language processing (NLP) techniques. Specifically, it performs text tokenization, contextual understanding, and sentiment analysis to identify participants' interests, personalities, and emotions.

[0631] Step 4:

[0632] The server generates an appropriate activity plan based on the analysis results. In this process, it utilizes machine learning models that reference historical data and external information sources to create suggestions that match the user's interests.

[0633] Step 5:

[0634] The server proposes the generated activity plan to the user. Specifically, it posts suggestion messages naturally within the conversation, presenting a range of activity options.

[0635] Step 6:

[0636] Users discuss the proposed activities within their group and make a final decision. If necessary, they can request additional information or alternative suggestions from the bot.

[0637] Step 7:

[0638] On your device, begin the booking process for your selected activity. Enter your details via the link or form within the LINE app to complete your booking.

[0639] Step 8:

[0640] The server works in conjunction with an external reservation system to secure reservation information. If payment is required, it accesses the payment system and executes the payment.

[0641] Step 9:

[0642] The user receives a message confirming that their reservation and payment are complete. They then receive a reminder notification for the day of the activity, allowing them to prepare for it.

[0643] (Example 1)

[0644] 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".

[0645] In modern social life, it is crucial to efficiently plan activities based on participants' interests and preferences through interpersonal communication. However, accurately understanding participants' hobbies and desires is difficult, and there is a need for a system that smoothly handles all procedures, from activity planning to reservations and payments. Furthermore, a system is needed that can reflect individual opinions and propose highly satisfying options.

[0646] 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.

[0647] In this invention, the server includes means for collecting information, means for analyzing the collected information to estimate the individual's interests, characteristics, and emotions, and means for generating choices based on the estimation results. This makes it possible to plan activities that take into account the diverse interests of the individual.

[0648] "Means of collecting information" refers to processing mechanisms that acquire data from communication between individuals and use it as the basis for analysis.

[0649] "Means for analyzing information and estimating an individual's interests, characteristics, and emotions" refers to a processing mechanism that uses acquired data to evaluate an individual's nature and emotions, and to help propose specific actions.

[0650] "Means for generating options based on estimation results" refers to a processing mechanism that, based on analyzed data, makes multiple suggestions that best reflect the diverse interests and desires of individuals.

[0651] "Means of presenting options and supporting decision-making" refers to processing mechanisms that communicate generated proposals to individuals in an easily understandable way and support them in making quick decisions.

[0652] "Means for processing and paying for selected items" refers to a procedural mechanism for automatically and securely processing reservations and payments related to actions chosen by an individual.

[0653] This section describes embodiments for carrying out this invention. The invention is constructed as a system that efficiently supports activity planning that takes into account the diverse interests of participants by utilizing interpersonal communication.

[0654] 1. Information gathering and analysis

[0655] The server collects and analyzes information from the messaging platform. Because advanced data analysis is required, a dedicated server machine is necessary. For software, an analysis toolkit strong in natural language processing (for example, using open-source natural language processing libraries or commercial language processing APIs in combination) is recommended.

[0656] 2. Estimation of interests, traits, and emotions

[0657] The server estimates the individual's interests, characteristics, and emotions from the collected information. For this purpose, a generative AI model could be used for analysis. This model is trained on a large dataset to improve the accuracy of the analysis.

[0658] 3. Generation and Proposal Generation

[0659] Based on the analysis results, the server generates the optimal choices for each individual and proposes them to the terminal. A dynamic choice generation algorithm is used in this proposal process. The generated choices are communicated to the individual via a specific platform.

[0660] 4. Specific Examples

[0661] For example, consider planning a weekend meal for a group. The user can enter a prompt and give instructions such as: "Please suggest a weekend meal plan for our group. Based on the conversation data, please generate a program that selects a restaurant considering each member's preferences and budget, and suggests a date, time, and location." This makes it possible to automatically suggest appropriate options based on data extracted from the conversation.

[0662] In this way, servers, terminals, and users cooperate to provide activity plans that meet the diverse needs of each individual. This method enables efficient decision-making that satisfies all participants.

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] The server automatically collects communication data between users through the messaging platform API. This input data includes text messages, sender information, and transmission time. The server preprocesses this data, removes noise, and then stores it in a database for analysis. This prepares the data for efficient subsequent analysis.

