system

Abstract

We provide the system. [Solution] Means for collecting user behavior data and preference data, A means for analyzing the aforementioned data and generating behavioral patterns and preference models, Means for generating the optimal choice for the user based on the aforementioned patterns and models, A means for notifying the user of the aforementioned options, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern life, users unconsciously make many choices, which often cause regret and a decrease in life satisfaction. Furthermore, it is difficult to enhance the essential satisfaction by grasping individual behavior patterns and preferences and utilizing them appropriately. Therefore, there is a demand for a system that can provide optimal choices based on users' potential needs and preferences.

Means for Solving the Problems

[0005] The present invention solves the above problems by providing a system that includes means for collecting user behavior data and preference data, means for analyzing the data to generate behavior patterns and preference models, means for generating optimal choices for the user based on the generated patterns and models, and means for notifying the user of those choices. This system enables users to become aware of their unconscious choices and make more intentional and satisfying choices.

[0006] "User" refers to an individual who uses this system and is the provider of their behavioral and preference data.

[0007] "Behavioral data" refers to data related to a user's location, purchase history, and activity on social networking services.

[0008] "Preference data" refers to data that indicates a user's preferences and interests, and is extracted based on past choices and behavioral patterns.

[0009] "Means of data collection" refers to the technical means of acquiring user behavioral data and preference data and making them usable within the system.

[0010] "Analysis" is the process of extracting meaningful information using collected data, and includes technical operations used to generate user behavior patterns and preference models.

[0011] "Behavioral patterns" refer to information that indicates habitual or repetitive actions, extracted from a user's past behavior.

[0012] A "preference model" is a model built to predict a user's interests and preferences based on their past data.

[0013] "Means for generating options" refers to technical means that derive optimal suggestions and actions from user behavior patterns and preference models.

[0014] "Means of notification" refers to the technical means of communicating the generated options to the user, including, for example, push notifications or presentation as in-app messages. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a 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, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a system that provides optimal choices based on the user's personal data, with the server, terminal, and user working in cooperation. The user's terminal acts as the starting point for data collection, first acquiring location information and purchase history. This information is transmitted to the server as needed with the user's permission. The terminal also has the function of connecting to the API of the social networking service used by the user and collecting posts and reactions.

[0037] The server receives the collected data and stores it in a database for analysis. The information stored in the database is analyzed using machine learning algorithms to generate user behavior patterns and preference models. This analysis helps understand what actions users tend to take and when, and what choices lead to high satisfaction.

[0038] Using generative AI, the server generates the optimal choices to suggest to the user based on these analysis results. These choices are customized according to the user's past behavioral trends and current situation. For example, it may suggest information about newly opened cafes or tourist spots that are helpful for travel planning.

[0039] The generated options are sent to the device in real time. The device has the capability to display these suggestions as push notifications or in-app messages so that users can easily review them. Users can select the options that interest them from the suggested choices and use them as a reference for their next action.

[0040] A concrete example is when a user is looking for a new hobby. The server, using past data it has collected, identifies that the user frequently liked cooking-related social media posts in the past. Based on this information, the server can suggest new cooking classes or sales on seasonings. In this way, the user can become aware of their latent interests and make new choices.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] Device: Confirms user consent and enables location services. Periodically collects location information and purchase history data. Also obtains user posts and like history via SNS APIs.

[0044] Step 2:

[0045] Server: Receives data sent from terminals and saves it to the database. When saving, data cleaning is performed to maintain the integrity and consistency of the information.

[0046] Step 3:

[0047] Server: Machine learning algorithms are applied to prepare the stored data for analysis. This identifies user behavior patterns and generates preference models. Clustering techniques are used in particular to group user interests and visit trends.

[0048] Step 4:

[0049] Server: Using generated behavioral patterns and preference models, it leverages generative AI to create optimal choices for the user. The generated choices are based on the user's past behavior, current trends, and available news and event information.

[0050] Step 5:

[0051] Server: Sends prioritized options to the terminal. Here, the information most relevant to the user is presented in the most prominent way.

[0052] Step 6:

[0053] Device: The device notifies the user of the received options in an easy-to-understand format. Notification methods such as push notifications and in-app messages are designed to be easily accessible to the user.

[0054] Step 7:

[0055] User: Review the options displayed on the device and select the next action that best suits their current interests and schedule. Based on the selected information, they can then plan specific actions.

[0056] (Example 1)

[0057] 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."

[0058] Conventional personalization systems have a problem in that they are not sufficient to effectively generate and provide individualized suggestions in real time based on the characteristics of the user. Furthermore, it is difficult to efficiently utilize users' location information, purchase history, and information sharing service data, and there is a lack of methods to provide appropriate choices that meet individual needs in a timely manner.

[0059] 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.

[0060] In this invention, the server includes means for collecting user characteristic data, means for analyzing the data to generate a user behavior pattern and preference model, and means for creating optimal choices for the user based on the behavior pattern and preference model. This makes it possible to provide individualized suggestions tailored to each user in real time.

[0061] "User characteristic data" refers to information related to an individual user, including location information, purchase history, and activity data from information sharing services.

[0062] A "behavioral and preference model" is a model extracted by analyzing a user's past behavioral patterns and preferences, and it shows what kinds of choices the user prefers.

[0063] "Optimal choice" means providing the most suitable suggestions or options to the user based on their personal data and generated behavioral patterns and preference models.

[0064] A "user terminal" is an electronic device used by users to display information and receive suggestions from a server, and includes devices such as smartphones and tablets.

[0065] A "generative AI model" is a model that uses artificial intelligence technology and includes algorithms for generating new information or options based on input data.

[0066] This invention is a system that provides optimal choices based on user characteristic data. The system is primarily realized through the organic cooperation of a server, terminals, and users.

[0067] Data collection

[0068] The device acts as a data collection hub, first acquiring the user's location information and purchase history. This information is collected with the user's consent. Furthermore, the device has the functionality to connect to information sharing service APIs and collect posted content and responses to it. The device incorporates hardware and software such as a GPS sensor and online shopping APIs.

[0069] Data transmission and storage

[0070] The terminal encrypts the collected data and sends it to the server. The server stores the received data in a database and prepares it for analysis. The database is a management platform that facilitates the secure storage and analysis of data.

[0071] Analysis and generation of optimal options

[0072] The server uses machine learning libraries (such as TENSORFLOW® and PyTorch) to generate a model of the user's behavior patterns and preferences. Based on this generated model, the server uses a generative AI model to create prompt messages, generating optimal choices that meet the user's needs. These prompt messages include specific instructions based on the user's recent behavior data and interests.

[0073] Providing and displaying options

[0074] The generated options are immediately sent to the device. The device then displays these suggestions as push notifications or in-app messages to help users access them without confusion.

[0075] A concrete example is a situation where a user is exploring new interests. If the server analyzes past data it has collected to determine that the user is interested in cooking, it can suggest information about cooking classes or food sales. The goal of this suggestion is to provide the user with useful information in real time.

[0076] Example prompt: "Based on the user's past social media activity and purchase history, suggest new hobbies and activities related to their interests."

[0077] In this way, the system can provide users with beneficial options and meet their individual needs.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The device collects the user's location information and purchase history. It uses location data obtained via GPS sensors and purchase data obtained from online shopping APIs as input. This input data is cleansed, its format is standardized, and then it is converted into a format suitable for transmission.

[0081] Step 2:

[0082] The device connects to the API of an information sharing service to retrieve user posts and reactions. User data from the information sharing service is used as input. Specifically, it collects user-posted content and reaction data such as likes and comments, and converts this data into a specified format.

[0083] Step 3:

[0084] The device encrypts the collected data and sends it to the server. The input consists of location information, purchase history, and social media data obtained in steps 1 and 2. The device combines this data and sends it to the server using the HTTPS protocol.

[0085] Step 4:

[0086] The server stores the received data in a database. The input is user characteristic data sent from the terminal. The server writes the data to the database in preparation for analysis, organizing the data and making it accessible.

[0087] Step 5:

[0088] The server uses machine learning algorithms to generate user behavior and preference models. It uses user data stored in a database as input, extracts behavioral patterns, and models them. The output is a behavioral model that reflects user preferences.

[0089] Step 6:

[0090] The server uses a generative AI model to create prompt messages and generate the most suitable options for the user. The input is the behavioral model generated in step 5, and specific suggestions are generated based on this model. The output is information and service suggestions tailored to the user.

[0091] Step 7:

[0092] The server sends the generated optimal choices to the terminal. The input is the data of the optimal choices obtained in step 6. The server sends the choices to the terminal in real time, allowing the user to check them immediately.

[0093] Step 8:

[0094] The device displays suggestions to the user as push notifications or in-app messages. The input is the best choice sent from the server. The device receives the data and displays it in a format that the user can easily access and select.

[0095] (Application Example 1)

[0096] 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."

[0097] Traditional shopping systems tend to offer generic product suggestions to users, lacking personalized recommendations based on individual preferences and behavioral patterns. This means users often have to spend time finding products they're interested in themselves, making it difficult to enjoy an efficient shopping experience.

[0098] 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.