[0666] Step 2:

[0667] The server analyzes the collected data using natural language processing technology. This process involves a generative AI model that estimates each user's interests, characteristics, and emotions as quantifiable indicators from the communication data. Preprocessed text data is taken as input, and individual profile information is generated as output and stored in a database. This allows for an understanding of individual characteristics and lays the foundation for optimal suggestions based on them.

[0668] Step 3:

[0669] The server generates activity options tailored to each individual based on the analysis results. Using the analyzed profile information as input, it creates activity suggestions that best suit each user through a selection generation algorithm. Specifically, it presents candidate dates, times, locations, and activities, taking into account the user's interests. This allows for suggestions that reflect the user's opinions.

[0670] Step 4:

[0671] The server presents the generated activity proposal to the user via the terminal. It receives the generated activity proposal as input and notifies the user's terminal as output. Specifically, it sends the details of the proposal (for example, "How about a picnic at City Park this Saturday at 3pm?") to the user via the messaging platform. At this stage, the user can accept or modify the proposal, or request a different proposal.

[0672] Step 5:

[0673] The terminal initiates the process through the reservation management system once the user approves the proposal. It takes user approval information as input and receives confirmation of reservation completion as output. Using a reservation system such as the OpenTable API, it reserves the proposed activity and informs the user of the necessary details. This process is crucial to ensuring the overall feasibility of the proposal.

[0674] (Application Example 1)

[0675] 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".

[0676] Modern consumers are required to choose products and services that suit their interests from a wide variety of options, but this often takes time and effort due to the sheer number of choices. Furthermore, in group activities, it is difficult to propose activities that take into account the interests and preferences of all participants. In addition, there is a lack of effective means to present personalized information in real time using smart devices.

[0677] 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.

[0678] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of multiple participants, and means for generating activity suggestions based on the estimation results. This makes it possible to provide suggestions based on the characteristics of each participant in real time and support efficient decision-making.

[0679] "Conversation information" refers to communication data in audio or text format exchanged between participants.

[0680] "Analysis" is the process of processing acquired data to understand its meaning and trends.

[0681] "Interest" refers to the degree to which participants show interest in a particular theme or activity.

[0682] "Personality" refers to the characteristics that indicate the behavioral patterns and preference tendencies of individual participants.

[0683] "Emotion" refers to a psychological state inferred from the content of a conversation or from someone's actions.

[0684] An "activity suggestion" is a recommendation of behavior created based on analyzed interests, personality, and emotions.

[0685] "Reservation" refers to the process of securing selected activities or services in advance.

[0686] "Electronic payment" refers to a method of monetary transactions conducted using digital technology.

[0687] "Behavioral information" refers to data about participants' movements and choices within the environment.

[0688] "Product recommendations" refer to the act of recommending highly relevant products or services based on the participants' interests.

[0689] An "information infrastructure" is a system for collecting, storing, and accessing data.

[0690] A "smart device" is an electronic device equipped with internet connectivity that serves to provide information to users.

[0691] The system for implementing this invention mainly consists of a server, multiple smart devices, and a communication network. The server is responsible for receiving data from smart devices equipped with the ability to acquire conversational information and analyzing it. For analysis, the Google Cloud Speech-to-Text API and natural language processing libraries (such as NLTK and spaCy) can be used. The acquired conversational information is evaluated by a generative AI model (e.g., OpenAI GPT-3) to estimate the participants' interests, personalities, and emotions.

[0692] The server generates activity suggestions based on these estimation results. These activity suggestions include user-related content based on product and service data obtained from an external information infrastructure. This generates product suggestions and campaign information tailored to the user's characteristics, which are displayed on smart devices such as smart glasses and smartphones. This information provision aims to support the user's decision-making. It also includes functions to support reservation and electronic payment procedures.

[0693] As a concrete example, consider a user walking through a shopping mall wearing smart glasses. These glasses can analyze the user's conversation in real time, recognize their interest in pet-related products, and then display recommended products and discount information from pet shops on the screen.

[0694] An example of a prompt to input into a generative AI model is: "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data."

[0695] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0696] Step 1:

[0697] The device acquires user conversation information as audio data. The acquired audio data is converted into text data by a speech recognition API (e.g., Google Cloud Speech-to-Text). In this conversion process, the audio waveform data is analyzed using a language model, and text data is output as a string.