[0099] In this invention, the server includes means for collecting user behavior data and preference data; means for analyzing the data and generating behavior patterns and preference models; means for generating optimal choices for the user based on the patterns and models; and means for locating the user in a real-world location and providing information from commercial facilities in order to provide the choices in relation to commercial activities. This enables the user to appropriately receive product information and promotions tailored to their preferences.

[0100] "User behavior data" refers to information that shows a series of actions taken by a user and the history of those actions.

[0101] "Preference data" refers to information about users' interests and preferences, and indicates tendencies regarding specific behaviors and choices.

[0102] A "behavioral pattern" is a pattern that shows the tendencies and frequency of actions a user takes over a certain period of time.

[0103] A "preference model" is a model that numerically or algorithmically represents a user's preferences and is used to predict their tastes.

[0104] A "means for generating options" refers to a system for creating specific suggestions and options to present to users based on their data.

[0105] "Means for providing in connection with commercial activities" refers to a system for providing users with commercial-related information and suggestions within or near a commercial facility.

[0106] "Means for determining the user's location" refers to a system for acquiring and analyzing the user's current location in real time.

[0107] "Information from commercial facilities" refers to various types of information provided by commercial facilities, such as products, services, promotions, and events.

[0108] This invention features a system that provides users with optimal commercial activity-related options based on their behavioral data and preference data.

[0109] Program Overview:

[0110] The server forms the core of this system, collecting, analyzing, and generating choices based on data sent by the user. The terminal acquires the user's location information in real time and sends it to the server. It also collects the user's purchase history and posts from social networking services. Smartphones are often used for this purpose. The collected data is stored in a database by the server and analyzed using machine learning algorithms.

[0111] Hardware and software:

[0112] Servers are recommended to be located on cloud services (such as AWS® or Google® Cloud). Machine learning libraries such as Python's scikit-learn or TensorFlow can be used for data analysis. Devices include iOS or Android® mobile devices. These devices send data to the server using APIs.

[0113] Use of Generative AI:

[0114] The OpenAI® API is used as the generative AI model. The server uses the generative AI to generate personalized product suggestions based on user behavior data. This process includes prompt messages that contain information tailored to the user's interests and current situation.

[0115] Specific example:

[0116] For example, when a user is in a shopping mall, the server suggests stores and products that are likely to interest the user based on their location and past purchase history. These suggestions are delivered to the user via push notifications on their smartphone.

[0117] Example of a prompt:

[0118] "This user has been identified as a fan of mystery novels in the past. Please provide information on mystery-related events and merchandise currently available in bookstores."

[0119] This system allows users to automatically find products that match their interests, providing a more efficient and satisfying shopping experience.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The device obtains location information with the user's permission. This location information is collected using GPS functionality and becomes data to determine the user's current location in real time. This data is sent to a server and linked to a specific location within the commercial facility.

[0123] Step 2:

[0124] The device collects the user's purchase history and posts obtained through social networking service APIs. This data, which reflects the user's past behavior and preferences, is sent to the server. This information is sent in text data format and used to generate preference models.

[0125] Step 3:

[0126] The server receives collected location data, purchase history, and data from social media, and stores it in a database. The stored data is then analyzed using a Python machine learning library (e.g., scikit-learn) to generate behavioral patterns and preference models.

[0127] Step 4:

[0128] The server generates the most suitable options for the user from the analyzed data. This process uses a generative AI model (e.g., OpenAI's API) to create prompts for products and events that match the user's preferences. These generated prompts serve as a guide for extracting the most relevant commercial information.

[0129] Step 5:

[0130] The server compiles information from commercial facilities based on the generated choices and sends it to the terminal. The terminal displays this information to the user as a push notification. This allows the user to receive recommended product and event information in real time.

[0131] 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.

[0132] This invention is a system that provides more personalized choices by collecting and analyzing emotional data in addition to user behavioral data and preference data. The system consists of a server, a terminal, and a user, and is equipped with a function to recognize the user's emotional state using an emotion engine.

[0133] The user's device uses an emotion engine to analyze voice and text data and determine the user's emotions in real time. This emotion data is sent to the server along with location information, purchase history, and social networking service data. The collection of emotion data is non-invasive and done with the user's permission.

[0134] The server stores various data sent from the terminal in a database and uses this data to analyze the user's behavior patterns, preference models, and emotional state. The data generated by the emotion engine is a crucial source of information, particularly in generating choices, enabling suggestions tailored to the user's current emotions. For example, when a user is stressed, the server might suggest options that are beneficial for relaxation.

[0135] Using a generative AI model, the server generates optimal choices adapted to the user's current state based on insights gained from analysis. These choices reflect the user's emotional needs at that moment by taking into account emotional state data.

[0136] For example, if the emotion engine detects "fatigue" while a user is browsing social media on their device during a break at work, the server will suggest nearby cafes where they can relax or stretching videos to help them change their mood. In this way, users can make appropriate choices based on their emotional state, leading to a more satisfying daily life.

[0137] This system aims to improve users' quality of life by providing a more personalized experience through an emotion engine that considers the user's emotions when making choices.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] Device: Obtain user consent and enable voice input and text analysis tools. This prepares the device for real-time collection of sentiment data from user speech and entered text.

[0141] Step 2:

[0142] Device: In addition to the user's daily behavioral data (location information, purchase history, social media posts), it collects acquired emotional data. This emotional data is analyzed by an emotion engine designed to identify a variety of emotions such as joy, sadness, and stress.

[0143] Step 3:

[0144] Terminal: Collects behavioral and emotional data and sends it to the server within the user's permission. Transmission occurs periodically, according to the frequency specified by the user.

[0145] Step 4:

[0146] Server: Integrates received data into the database and organizes information for each user. During this process, filtering and cleaning processes are performed to maintain data consistency.

[0147] Step 5:

[0148] Server: Analyzes integrated data and updates user behavior patterns and preference models. Emotional data is particularly important and influences the generation of situation-appropriate choices.

[0149] Step 6:

[0150] Server: Using a generative AI model, it generates the most suitable options for the user based on all the collected data. This process incorporates the user's current emotional state; for example, if the user is feeling stressed, it will create suggestions that promote relaxation.

[0151] Step 7:

[0152] Server: Sorts the generated options according to priority and sends them to the user's terminal.

[0153] Step 8:

[0154] Terminal: Receives selections from the server and notifies the user. Notifications are delivered using push notifications, in-app messages, and widgets, and are designed for easy user access.

[0155] Step 9:

[0156] User: Check notifications from their device, select options of interest, and decide on their next action. Based on their selection, they begin a new experience or action.

[0157] This series of steps allows users to make choices that align with their emotional state at any given time, resulting in a more personalized experience.

[0158] (Example 2)

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

[0160] In today's information society, it is difficult for users to choose the best option from a vast array of choices. In particular, there is a lack of systems that provide appropriate choices based on the user's emotional state. Choices that ignore emotional information cannot adequately increase user satisfaction and may even negatively impact their quality of life.

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

[0162] In this invention, the server includes means for collecting user behavior information, preference information, and emotional information; means for analyzing the information and generating behavior patterns, preference models, and emotional states; and means for generating choices suitable for the user based on the patterns, models, and states. This makes it possible to provide personalized choices that correspond to the user's emotional state.

[0163] "User behavior information" refers to data about the actions and tendencies that users perform on a daily basis.

[0164] "Preference information" refers to data about a user's preferences and interests.

[0165] "Emotional information" refers to data that indicates a user's emotional state or psychological condition.

[0166] "Options" refer to multiple possible actions or decisions presented to the user.

[0167] A "generative model" is an algorithm or computational method used to analyze data and generate new information or options.

[0168] A "behavioral pattern" is a model that shows the regularity or common tendencies in user behavior.

[0169] A "preference model" is a data model built to represent and utilize user preferences.

[0170] "Emotional state" refers to the user's emotions and psychological condition at a specific moment in time.

[0171] "Communication network service information" refers to data about a user's online activities, and is information provided via a communication network.

[0172] In an embodiment for carrying out this invention, the system consists of three elements: a server, a terminal, and a user.

[0173] Users first generate behavioral, preference, and emotional information through their daily use of their devices. These devices are equipped with voice and text input capabilities, and analysis software called an emotion engine analyzes this data in real time to determine the user's emotional state. This emotion engine identifies voice tone and keywords within the text to classify the user's emotions.

[0174] The device transmits location information, transaction history, and communication network service information, along with analyzed emotional information, to the server. The server stores this information in a database and generates user behavior patterns and preference models. It also records the emotional state based on the generated data and uses this information to provide the user with the most suitable options.

[0175] As a concrete example, if the emotion engine detects "fatigue" while a user is browsing entertainment information on their device during their lunch break, the server will use a generative AI model to suggest a nearby quiet cafe or a short relaxation video to the user. This suggestion is instructed to the generative AI model as a prompt: "Please provide options to alleviate the fatigue the user is currently feeling."

[0176] As described above, the system aims to improve user satisfaction and quality of life by utilizing real-time user sentiment data and providing personalized options tailored to individual needs.

[0177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0178] Step 1:

[0179] The user inputs voice and text data through the device. The device collects this data and inputs it into the emotion engine. Specifically, it uses speech recognition technology to convert the voice data into text and prepares it for emotion analysis by combining it with the text data.