[0698] Step 2:

[0699] The server analyzes the acquired text data using natural language processing libraries (e.g., NLTK and spaCy). This analysis identifies context, emotions, and interests. The text data is tokenized, tagged with parts of speech, and subjected to dependency analysis before being processed into a format that can be input into a generative AI model. Here, keywords and phrases that indicate the user's interests and personality are extracted.

[0700] Step 3:

[0701] The server uses a generative AI model (e.g., OpenAI GPT-3) to create prompt sentences based on the keywords extracted in step 2. The server receives a prompt in the format of, "Generate relevant product and promotional information of 100 characters or less based on the user's interests derived from their conversation data." The generated text is then output as a product suggestion tailored to the user.

[0702] Step 4:

[0703] The server compares product suggestions and promotional information with data from an external information infrastructure to determine the final display content. Here, it searches the database for relevant product information and campaigns, filters them, and selects the information that best suits the user's interests.

[0704] Step 5:

[0705] The terminal transmits the final selected product suggestions and promotional information to the user's smart device, displaying them in real time. For example, it can display information on the screen of smart glasses to support the user's decision-making. Links and QR codes can also be used in conjunction with this, allowing the user to directly access the products.

[0706] 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.

[0707] The embodiments for carrying out the present invention are described below. This system provides technology for effectively planning group activities by collecting and analyzing conversation data, recognizing user emotions using an emotion engine, and analyzing conversation data. The system operates on a messaging application and is integrated into an active group chat.

[0708] The server acquires conversation data in real time and uses an emotion engine to analyze users' emotions. This complements the results of analysis using conventional natural language processing techniques, enabling deeper level-based estimation of interests, personality, and emotions. Specifically, the emotion engine detects emotional tone and nuances from the user's text and determines the expectations and motivations that individual members have for the activity.

[0709] Based on these analysis results, the server generates and provides customized activity suggestions to the user. In particular, if the user is showing negative emotions, it will suggest activities that improve their mood, thus providing emotionally sensitive suggestions. In this way, flexible planning that takes into account the user's psychological state and group dynamics is promoted.

[0710] As a concrete example, consider a scenario where users A, B, and C get together and plan an activity for the weekend. The server uses its emotion engine to analyze the conversation and determine that user A is tired from work and needs to relax, and user B wants to try something new. Based on this, the server suggests options such as "a relaxing day at a nearby resort" or "a cooking class to try new dishes."

[0711] Once the user accepts the proposal, the terminal guides them through the booking process via text message. The server connects to the booking system to process the details and supports payment on the terminal. Furthermore, an emotional engine continuously monitors user feedback, enabling dynamic adjustments accordingly. This ensures a satisfactory plan for all participants.

[0712] This system, by incorporating features that take emotions into consideration, surpasses conventional activity planning systems and enables more adaptable action suggestions and decisions.

[0713] The following describes the processing flow.

[0714] Step 1:

[0715] The user adds an emotion engine-enabled bot to a group chat within the LINE app. This action prepares the bot to begin monitoring all conversational interactions.

[0716] Step 2:

[0717] The server retrieves group chat conversation data in real time. The text of each message is sent to the server using the LINE Messaging API.

[0718] Step 3:

[0719] The server analyzes the conversation data obtained using natural language processing techniques. Natural language processing identifies each user's basic interests and topic priorities.

[0720] Step 4:

[0721] The server uses an emotion engine to recognize the user's emotions from the text. This engine detects emotion-specific keywords and phrases and determines the tone of the emotion, which is then classified into different emotion labels such as joy, anger, and sadness.

[0722] Step 5:

[0723] The server integrates data from both the emotion engine and natural language processing to generate customized activity suggestions based on each user's interests, personality, and emotions.

[0724] Step 6:

[0725] The server presents the generated activity suggestions to the user. It sends suggestions directly to the user using a message format, providing them with options.

[0726] Step 7:

[0727] The user selects and accepts the activity that interests them most from the presented suggestions. During this process, they can also ask the server any questions or inquire about other options.

[0728] Step 8:

[0729] On the device, the user starts the booking process for the selected activity. By clicking a link within the LINE app, the user enters the necessary details for the booking and completes the reservation.

[0730] Step 9:

[0731] After the reservation is complete, the server connects with an external payment system to execute a secure payment process. The user's payment information is verified, and the transaction is confirmed.