[0180] Step 2:

[0181] The device's emotion engine analyzes voice and text data to determine the user's emotional state. In this process, the emotion engine extracts features from the input data and compares them with an existing emotion database to output an emotion category (e.g., "joy," "sadness," "fatigue," etc.). Specifically, it performs matching based on voice tone and keywords in the text.

[0182] Step 3:

[0183] The device acquires emotional data, location information, purchase history, and communication network service information, and sends this data to the server. Specifically, it obtains the current location from location services and purchase history from past transaction logs, and prepares to send all the information as packets to the server.

[0184] Step 4:

[0185] The server stores the received data in a database and analyzes the user's behavior patterns, preference models, and emotional states. The input consists of multiple user data points stored in the database, and new patterns and models are generated based on this data. This process utilizes data mining techniques to extract useful patterns and generates behavioral pattern models and preference models as output.

[0186] Step 5:

[0187] The server uses a generative AI model to generate suitable options for the user based on the analysis results. Here, the generative AI model receives instructions using prompts and outputs appropriate options (e.g., relaxation locations, stretching videos, etc.) based on the input data. Specifically, the generative AI model searches the cloud or database for resources that match the analyzed emotional state and generates suggestions that meet the user's needs.

[0188] Step 6:

[0189] The server sends the generated options to the user's device and presents them. The device receives this and notifies the user visually or audibly. Specific actions include displaying information in the notification bar or prompting suggestions with voice guidance.

[0190] (Application Example 2)

[0191] 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".

[0192] When users engage with digital content, there is a challenge in providing them with appropriate choices that align with their emotional state at any given moment. Furthermore, traditional methods struggle to achieve deep personalization that considers not only user preferences and behavioral data but also their real-time emotional state.

[0193] 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.

[0194] In this invention, the server includes means for collecting user behavior data, preference data, and emotional data; means for analyzing the data and generating behavior patterns, preference models, and emotional states; and means for generating optimal choices for the user based on the patterns, models, and emotional states. This makes it possible to provide personalized content based on the user's emotional state.

[0195] "Behavioral data" refers to information that records a user's activities and usage patterns.

[0196] "Preference data" refers to information about the content and services that users prefer.

[0197] "Emotional data" refers to information about a user's emotional state, analyzed from sources such as voice and text.

[0198] "Behavioral patterns" refer to typical behavioral tendencies and habits analyzed from user behavior data.

[0199] A "preference model" is a model that shows individualized preference trends derived from user preference data.

[0200] "Emotional state" represents the user's current emotional condition and is a real-time analysis result.

[0201] "Options" refer to the suggested actions or content presented to the user.

[0202] "Content" refers to information resources such as movies, music, and videos that are provided to users.

[0203] A "generative artificial intelligence model" is an artificial intelligence model used to generate appropriate choices using data analysis.

[0204] The system implementing this invention mainly consists of a server, a terminal, and a user. The terminal is a device that provides a user interface, such as a smartphone or smart glasses. The terminal is equipped with an emotion recognition engine that analyzes the user's voice and text data in real time. The analyzed emotion data is sent to the server along with the user's geographical location data, purchase history data, and social networking service data.

[0205] Based on this data, the server generates customized behavioral patterns, preference models, and emotional states for each user. A generative artificial intelligence model is used for data analysis and choice generation. This model considers the generated behavioral patterns, preference models, and emotional states to propose a list of content optimized for the user.

[0206] For example, when a user is using a streaming service, if the emotion engine detects fatigue or stress, it will recommend uplifting comedy movies or relaxing music. This suggestion will be notified to the user and displayed on their device as available content.

[0207] As an example of a prompt message that a generative AI model might use to generate choices, we can use a sentence like, "Your current emotional state has been detected as 'fatigue.' Please recommend a relaxing movie." This allows users to smoothly select content that matches their emotional state, providing a highly satisfying experience.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The device sends the user's voice and text data as input to an emotion recognition engine, which analyzes the emotional state in real time. As a result of the analysis, it outputs the user's current emotional state.

[0211] Step 2:

[0212] The device transmits user emotional state data, geographical location data, purchase history data, and social networking service data to the server. This data serves as input necessary for generating user behavior patterns and preference models.

[0213] Step 3:

[0214] The server uses data analysis software to generate user behavior patterns and preference models based on the received data. As a result of the analysis, it outputs customized behavior patterns, preference models, and emotional states for each user.

[0215] Step 4:

[0216] The server uses the behavioral patterns, preference models, and emotional states generated by the artificial intelligence model as input to generate a list of user-optimized content. This process utilizes prompt statements to generate choices. The generated results are output as choices suggested to the user.

[0217] Step 5:

[0218] The server sends the generated content list to the device. Based on the received list, the device notifies the user and displays content on the screen that matches their emotional state. By using the suggested content, the user can have a more satisfying experience.

[0219] 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.

[0220] 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.

[0221] 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.

[0222] [Second Embodiment]

[0223] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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".

[0235] This invention is a system that provides optimal choices based on the user's personal data, with the server, terminal, and user working in cooperation. The user's terminal acts as the starting point for data collection, first acquiring location information and purchase history. This information is transmitted to the server as needed with the user's permission. The terminal also has the function of connecting to the API of the social networking service used by the user and collecting posts and reactions.

[0236] The server receives the collected data and stores it in a database for analysis. The information stored in the database is analyzed using machine learning algorithms to generate user behavior patterns and preference models. This analysis helps understand what actions users tend to take and when, and what choices lead to high satisfaction.

[0237] Using generative AI, the server generates the optimal choices to suggest to the user based on these analysis results. These choices are customized according to the user's past behavioral trends and current situation. For example, it may suggest information about newly opened cafes or tourist spots that are helpful for travel planning.

[0238] The generated options are sent to the device in real time. The device has the capability to display these suggestions as push notifications or in-app messages so that users can easily review them. Users can select the options that interest them from the suggested choices and use them as a reference for their next action.

[0239] A concrete example is when a user is looking for a new hobby. The server, using past data it has collected, identifies that the user frequently liked cooking-related social media posts in the past. Based on this information, the server can suggest new cooking classes or sales on seasonings. In this way, the user can become aware of their latent interests and make new choices.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] Device: Confirms user consent and enables location services. Periodically collects location information and purchase history data. Also obtains user posts and like history via SNS APIs.

[0243] Step 2:

[0244] Server: Receives data sent from terminals and saves it to the database. When saving, data cleaning is performed to maintain the integrity and consistency of the information.

[0245] Step 3:

[0246] Server: Machine learning algorithms are applied to prepare the stored data for analysis. This identifies user behavior patterns and generates preference models. Clustering techniques are used in particular to group user interests and visit trends.

[0247] Step 4:

[0248] Server: Using generated behavioral patterns and preference models, it leverages generative AI to create optimal choices for the user. The generated choices are based on the user's past behavior, current trends, and available news and event information.

[0249] Step 5:

[0250] Server: Sends prioritized options to the terminal. Here, the information most relevant to the user is presented in the most prominent way.

[0251] Step 6:

[0252] Device: The device notifies the user of the received options in an easy-to-understand format. Notification methods such as push notifications and in-app messages are designed to be easily accessible to the user.

[0253] Step 7:

[0254] User: Review the options displayed on the device and select the next action that best suits their current interests and schedule. Based on the selected information, they can then plan specific actions.

[0255] (Example 1)

[0256] 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."

[0257] Conventional personalization systems have a problem in that they are not sufficient to effectively generate and provide individualized suggestions in real time based on the characteristics of the user. Furthermore, it is difficult to efficiently utilize users' location information, purchase history, and information sharing service data, and there is a lack of methods to provide appropriate choices that meet individual needs in a timely manner.

[0258] 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.

[0259] In this invention, the server includes means for collecting user characteristic data, means for analyzing the data to generate a user behavior pattern and preference model, and means for creating optimal choices for the user based on the behavior pattern and preference model. This makes it possible to provide individualized suggestions tailored to each user in real time.

[0260] "User characteristic data" refers to information related to an individual user, including location information, purchase history, and activity data from information sharing services.

[0261] A "behavioral and preference model" is a model extracted by analyzing a user's past behavioral patterns and preferences, and it shows what kinds of choices the user prefers.

[0262] "Optimal choice" means providing the most suitable suggestions or options to the user based on their personal data and generated behavioral patterns and preference models.

[0263] A "user terminal" is an electronic device used by users to display information and receive suggestions from a server, and includes devices such as smartphones and tablets.

[0264] A "generative AI model" is a model that uses artificial intelligence technology and includes algorithms for generating new information or options based on input data.

[0265] This invention is a system that provides optimal choices based on user characteristic data. The system is primarily realized through the organic cooperation of a server, terminals, and users.

[0266] Data collection

[0267] The device acts as a data collection hub, first acquiring the user's location information and purchase history. This information is collected with the user's consent. Furthermore, the device has the functionality to connect to information sharing service APIs and collect posted content and responses to it. The device incorporates hardware and software such as a GPS sensor and online shopping APIs.

[0268] Data transmission and storage

[0269] The terminal encrypts the collected data and sends it to the server. The server stores the received data in a database and prepares it for analysis. The database is a management platform that facilitates the secure storage and analysis of data.

[0270] Analysis and generation of optimal options

[0271] The server uses machine learning libraries (such as TensorFlow and PyTorch) to generate a model of the user's behavior and preferences. Based on this model, the server uses a generative AI model to create prompts, generating optimal choices that meet the user's needs. These prompts include specific instructions based on the user's recent behavior data and interests.

[0272] Providing and displaying options

[0273] The generated options are immediately sent to the device. The device then displays these suggestions as push notifications or in-app messages to help users access them without confusion.

[0274] A concrete example is a situation where a user is exploring new interests. If the server analyzes past data it has collected to determine that the user is interested in cooking, it can suggest information about cooking classes or food sales. The goal of this suggestion is to provide the user with useful information in real time.

[0275] Example prompt: "Based on the user's past social media activity and purchase history, suggest new hobbies and activities related to their interests."

[0276] In this way, the system can provide users with beneficial options and meet their individual needs.

[0277] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0278] Step 1:

[0279] The device collects the user's location information and purchase history. It uses location data obtained via GPS sensors and purchase data obtained from online shopping APIs as input. This input data is cleansed, its format is standardized, and then it is converted into a format suitable for transmission.

[0280] Step 2:

[0281] The terminal connects to the API of the information sharing service and obtains the user's posted content and reactions. There is user data from the information sharing service as input. Specifically, it collects the content posted by the user and reaction data such as likes and comments on it, and converts these data into a specified format.

[0282] Step 3:

[0283] The terminal encrypts the collected data and then sends it to the server. The input is the location information, purchase history, and SNS data obtained in Steps 1 and 2. The terminal combines these and sends them to the server using the HTTPS protocol.

[0284] Step 4:

[0285] The server saves the received data in the database. The input is the user's characteristic data sent from the terminal. The server writes the data into the database in preparation for analysis and organizes the data into an accessible state.

[0286] Step 5:

[0287] The server uses a machine learning algorithm to generate the user's behavior pattern and preference model. Using the user data stored in the database as input, it extracts the behavior pattern and performs modeling. The output is a behavior pattern model reflecting the user's preferences.

[0288] Step 6:

[0289] The server uses the generated AI model to create a prompt sentence and generate the optimal options for the user. The input is the behavior pattern model generated in Step 5, and based on this model, it generates specific proposals. The output is information and service proposals suitable for the user.

[0290] Step 7:

[0291] The server sends the generated optimal choices to the terminal. The input is the data of the optimal choices obtained in step 6. The server sends the choices to the terminal in real time, allowing the user to check them immediately.

[0292] Step 8:

[0293] The device displays suggestions to the user as push notifications or in-app messages. The input is the best choice sent from the server. The device receives the data and displays it in a format that the user can easily access and select.

[0294] (Application Example 1)

[0295] 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."

[0296] Traditional shopping systems tend to offer generic product suggestions to users, lacking personalized recommendations based on individual preferences and behavioral patterns. This means users often have to spend time finding products they're interested in themselves, making it difficult to enjoy an efficient shopping experience.

[0297] 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.

[0298] In this invention, the server includes means for collecting user behavior data and preference data; means for analyzing the data and generating behavior patterns and preference models; means for generating optimal choices for the user based on the patterns and models; and means for locating the user in a real-world location and providing information from commercial facilities in order to provide the choices in relation to commercial activities. This enables the user to appropriately receive product information and promotions tailored to their preferences.

[0299] "User behavior data" refers to information indicating a series of actions taken by a user and the history of those actions.

[0300] "Preference data" refers to information regarding a user's interests and preferences, indicating tendencies related to specific actions or choices.

[0301] "Behavior pattern" refers to a pattern indicating the tendencies and frequencies of actions taken by a user over a certain period.

[0302] "Preference model" refers to a model that numerically or algorithmically represents a user's preferences and is used to infer the user's preferences.

[0303] "Means for generating options" refers to a mechanism for creating specific proposals or options to be presented to a user based on the user's data.

[0304] "Means for providing in relation to commercial activities" refers to a mechanism for providing commercial-related information and proposals to a user within or near a commercial facility.

[0305] "Means for identifying the user's location" refers to a mechanism for acquiring and analyzing the user's current location in real time.

[0306] "Information from commercial facilities" refers to various types of information provided by commercial facilities, such as products, services, promotions, events, etc.

[0307] This invention features a system that provides optimal commercial activity-related options to a user based on the user's behavior data and preference data.

[0308] Outline of the program:

[0309] The server forms the core of this system, collecting, analyzing, and generating choices based on data sent by the user. The terminal acquires the user's location information in real time and sends it to the server. It also collects the user's purchase history and posts from social networking services. Smartphones are often used for this purpose. The collected data is stored in a database by the server and analyzed using machine learning algorithms.

[0310] Hardware and software:

[0311] It is recommended that the server be located on a cloud service (such as AWS or Google Cloud). Machine learning libraries such as Python's scikit-learn or TensorFlow can be used for data analysis. The devices include iOS or Android mobile devices. These devices send data to the server using an API.

[0312] Use of Generative AI:

[0313] The OpenAI API is used as the generative AI model. The server uses the generative AI to generate personalized product suggestions based on user behavior data. This process includes prompt messages that contain information tailored to the user's interests and current situation.

[0314] Specific example:

[0315] For example, when a user is in a shopping mall, the server suggests stores and products that are likely to interest the user based on their location and past purchase history. These suggestions are delivered to the user via push notifications on their smartphone.

[0316] Example of a prompt:

[0317] "This user has been identified as a fan of mystery novels in the past. Please provide information on mystery-related events and merchandise currently available in bookstores."

[0318] This system allows users to automatically find products that match their interests, providing a more efficient and satisfying shopping experience.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The device obtains location information with the user's permission. This location information is collected using GPS functionality and becomes data to determine the user's current location in real time. This data is sent to a server and linked to a specific location within the commercial facility.

[0322] Step 2:

[0323] The device collects the user's purchase history and posts obtained through social networking service APIs. This data, which reflects the user's past behavior and preferences, is sent to the server. This information is sent in text data format and used to generate preference models.

[0324] Step 3:

[0325] The server receives collected location data, purchase history, and data from social media, and stores it in a database. The stored data is then analyzed using a Python machine learning library (e.g., scikit-learn) to generate behavioral patterns and preference models.

[0326] Step 4:

[0327] The server generates the most suitable options for the user from the analyzed data. This process uses a generative AI model (e.g., OpenAI's API) to create prompts for products and events that match the user's preferences. These generated prompts serve as a guide for extracting the most relevant commercial information.

[0328] Step 5:

[0329] The server compiles information from commercial facilities based on the generated choices and sends it to the terminal. The terminal displays this information to the user as a push notification. This allows the user to receive recommended product and event information in real time.

[0330] 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.

[0331] This invention is a system that provides more personalized choices by collecting and analyzing emotional data in addition to user behavioral data and preference data. The system consists of a server, a terminal, and a user, and is equipped with a function to recognize the user's emotional state using an emotion engine.

[0332] The user's device uses an emotion engine to analyze voice and text data and determine the user's emotions in real time. This emotion data is sent to the server along with location information, purchase history, and social networking service data. The collection of emotion data is non-invasive and done with the user's permission.

[0333] The server stores various data sent from the terminal in a database and uses this data to analyze the user's behavior patterns, preference models, and emotional state. The data generated by the emotion engine is a crucial source of information, particularly in generating choices, enabling suggestions tailored to the user's current emotions. For example, when a user is stressed, the server might suggest options that are beneficial for relaxation.

[0334] Using a generative AI model, the server generates optimal choices adapted to the user's current state based on insights gained from analysis. These choices reflect the user's emotional needs at that moment by taking into account emotional state data.

[0335] For example, if the emotion engine detects "fatigue" while a user is browsing social media on their device during a break at work, the server will suggest nearby cafes where they can relax or stretching videos to help them change their mood. In this way, users can make appropriate choices based on their emotional state, leading to a more satisfying daily life.

[0336] This system aims to improve users' quality of life by providing a more personalized experience through an emotion engine that considers the user's emotions when making choices.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] Device: Obtain user consent and enable voice input and text analysis tools. This prepares the device for real-time collection of sentiment data from user speech and entered text.

[0340] Step 2:

[0341] Device: In addition to the user's daily behavioral data (location information, purchase history, social media posts), it collects acquired emotional data. This emotional data is analyzed by an emotion engine designed to identify a variety of emotions such as joy, sadness, and stress.

[0342] Step 3:

[0343] Terminal: Collects behavioral and emotional data and sends it to the server within the user's permission. Transmission occurs periodically, according to the frequency specified by the user.

[0344] Step 4:

[0345] Server: Integrates received data into the database and organizes information for each user. During this process, filtering and cleaning processes are performed to maintain data consistency.

[0346] Step 5:

[0347] Server: Analyzes integrated data and updates user behavior patterns and preference models. Emotional data is particularly important and influences the generation of situation-appropriate choices.