[0732] Step 10:

[0733] Users receive a final confirmation message regarding their planned activities. They can also receive reminder notifications as the activity date approaches.

[0734] (Example 2)

[0735] 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".

[0736] In modern society, there is a need to efficiently plan group activities while taking into account the psychological state and emotions of participants. However, conventional activity planning systems have the challenge of making proposals that adequately reflect the emotions and motivations of participants. Furthermore, these systems lack the flexibility to make adjustments based on post-activity feedback, so improvements are needed to increase participant satisfaction.

[0737] 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.

[0738] In this invention, the server includes means for acquiring conversation information, means for analyzing the acquired conversation information and estimating the interests, personalities, and emotions of the participants, and means for utilizing a generative model that generates activity suggestions based on the estimation results. This makes it possible to generate activity suggestions that reflect the user's emotions and to dynamically adjust the suggestions based on subsequent feedback.

[0739] "Conversational information" refers to communication data such as text and audio exchanged between users.

[0740] "Analysis" refers to a series of processes that involve analyzing conversational information and extracting characteristics such as its content and emotional tone.

[0741] "Interest" refers to the degree to which participants show interest in a particular activity or topic.

[0742] "Personality" refers to the individual psychological characteristics that influence the behavior and reactions of participants.

[0743] "Emotion" refers to the emotional state that participants exhibit in response to a particular situation or stimulus.

[0744] A "generative model" refers to an algorithm or system for generating a new output from input data.

[0745] An "emotion engine" refers to a technology or system that can detect emotional tone and nuances from text data.

[0746] "Dynamic adjustment" refers to changing proposed content and system settings in real time based on analysis and feedback.

[0747] This invention is a system that supports the planning of group activities by comprehensively analyzing user emotions and proposing optimal activities based on those analyses. This system operates on a messaging platform and combines a server, terminals, and a generative AI model.

[0748] The server retrieves conversation information from messaging applications in real time. It connects to the platform using an API to collect communication data between users. This collected data is then analyzed using an emotion engine. This emotion engine utilizes the Google Cloud Natural Language API and general emotion analysis tools to detect emotional tone and nuances, thereby understanding the user's emotional state.

[0749] Based on the analysis results, the server generates activity suggestions using a generative AI model. This model considers the user's interests and emotional state, and creates suggestions using appropriate prompts. For example, a prompt might be "Use the user's conversation data to generate activity suggestions that take their mood into consideration."

[0750] The generated suggestions are presented to the user via the device. The device displays a notification on the messaging application, prompting the user to review the suggestions. If the suggestion is accepted, the device guides the user through the booking process, and the server connects to the booking system to process the necessary information. The server also analyzes the post-activity feedback again using the sentiment engine to help adjust future suggestions. This ensures that users can continue to experience satisfaction.

[0751] As a concrete example, when users A and B plan their weekend activities, the server analyzes their conversation to determine that user A needs relaxation and user B is seeking a new experience. Based on this analysis, the server provides activity suggestions that combine a "relaxing day for relaxation" with an "innovative cooking class," thereby creating a plan that meets the users' expectations.

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

[0753] Step 1:

[0754] The server retrieves conversation information in real time from the messaging platform. The input is message data between users, and the output is conversation information in text format. This conversation information is obtained by the server connecting to the platform via an API. The server then sends the retrieved conversation information to the next parsing step.

[0755] Step 2:

[0756] The server analyzes conversational information acquired using an emotion engine. The input is conversational information in text format, and the output is each user's emotional state and characteristics. Specifically, the emotion engine uses natural language processing techniques to analyze the text content and identify emotions such as positive, negative, and neutral. This result is then used as input to a generative model.

[0757] Step 3:

[0758] The server generates activity suggestions using a generative AI model based on the analysis results. The input is data about the user's emotional state, interests, and personality, and the output is a customized activity suggestion. The prompt is "Construct an appropriate activity suggestion based on the user's emotions." The generative AI model devises specific activities that match the user's psychological state and creates them as activity suggestions.

[0759] Step 4:

[0760] The terminal presents the generated activity suggestions to the user. The input is the activity suggestions received from the server, and the output is the activity details presented to the user as a notification. The terminal uses an existing messaging application to have the user review the suggestions. The user can select activities of interest from the presented options.

[0761] Step 5:

[0762] When a user selects an activity, the terminal guides them through the booking process. The input is the activity information selected by the user, and the output is the booking procedure details. The terminal provides a specific link, and the server connects to the booking system and processes the necessary information, allowing the user to complete the booking smoothly.

[0763] Step 6:

[0764] The server collects user feedback after an activity and analyzes it again using the emotion engine. The input is user feedback data, and the output is information for adjusting future suggestions. Based on the analyzed feedback, the server adjusts the generative AI model and uses it to make future suggestions more personalized.

[0765] (Application Example 2)

[0766] 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".

[0767] Modern conversation analysis systems using information and communication technology do not adequately consider user emotions or personalities, making it impossible to fully personalize individual experiences and product recommendations. Furthermore, the lack of flexible suggestions linked to real-world experiences makes it difficult for users to make purchases and experience choices optimized for them.

[0768] 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.

[0769] In this invention, the server includes means for acquiring conversation information and estimating the participants' interests, personalities, and emotions; means for generating activity suggestions based on the estimation results; and means for making reservations and payments for selected activities. This enables appropriate in-store experience suggestions and product suggestions tailored to the user's emotional state.

[0770] "Conversation information" refers to information about the content of communications and messages exchanged between users.

[0771] "Interest" refers to the degree to which a user is interested in a particular field or activity.

[0772] "Personality" is a set of psychological characteristics that influence a user's decision-making and behavior.

[0773] "Emotion" refers to a temporary feeling or reaction that a user experiences in response to a particular situation or stimulus.

[0774] An "activity proposal" is a concrete plan that, based on user interests and emotions, promotes experiences at physical stores and services.

[0775] A "reservation" is a pre-arranged procedure undertaken by a user to secure the provision of a specific product or service.

[0776] "Payment" refers to the process of paying for goods or services provided.

[0777] A "physical store" refers to a facility where users can directly experience or purchase products or services in a physical location.

[0778] "Product suggestions" refer to presenting products as potential purchase options, selected based on the user's emotions and interests.

[0779] The system for implementing this invention primarily consists of data exchange between a server and a terminal. The server first acquires conversation information between users in real time and analyzes this information using natural language processing and sentiment analysis techniques. Specifically, the Python TextBlob library assists in this sentiment analysis, playing a role in estimating the user's interests, personality, and emotions.

[0780] Based on the estimation results obtained, the server generates activity suggestions that correspond to the user's emotional state and interests. These activity suggestions include specific suggestions such as in-store experiences and products designed to improve the user's psychological state. Furthermore, the terminal presents the suggested information to the user and plays a role in supporting decision-making.

[0781] When a user selects a specific suggestion, the terminal assists with the booking and payment process. The server collaborates with external booking databases and payment systems to complete transactions quickly and securely. Furthermore, a generative AI model is used to continuously analyze user sentiment and feedback, collecting data to provide better activity suggestions.

[0782] For example, if a user mentions feeling tired, the system can suggest a relaxing experience. A possible prompt might be: "Generate a message suggesting an effective relaxation experience when the user is seeking relaxation."

[0783] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0784] Step 1:

[0785] The server obtains conversation information between users via a messaging application. In this step, raw data in text format is input and stored on the server as conversation data.

[0786] Step 2:

[0787] The server analyzes the acquired conversational information using natural language processing and sentiment analysis techniques. Here, the Python TextBlob library is used to detect the emotional tone of the text and estimate the user's interests and emotions. This process yields emotion and interest metrics extracted from the conversation as output.

[0788] Step 3:

[0789] The server generates activity suggestions tailored to the user based on the analysis results. Using sentiment analysis data as input, the generation AI model generates suggestions and prompts. For example, it might create prompts such as, "Generate prompts for experiences that provide relaxation."

[0790] Step 4:

[0791] The terminal presents activity suggestions received from the server to the user, supporting decision-making. The user interface includes notifications and a dashboard displaying the suggested content. It also provides a user feedback function, recording user responses as input.

[0792] Step 5:

[0793] When a user selects a specific suggestion, the terminal guides them through the booking and payment process. This process uses the user's selected activity as input to call the booking system and payment API, and outputs booking confirmation and payment information.

[0794] Step 6:

[0795] The server continuously monitors and analyzes user feedback using a generative AI model, and utilizes this feedback to improve the suggestions. This results in more personalized activity suggestions for the future, enhancing the user experience. Feedback data is input, and adjustment data for generating the next activity suggestion is output.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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.