[0348] Step 6:

[0349] Server: Using a generative AI model, it generates the most suitable options for the user based on all the collected data. This process incorporates the user's current emotional state; for example, if the user is feeling stressed, it will create suggestions that promote relaxation.

[0350] Step 7:

[0351] Server: Sorts the generated options according to priority and sends them to the user's terminal.

[0352] Step 8:

[0353] Terminal: Receives selections from the server and notifies the user. Notifications are delivered using push notifications, in-app messages, and widgets, and are designed for easy user access.

[0354] Step 9:

[0355] User: Check notifications from their device, select options of interest, and decide on their next action. Based on their selection, they begin a new experience or action.

[0356] This series of steps allows users to make choices that align with their emotional state at any given time, resulting in a more personalized experience.

[0357] (Example 2)

[0358] 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".

[0359] In today's information society, it is difficult for users to choose the best option from a vast array of choices. In particular, there is a lack of systems that provide appropriate choices based on the user's emotional state. Choices that ignore emotional information cannot adequately increase user satisfaction and may even negatively impact their quality of life.

[0360] 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.

[0361] In this invention, the server includes means for collecting user behavior information, preference information, and emotional information; means for analyzing the information and generating behavior patterns, preference models, and emotional states; and means for generating choices suitable for the user based on the patterns, models, and states. This makes it possible to provide personalized choices that correspond to the user's emotional state.

[0362] "User behavior information" refers to data about the actions and tendencies that users perform on a daily basis.

[0363] "Preference information" refers to data about a user's preferences and interests.

[0364] "Emotional information" refers to data that indicates a user's emotional state or psychological condition.

[0365] "Options" refer to multiple possible actions or decisions presented to the user.

[0366] A "generative model" is an algorithm or computational method used to analyze data and generate new information or options.

[0367] A "behavioral pattern" is a model that shows the regularity or common tendencies in user behavior.

[0368] A "preference model" is a data model built to represent and utilize user preferences.

[0369] "Emotional state" refers to the user's emotions and psychological condition at a specific moment in time.

[0370] "Communication network service information" refers to data about a user's online activities, and is information provided via a communication network.

[0371] In an embodiment for carrying out this invention, the system consists of three elements: a server, a terminal, and a user.

[0372] Users first generate behavioral, preference, and emotional information through their daily use of their devices. These devices are equipped with voice and text input capabilities, and analysis software called an emotion engine analyzes this data in real time to determine the user's emotional state. This emotion engine identifies voice tone and keywords within the text to classify the user's emotions.

[0373] The device transmits location information, transaction history, and communication network service information, along with analyzed emotional information, to the server. The server stores this information in a database and generates user behavior patterns and preference models. It also records the emotional state based on the generated data and uses this information to provide the user with the most suitable options.

[0374] As a concrete example, if the emotion engine detects "fatigue" while a user is browsing entertainment information on their device during their lunch break, the server will use a generative AI model to suggest a nearby quiet cafe or a short relaxation video to the user. This suggestion is instructed to the generative AI model as a prompt: "Please provide options to alleviate the fatigue the user is currently feeling."

[0375] As described above, the system aims to improve user satisfaction and quality of life by utilizing real-time user sentiment data and providing personalized options tailored to individual needs.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The user inputs voice and text data through the device. The device collects this data and inputs it into the emotion engine. Specifically, it uses speech recognition technology to convert the voice data into text and prepares it for emotion analysis by combining it with the text data.

[0379] Step 2:

[0380] The device's emotion engine analyzes voice and text data to determine the user's emotional state. In this process, the emotion engine extracts features from the input data and compares them with an existing emotion database to output an emotion category (e.g., "joy," "sadness," "fatigue," etc.). Specifically, it performs matching based on voice tone and keywords in the text.

[0381] Step 3:

[0382] The device acquires emotional data, location information, purchase history, and communication network service information, and sends this data to the server. Specifically, it obtains the current location from location services and purchase history from past transaction logs, and prepares to send all the information as packets to the server.

[0383] Step 4:

[0384] The server stores the received data in a database and analyzes the user's behavior patterns, preference models, and emotional states. The input consists of multiple user data points stored in the database, and new patterns and models are generated based on this data. This process utilizes data mining techniques to extract useful patterns and generates behavioral pattern models and preference models as output.

[0385] Step 5:

[0386] The server uses a generative AI model to generate suitable options for the user based on the analysis results. Here, the generative AI model receives instructions using prompts and outputs appropriate options (e.g., relaxation locations, stretching videos, etc.) based on the input data. Specifically, the generative AI model searches the cloud or database for resources that match the analyzed emotional state and generates suggestions that meet the user's needs.

[0387] Step 6:

[0388] The server sends the generated options to the user's device and presents them. The device receives this and notifies the user visually or audibly. Specific actions include displaying information in the notification bar or prompting suggestions with voice guidance.

[0389] (Application Example 2)

[0390] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0391] When users engage with digital content, there is a challenge in providing them with appropriate choices that align with their emotional state at any given moment. Furthermore, traditional methods struggle to achieve deep personalization that considers not only user preferences and behavioral data but also their real-time emotional state.

[0392] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0393] In this invention, the server includes means for collecting user behavior data, preference data, and emotional data; means for analyzing the data and generating behavior patterns, preference models, and emotional states; and means for generating optimal choices for the user based on the patterns, models, and emotional states. This makes it possible to provide personalized content based on the user's emotional state.

[0394] "Behavioral data" refers to information that records a user's activities and usage patterns.

[0395] "Preference data" refers to information about the content and services that users prefer.

[0396] "Emotional data" refers to information about a user's emotional state, analyzed from sources such as voice and text.

[0397] "Behavioral patterns" refer to typical behavioral tendencies and habits analyzed from user behavior data.

[0398] A "preference model" is a model that shows individualized preference trends derived from user preference data.

[0399] "Emotional state" represents the user's current emotional condition and is a real-time analysis result.

[0400] "Options" refer to the suggested actions or content presented to the user.

[0401] "Content" refers to information resources such as movies, music, and videos that are provided to users.

[0402] A "generative artificial intelligence model" is an artificial intelligence model used to generate appropriate choices using data analysis.

[0403] The system implementing this invention mainly consists of a server, a terminal, and a user. The terminal is a device that provides a user interface, such as a smartphone or smart glasses. The terminal is equipped with an emotion recognition engine that analyzes the user's voice and text data in real time. The analyzed emotion data is sent to the server along with the user's geographical location data, purchase history data, and social networking service data.

[0404] Based on this data, the server generates customized behavioral patterns, preference models, and emotional states for each user. A generative artificial intelligence model is used for data analysis and choice generation. This model considers the generated behavioral patterns, preference models, and emotional states to propose a list of content optimized for the user.

[0405] For example, when a user is using a streaming service, if the emotion engine detects fatigue or stress, it will recommend uplifting comedy movies or relaxing music. This suggestion will be notified to the user and displayed on their device as available content.

[0406] As an example of a prompt message that a generative AI model might use to generate choices, we can use a sentence like, "Your current emotional state has been detected as 'fatigue.' Please recommend a relaxing movie." This allows users to smoothly select content that matches their emotional state, providing a highly satisfying experience.

[0407] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0408] Step 1:

[0409] The device sends the user's voice and text data as input to an emotion recognition engine, which analyzes the emotional state in real time. As a result of the analysis, it outputs the user's current emotional state.

[0410] Step 2:

[0411] The device transmits user emotional state data, geographical location data, purchase history data, and social networking service data to the server. This data serves as input necessary for generating user behavior patterns and preference models.

[0412] Step 3:

[0413] The server uses data analysis software to generate user behavior patterns and preference models based on the received data. As a result of the analysis, it outputs customized behavior patterns, preference models, and emotional states for each user.

[0414] Step 4:

[0415] The server uses the behavioral patterns, preference models, and emotional states generated by the artificial intelligence model as input to generate a list of user-optimized content. This process utilizes prompt statements to generate choices. The generated results are output as choices suggested to the user.

[0416] Step 5:

[0417] The server sends the generated content list to the device. Based on the received list, the device notifies the user and displays content on the screen that matches their emotional state. By using the suggested content, the user can have a more satisfying experience.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] [Third Embodiment]

[0422] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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".

[0434] This invention is a system that provides optimal choices based on the user's personal data, with the server, terminal, and user working in cooperation. The user's terminal acts as the starting point for data collection, first acquiring location information and purchase history. This information is transmitted to the server as needed with the user's permission. The terminal also has the function of connecting to the API of the social networking service used by the user and collecting posts and reactions.

[0435] The server receives the collected data and stores it in a database for analysis. The information stored in the database is analyzed using machine learning algorithms to generate user behavior patterns and preference models. This analysis helps understand what actions users tend to take and when, and what choices lead to high satisfaction.

[0436] Using generative AI, the server generates the optimal choices to suggest to the user based on these analysis results. These choices are customized according to the user's past behavioral trends and current situation. For example, it may suggest information about newly opened cafes or tourist spots that are helpful for travel planning.

[0437] The generated options are sent to the device in real time. The device has the capability to display these suggestions as push notifications or in-app messages so that users can easily review them. Users can select the options that interest them from the suggested choices and use them as a reference for their next action.

[0438] A concrete example is when a user is looking for a new hobby. The server, using past data it has collected, identifies that the user frequently liked cooking-related social media posts in the past. Based on this information, the server can suggest new cooking classes or sales on seasonings. In this way, the user can become aware of their latent interests and make new choices.

[0439] The following describes the processing flow.

[0440] Step 1:

[0441] Device: Confirms user consent and enables location services. Periodically collects location information and purchase history data. Also obtains user posts and like history via SNS APIs.

[0442] Step 2:

[0443] Server: Receives data sent from terminals and saves it to the database. When saving, data cleaning is performed to maintain the integrity and consistency of the information.

[0444] Step 3:

[0445] Server: Machine learning algorithms are applied to prepare the stored data for analysis. This identifies user behavior patterns and generates preference models. Clustering techniques are used in particular to group user interests and visit trends.

[0446] Step 4:

[0447] Server: Using generated behavioral patterns and preference models, it leverages generative AI to create optimal choices for the user. The generated choices are based on the user's past behavior, current trends, and available news and event information.

[0448] Step 5:

[0449] Server: Sends prioritized options to the terminal. Here, the information most relevant to the user is presented in the most prominent way.

[0450] Step 6:

[0451] Device: The device notifies the user of the received options in an easy-to-understand format. Notification methods such as push notifications and in-app messages are designed to be easily accessible to the user.

[0452] Step 7:

[0453] User: Review the options displayed on the device and select the next action that best suits their current interests and schedule. Based on the selected information, they can then plan specific actions.

[0454] (Example 1)

[0455] 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."

[0456] Conventional personalization systems have a problem in that they are not sufficient to effectively generate and provide individualized suggestions in real time based on the characteristics of the user. Furthermore, it is difficult to efficiently utilize users' location information, purchase history, and information sharing service data, and there is a lack of methods to provide appropriate choices that meet individual needs in a timely manner.

[0457] 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.

[0458] In this invention, the server includes means for collecting user characteristic data, means for analyzing the data to generate a user behavior pattern and preference model, and means for creating optimal choices for the user based on the behavior pattern and preference model. This makes it possible to provide individualized suggestions tailored to each user in real time.

[0459] "User characteristic data" refers to information related to an individual user, including location information, purchase history, and activity data from information sharing services.

[0460] A "behavioral and preference model" is a model extracted by analyzing a user's past behavioral patterns and preferences, and it shows what kinds of choices the user prefers.

[0461] "Optimal choice" means providing the most suitable suggestions or options to the user based on their personal data and generated behavioral patterns and preference models.

[0462] A "user terminal" is an electronic device used by users to display information and receive suggestions from a server, and includes devices such as smartphones and tablets.

[0463] A "generative AI model" is a model that uses artificial intelligence technology and includes algorithms for generating new information or options based on input data.

[0464] This invention is a system that provides optimal choices based on user characteristic data. The system is primarily realized through the organic cooperation of a server, terminals, and users.

[0465] Data collection

[0466] The device acts as a data collection hub, first acquiring the user's location information and purchase history. This information is collected with the user's consent. Furthermore, the device has the functionality to connect to information sharing service APIs and collect posted content and responses to it. The device incorporates hardware and software such as a GPS sensor and online shopping APIs.

[0467] Data transmission and storage

[0468] The terminal encrypts the collected data and sends it to the server. The server stores the received data in a database and prepares it for analysis. The database is a management platform that facilitates the secure storage and analysis of data.

[0469] Analysis and generation of optimal options

[0470] The server uses machine learning libraries (such as TensorFlow and PyTorch) to generate a model of the user's behavior and preferences. Based on this model, the server uses a generative AI model to create prompts, generating optimal choices that meet the user's needs. These prompts include specific instructions based on the user's recent behavior data and interests.

[0471] Providing and displaying options

[0472] The generated options are immediately sent to the device. The device then displays these suggestions as push notifications or in-app messages to help users access them without confusion.

[0473] A concrete example is a situation where a user is exploring new interests. If the server analyzes past data it has collected to determine that the user is interested in cooking, it can suggest information about cooking classes or food sales. The goal of this suggestion is to provide the user with useful information in real time.

[0474] Example prompt: "Based on the user's past social media activity and purchase history, suggest new hobbies and activities related to their interests."

[0475] In this way, the system can provide users with beneficial options and meet their individual needs.

[0476] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0477] Step 1:

[0478] The device collects the user's location information and purchase history. It uses location data obtained via GPS sensors and purchase data obtained from online shopping APIs as input. This input data is cleansed, its format is standardized, and then it is converted into a format suitable for transmission.

[0479] Step 2:

[0480] The device connects to the API of an information sharing service to retrieve user posts and reactions. User data from the information sharing service is used as input. Specifically, it collects user-posted content and reaction data such as likes and comments, and converts this data into a specified format.

[0481] Step 3:

[0482] The device encrypts the collected data and sends it to the server. The input consists of location information, purchase history, and social media data obtained in steps 1 and 2. The device combines this data and sends it to the server using the HTTPS protocol.

[0483] Step 4:

[0484] The server stores the received data in a database. The input is user characteristic data sent from the terminal. The server writes the data to the database in preparation for analysis, organizing the data and making it accessible.

[0485] Step 5:

[0486] The server uses machine learning algorithms to generate user behavior and preference models. It uses user data stored in a database as input, extracts behavioral patterns, and models them. The output is a behavioral model that reflects user preferences.

[0487] Step 6:

[0488] The server uses a generative AI model to create prompt messages and generate the most suitable options for the user. The input is the behavioral model generated in step 5, and specific suggestions are generated based on this model. The output is information and service suggestions tailored to the user.

[0489] Step 7:

[0490] The server sends the generated optimal choices to the terminal. The input is the data of the optimal choices obtained in step 6. The server sends the choices to the terminal in real time, allowing the user to check them immediately.

[0491] Step 8:

[0492] The device displays suggestions to the user as push notifications or in-app messages. The input is the best choice sent from the server. The device receives the data and displays it in a format that the user can easily access and select.

[0493] (Application Example 1)

[0494] 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."

[0495] Traditional shopping systems tend to offer generic product suggestions to users, lacking personalized recommendations based on individual preferences and behavioral patterns. This means users often have to spend time finding products they're interested in themselves, making it difficult to enjoy an efficient shopping experience.

[0496] 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.

[0497] In this invention, the server includes means for collecting user behavior data and preference data; means for analyzing the data and generating behavior patterns and preference models; means for generating optimal choices for the user based on the patterns and models; and means for locating the user in a real-world location and providing information from commercial facilities in order to provide the choices in relation to commercial activities. This enables the user to appropriately receive product information and promotions tailored to their preferences.

[0498] "User behavior data" refers to information that shows a series of actions taken by a user and the history of those actions.

[0499] "Preference data" refers to information about users' interests and preferences, and indicates tendencies regarding specific behaviors and choices.

[0500] A "behavioral pattern" is a pattern that shows the tendencies and frequency of actions a user takes over a certain period of time.

[0501] A "preference model" is a model that numerically or algorithmically represents a user's preferences and is used to predict their tastes.

[0502] A "means for generating options" refers to a system for creating specific suggestions and options to present to users based on their data.

[0503] "Means for providing in connection with commercial activities" refers to a system for providing users with commercial-related information and suggestions within or near a commercial facility.

[0504] "Means for determining the user's location" refers to a system for acquiring and analyzing the user's current location in real time.

[0505] "Information from commercial facilities" refers to various types of information provided by commercial facilities, such as products, services, promotions, and events.

[0506] This invention features a system that provides users with optimal commercial activity-related options based on their behavioral data and preference data.

[0507] Program Overview:

[0508] The server forms the core of this system, collecting, analyzing, and generating choices based on data sent by the user. The terminal acquires the user's location information in real time and sends it to the server. It also collects the user's purchase history and posts from social networking services. Smartphones are often used for this purpose. The collected data is stored in a database by the server and analyzed using machine learning algorithms.

[0509] Hardware and software:

[0510] It is recommended that the server be located on a cloud service (such as AWS or Google Cloud). Machine learning libraries such as Python's scikit-learn or TensorFlow can be used for data analysis. The devices include iOS or Android mobile devices. These devices send data to the server using an API.

[0511] Use of Generative AI:

[0512] The OpenAI API is used as the generative AI model. The server uses the generative AI to generate personalized product suggestions based on user behavior data. This process includes prompt messages that contain information tailored to the user's interests and current situation.

[0513] Specific example:

[0514] For example, when a user is in a shopping mall, the server suggests stores and products that are likely to interest the user based on their location and past purchase history. These suggestions are delivered to the user via push notifications on their smartphone.

[0515] Example of a prompt:

[0516] "This user has been identified as a fan of mystery novels in the past. Please provide information on mystery-related events and merchandise currently available in bookstores."

[0517] This system allows users to automatically find products that match their interests, providing a more efficient and satisfying shopping experience.

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1:

[0520] The device obtains location information with the user's permission. This location information is collected using GPS functionality and becomes data to determine the user's current location in real time. This data is sent to a server and linked to a specific location within the commercial facility.