[0800] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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."

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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.

[0817] The following is further disclosed regarding the embodiments described above.

[0818] (Claim 1)

[0819] Means of acquiring conversation data,

[0820] A method for analyzing acquired conversation data to estimate participants' interests, personalities, and emotions,

[0821] A means for generating activity proposals based on estimation results,

[0822] A means of presenting activity proposals and supporting decision-making,

[0823] A system that includes means for making reservations and payments for selected activities.

[0824] (Claim 2)

[0825] The system according to claim 1, which analyzes conversation data using natural language processing technology and estimates the emotions of the participants.

[0826] (Claim 3)

[0827] The system according to claim 1, which retrieves activity-related information from an external database and generates activity proposals.

[0828] "Example 1"

[0829] (Claim 1)

[0830] Means of collecting information,

[0831] A means of analyzing collected information to estimate an individual's interests, characteristics, and emotions,

[0832] A means for generating options based on estimation results,

[0833] A means of presenting options and supporting decision-making,

[0834] A system that includes means for processing and making payments for selected items.

[0835] (Claim 2)

[0836] The system according to claim 1, which analyzes information using language processing technology and estimates the emotions of an individual.

[0837] (Claim 3)

[0838] The system according to claim 1, which obtains information related to an item from an external storage device and generates a selection of options.

[0839] "Application Example 1"

[0840] (Claim 1)

[0841] Means of obtaining conversational information,

[0842] A means of analyzing acquired conversation information to estimate the interests, personalities, and emotions of multiple participants,

[0843] A means for generating activity proposals based on estimation results,

[0844] A means of presenting activity proposals and supporting decision-making,

[0845] A means of making reservations and electronic payments for selected activities,

[0846] A means of analyzing the behavioral information of multiple participants to present products and services based on their interests,

[0847] A means of acquiring store-related data from an external information infrastructure and generating product suggestions based on interests,

[0848] A means of displaying information generated by a smart device,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, which analyzes conversational information using natural language processing technology and estimates the emotions of the participants.

[0852] (Claim 3)

[0853] The system according to claim 1, which retrieves activity-related information from an external database and generates activity proposals.

[0854] "Example 2 of combining an emotion engine"

[0855] (Claim 1)

[0856] Means of obtaining conversational information,

[0857] A means of analyzing acquired conversation information to estimate participants' interests, personality, and emotions,

[0858] A means of using a generative model that generates activity proposals based on estimation results,

[0859] A means of presenting generated activity proposals and supporting decision-making,

[0860] A means of making reservations and payments for selected activities,

[0861] A system that includes means for analyzing user feedback using an emotion engine and dynamically adjusting suggestions.

[0862] (Claim 2)

[0863] The system according to claim 1, which analyzes conversational information using natural language processing techniques and estimates the emotions of the participants.

[0864] (Claim 3)

[0865] The system according to claim 1, which obtains information related to an activity from an external source and generates an activity proposal.

[0866] "Application example 2 when combining with an emotional engine"

[0867] (Claim 1)

[0868] Means of obtaining conversational information,

[0869] A means of analyzing acquired conversation information to estimate participants' interests, personality, and emotions,

[0870] A means for generating activity proposals based on estimation results,

[0871] A means of presenting activity proposals and supporting decision-making,

[0872] A means of making reservations and payments for selected activities,

[0873] Based on the analysis results, we propose methods for providing in-store experiences,

[0874] A means of dynamically suggesting products and services while considering the user's emotional state,

[0875] A system that includes this.

[0876] (Claim 2)

[0877] The system according to claim 1, which analyzes conversation information using natural language processing technology and sentiment analysis technology to estimate the emotions of the participants.

[0878] (Claim 3)

[0879] The system according to claim 1, which provides a real-life experience tailored to the user's emotional state using activity-related information obtained from an external source. [Explanation of Symbols]

[0880] 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 acquiring conversation data, A method for analyzing acquired conversation data to estimate participants' interests, personalities, and emotions, A means for generating activity proposals based on estimation results, A means of presenting activity proposals and supporting decision-making, A system that includes means for making reservations and payments for selected activities.

2. The system according to claim 1, which analyzes conversation data using natural language processing technology and estimates the emotions of the participants.

3. The system according to claim 1, which retrieves activity-related information from an external database and generates activity proposals.

Images