[0521] Step 2:

[0522] The device collects the user's purchase history and posts obtained through social networking service APIs. This data, which reflects the user's past behavior and preferences, is sent to the server. This information is sent in text data format and used to generate preference models.

[0523] Step 3:

[0524] The server receives collected location data, purchase history, and data from social media, and stores it in a database. The stored data is then analyzed using a Python machine learning library (e.g., scikit-learn) to generate behavioral patterns and preference models.

[0525] Step 4:

[0526] The server generates the most suitable options for the user from the analyzed data. This process uses a generative AI model (e.g., OpenAI's API) to create prompts for products and events that match the user's preferences. These generated prompts serve as a guide for extracting the most relevant commercial information.

[0527] Step 5:

[0528] The server compiles information from commercial facilities based on the generated choices and sends it to the terminal. The terminal displays this information to the user as a push notification. This allows the user to receive recommended product and event information in real time.

[0529] 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.

[0530] This invention is a system that provides more personalized choices by collecting and analyzing emotional data in addition to user behavioral data and preference data. The system consists of a server, a terminal, and a user, and is equipped with a function to recognize the user's emotional state using an emotion engine.

[0531] The user's device uses an emotion engine to analyze voice and text data and determine the user's emotions in real time. This emotion data is sent to the server along with location information, purchase history, and social networking service data. The collection of emotion data is non-invasive and done with the user's permission.

[0532] The server stores various data sent from the terminal in a database and uses this data to analyze the user's behavior patterns, preference models, and emotional state. The data generated by the emotion engine is a crucial source of information, particularly in generating choices, enabling suggestions tailored to the user's current emotions. For example, when a user is stressed, the server might suggest options that are beneficial for relaxation.

[0533] Using a generative AI model, the server generates optimal choices adapted to the user's current state based on insights gained from analysis. These choices reflect the user's emotional needs at that moment by taking into account emotional state data.

[0534] For example, if the emotion engine detects "fatigue" while a user is browsing social media on their device during a break at work, the server will suggest nearby cafes where they can relax or stretching videos to help them change their mood. In this way, users can make appropriate choices based on their emotional state, leading to a more satisfying daily life.

[0535] This system aims to improve users' quality of life by providing a more personalized experience through an emotion engine that considers the user's emotions when making choices.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] Device: Obtain user consent and enable voice input and text analysis tools. This prepares the device for real-time collection of sentiment data from user speech and entered text.

[0539] Step 2:

[0540] Device: In addition to the user's daily behavioral data (location information, purchase history, social media posts), it collects acquired emotional data. This emotional data is analyzed by an emotion engine designed to identify a variety of emotions such as joy, sadness, and stress.

[0541] Step 3:

[0542] Terminal: Collects behavioral and emotional data and sends it to the server within the user's permission. Transmission occurs periodically, according to the frequency specified by the user.

[0543] Step 4:

[0544] Server: Integrates received data into the database and organizes information for each user. During this process, filtering and cleaning processes are performed to maintain data consistency.

[0545] Step 5:

[0546] Server: Analyzes integrated data and updates user behavior patterns and preference models. Emotional data is particularly important and influences the generation of situation-appropriate choices.

[0547] Step 6:

[0548] Server: Using a generative AI model, it generates the most suitable options for the user based on all the collected data. This process incorporates the user's current emotional state; for example, if the user is feeling stressed, it will create suggestions that promote relaxation.

[0549] Step 7:

[0550] Server: Sorts the generated options according to priority and sends them to the user's terminal.

[0551] Step 8:

[0552] Terminal: Receives selections from the server and notifies the user. Notifications are delivered using push notifications, in-app messages, and widgets, and are designed for easy user access.

[0553] Step 9:

[0554] User: Check notifications from their device, select options of interest, and decide on their next action. Based on their selection, they begin a new experience or action.

[0555] This series of steps allows users to make choices that align with their emotional state at any given time, resulting in a more personalized experience.

[0556] (Example 2)

[0557] 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."

[0558] In today's information society, it is difficult for users to choose the best option from a vast array of choices. In particular, there is a lack of systems that provide appropriate choices based on the user's emotional state. Choices that ignore emotional information cannot adequately increase user satisfaction and may even negatively impact their quality of life.

[0559] 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.

[0560] In this invention, the server includes means for collecting user behavior information, preference information, and emotional information; means for analyzing the information and generating behavior patterns, preference models, and emotional states; and means for generating choices suitable for the user based on the patterns, models, and states. This makes it possible to provide personalized choices that correspond to the user's emotional state.

[0561] "User behavior information" refers to data about the actions and tendencies that users perform on a daily basis.

[0562] "Preference information" refers to data about a user's preferences and interests.

[0563] "Emotional information" refers to data that indicates a user's emotional state or psychological condition.

[0564] "Options" refer to multiple possible actions or decisions presented to the user.

[0565] A "generative model" is an algorithm or computational method used to analyze data and generate new information or options.

[0566] A "behavioral pattern" is a model that shows the regularity or common tendencies in user behavior.

[0567] A "preference model" is a data model built to represent and utilize user preferences.

[0568] "Emotional state" refers to the user's emotions and psychological condition at a specific moment in time.

[0569] "Communication network service information" refers to data about a user's online activities, and is information provided via a communication network.

[0570] In an embodiment for carrying out this invention, the system consists of three elements: a server, a terminal, and a user.

[0571] Users first generate behavioral, preference, and emotional information through their daily use of their devices. These devices are equipped with voice and text input capabilities, and analysis software called an emotion engine analyzes this data in real time to determine the user's emotional state. This emotion engine identifies voice tone and keywords within the text to classify the user's emotions.

[0572] The device transmits location information, transaction history, and communication network service information, along with analyzed emotional information, to the server. The server stores this information in a database and generates user behavior patterns and preference models. It also records the emotional state based on the generated data and uses this information to provide the user with the most suitable options.

[0573] As a concrete example, if the emotion engine detects "fatigue" while a user is browsing entertainment information on their device during their lunch break, the server will use a generative AI model to suggest a nearby quiet cafe or a short relaxation video to the user. This suggestion is instructed to the generative AI model as a prompt: "Please provide options to alleviate the fatigue the user is currently feeling."

[0574] As described above, the system aims to improve user satisfaction and quality of life by utilizing real-time user sentiment data and providing personalized options tailored to individual needs.

[0575] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0576] Step 1:

[0577] The user inputs voice and text data through the device. The device collects this data and inputs it into the emotion engine. Specifically, it uses speech recognition technology to convert the voice data into text and prepares it for emotion analysis by combining it with the text data.

[0578] Step 2:

[0579] The device's emotion engine analyzes voice and text data to determine the user's emotional state. In this process, the emotion engine extracts features from the input data and compares them with an existing emotion database to output an emotion category (e.g., "joy," "sadness," "fatigue," etc.). Specifically, it performs matching based on voice tone and keywords in the text.

[0580] Step 3:

[0581] The device acquires emotional data, location information, purchase history, and communication network service information, and sends this data to the server. Specifically, it obtains the current location from location services and purchase history from past transaction logs, and prepares to send all the information as packets to the server.

[0582] Step 4:

[0583] The server stores the received data in a database and analyzes the user's behavior patterns, preference models, and emotional states. The input consists of multiple user data points stored in the database, and new patterns and models are generated based on this data. This process utilizes data mining techniques to extract useful patterns and generates behavioral pattern models and preference models as output.

[0584] Step 5:

[0585] The server uses a generative AI model to generate suitable options for the user based on the analysis results. Here, the generative AI model receives instructions using prompts and outputs appropriate options (e.g., relaxation locations, stretching videos, etc.) based on the input data. Specifically, the generative AI model searches the cloud or database for resources that match the analyzed emotional state and generates suggestions that meet the user's needs.

[0586] Step 6:

[0587] The server sends the generated options to the user's device and presents them. The device receives this and notifies the user visually or audibly. Specific actions include displaying information in the notification bar or prompting suggestions with voice guidance.

[0588] (Application Example 2)

[0589] 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."

[0590] When users engage with digital content, there is a challenge in providing them with appropriate choices that align with their emotional state at any given moment. Furthermore, traditional methods struggle to achieve deep personalization that considers not only user preferences and behavioral data but also their real-time emotional state.

[0591] 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.

[0592] In this invention, the server includes means for collecting user behavior data, preference data, and emotional data; means for analyzing the data and generating behavior patterns, preference models, and emotional states; and means for generating optimal choices for the user based on the patterns, models, and emotional states. This makes it possible to provide personalized content based on the user's emotional state.

[0593] "Behavioral data" refers to information that records a user's activities and usage patterns.

[0594] "Preference data" refers to information about the content and services that users prefer.

[0595] "Emotional data" refers to information about a user's emotional state, analyzed from sources such as voice and text.

[0596] "Behavioral patterns" refer to typical behavioral tendencies and habits analyzed from user behavior data.

[0597] A "preference model" is a model that shows individualized preference trends derived from user preference data.

[0598] "Emotional state" represents the user's current emotional condition and is a real-time analysis result.

[0599] "Options" refer to the suggested actions or content presented to the user.

[0600] "Content" refers to information resources such as movies, music, and videos that are provided to users.

[0601] A "generative artificial intelligence model" is an artificial intelligence model used to generate appropriate choices using data analysis.

[0602] The system implementing this invention mainly consists of a server, a terminal, and a user. The terminal is a device that provides a user interface, such as a smartphone or smart glasses. The terminal is equipped with an emotion recognition engine that analyzes the user's voice and text data in real time. The analyzed emotion data is sent to the server along with the user's geographical location data, purchase history data, and social networking service data.

[0603] Based on this data, the server generates customized behavioral patterns, preference models, and emotional states for each user. A generative artificial intelligence model is used for data analysis and choice generation. This model considers the generated behavioral patterns, preference models, and emotional states to propose a list of content optimized for the user.

[0604] For example, when a user is using a streaming service, if the emotion engine detects fatigue or stress, it will recommend uplifting comedy movies or relaxing music. This suggestion will be notified to the user and displayed on their device as available content.

[0605] As an example of a prompt message that a generative AI model might use to generate choices, we can use a sentence like, "Your current emotional state has been detected as 'fatigue.' Please recommend a relaxing movie." This allows users to smoothly select content that matches their emotional state, providing a highly satisfying experience.

[0606] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0607] Step 1:

[0608] The device sends the user's voice and text data as input to an emotion recognition engine, which analyzes the emotional state in real time. As a result of the analysis, it outputs the user's current emotional state.

[0609] Step 2:

[0610] The device transmits user emotional state data, geographical location data, purchase history data, and social networking service data to the server. This data serves as input necessary for generating user behavior patterns and preference models.

[0611] Step 3:

[0612] The server uses data analysis software to generate user behavior patterns and preference models based on the received data. As a result of the analysis, it outputs customized behavior patterns, preference models, and emotional states for each user.

[0613] Step 4:

[0614] The server uses the behavioral patterns, preference models, and emotional states generated by the artificial intelligence model as input to generate a list of user-optimized content. This process utilizes prompt statements to generate choices. The generated results are output as choices suggested to the user.

[0615] Step 5:

[0616] The server sends the generated content list to the device. Based on the received list, the device notifies the user and displays content on the screen that matches their emotional state. By using the suggested content, the user can have a more satisfying experience.

[0617] 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.

[0618] 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.

[0619] 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.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] 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.

[0623] 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).

[0624] 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.

[0625] 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.

[0626] 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).

[0627] 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.

[0628] 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.

[0629] 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.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] 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".

[0634] This invention is a system that provides optimal choices based on the user's personal data, with the server, terminal, and user working in cooperation. The user's terminal acts as the starting point for data collection, first acquiring location information and purchase history. This information is transmitted to the server as needed with the user's permission. The terminal also has the function of connecting to the API of the social networking service used by the user and collecting posts and reactions.

[0635] The server receives the collected data and stores it in a database for analysis. The information stored in the database is analyzed using machine learning algorithms to generate user behavior patterns and preference models. This analysis helps understand what actions users tend to take and when, and what choices lead to high satisfaction.

[0636] Using generative AI, the server generates the optimal choices to suggest to the user based on these analysis results. These choices are customized according to the user's past behavioral trends and current situation. For example, it may suggest information about newly opened cafes or tourist spots that are helpful for travel planning.

[0637] The generated options are sent to the device in real time. The device has the capability to display these suggestions as push notifications or in-app messages so that users can easily review them. Users can select the options that interest them from the suggested choices and use them as a reference for their next action.

[0638] A concrete example is when a user is looking for a new hobby. The server, using past data it has collected, identifies that the user frequently liked cooking-related social media posts in the past. Based on this information, the server can suggest new cooking classes or sales on seasonings. In this way, the user can become aware of their latent interests and make new choices.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] Device: Confirms user consent and enables location services. Periodically collects location information and purchase history data. Also obtains user posts and like history via SNS APIs.

[0642] Step 2:

[0643] Server: Receives data sent from terminals and saves it to the database. When saving, data cleaning is performed to maintain the integrity and consistency of the information.

[0644] Step 3:

[0645] Server: Machine learning algorithms are applied to prepare the stored data for analysis. This identifies user behavior patterns and generates preference models. Clustering techniques are used in particular to group user interests and visit trends.

[0646] Step 4:

[0647] Server: Using generated behavioral patterns and preference models, it leverages generative AI to create optimal choices for the user. The generated choices are based on the user's past behavior, current trends, and available news and event information.

[0648] Step 5:

[0649] Server: Sends prioritized options to the terminal. Here, the information most relevant to the user is presented in the most prominent way.

[0650] Step 6:

[0651] Device: The device notifies the user of the received options in an easy-to-understand format. Notification methods such as push notifications and in-app messages are designed to be easily accessible to the user.

[0652] Step 7:

[0653] User: Review the options displayed on the device and select the next action that best suits their current interests and schedule. Based on the selected information, they can then plan specific actions.

[0654] (Example 1)

[0655] 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".

[0656] Conventional personalization systems have a problem in that they are not sufficient to effectively generate and provide individualized suggestions in real time based on the characteristics of the user. Furthermore, it is difficult to efficiently utilize users' location information, purchase history, and information sharing service data, and there is a lack of methods to provide appropriate choices that meet individual needs in a timely manner.

[0657] 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.

[0658] In this invention, the server includes means for collecting user characteristic data, means for analyzing the data to generate a user behavior pattern and preference model, and means for creating optimal choices for the user based on the behavior pattern and preference model. This makes it possible to provide individualized suggestions tailored to each user in real time.

[0659] "User characteristic data" refers to information related to an individual user, including location information, purchase history, and activity data from information sharing services.

[0660] A "behavioral and preference model" is a model extracted by analyzing a user's past behavioral patterns and preferences, and it shows what kinds of choices the user prefers.

[0661] "Optimal choice" means providing the most suitable suggestions or options to the user based on their personal data and generated behavioral patterns and preference models.

[0662] A "user terminal" is an electronic device used by users to display information and receive suggestions from a server, and includes devices such as smartphones and tablets.

[0663] A "generative AI model" is a model that uses artificial intelligence technology and includes algorithms for generating new information or options based on input data.

[0664] This invention is a system that provides optimal choices based on user characteristic data. The system is primarily realized through the organic cooperation of a server, terminals, and users.

[0665] Data collection

[0666] The device acts as a data collection hub, first acquiring the user's location information and purchase history. This information is collected with the user's consent. Furthermore, the device has the functionality to connect to information sharing service APIs and collect posted content and responses to it. The device incorporates hardware and software such as a GPS sensor and online shopping APIs.

[0667] Data transmission and storage

[0668] The terminal encrypts the collected data and sends it to the server. The server stores the received data in a database and prepares it for analysis. The database is a management platform that facilitates the secure storage and analysis of data.

[0669] Analysis and generation of optimal options

[0670] The server uses machine learning libraries (such as TensorFlow and PyTorch) to generate a model of the user's behavior and preferences. Based on this model, the server uses a generative AI model to create prompts, generating optimal choices that meet the user's needs. These prompts include specific instructions based on the user's recent behavior data and interests.

[0671] Providing and displaying options

[0672] The generated options are immediately sent to the device. The device then displays these suggestions as push notifications or in-app messages to help users access them without confusion.

[0673] A concrete example is a situation where a user is exploring new interests. If the server analyzes past data it has collected to determine that the user is interested in cooking, it can suggest information about cooking classes or food sales. The goal of this suggestion is to provide the user with useful information in real time.

[0674] Example prompt: "Based on the user's past social media activity and purchase history, suggest new hobbies and activities related to their interests."

[0675] In this way, the system can provide users with beneficial options and meet their individual needs.

[0676] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0677] Step 1:

[0678] The device collects the user's location information and purchase history. It uses location data obtained via GPS sensors and purchase data obtained from online shopping APIs as input. This input data is cleansed, its format is standardized, and then it is converted into a format suitable for transmission.

[0679] Step 2:

[0680] The device connects to the API of an information sharing service to retrieve user posts and reactions. User data from the information sharing service is used as input. Specifically, it collects user-posted content and reaction data such as likes and comments, and converts this data into a specified format.

[0681] Step 3:

[0682] The device encrypts the collected data and sends it to the server. The input consists of location information, purchase history, and social media data obtained in steps 1 and 2. The device combines this data and sends it to the server using the HTTPS protocol.

[0683] Step 4:

[0684] The server stores the received data in a database. The input is user characteristic data sent from the terminal. The server writes the data to the database in preparation for analysis, organizing the data and making it accessible.

[0685] Step 5:

[0686] The server uses machine learning algorithms to generate user behavior and preference models. It uses user data stored in a database as input, extracts behavioral patterns, and models them. The output is a behavioral model that reflects user preferences.

[0687] Step 6:

[0688] The server uses a generative AI model to create prompt messages and generate the most suitable options for the user. The input is the behavioral model generated in step 5, and specific suggestions are generated based on this model. The output is information and service suggestions tailored to the user.

[0689] Step 7:

[0690] The server sends the generated optimal choices to the terminal. The input is the data of the optimal choices obtained in step 6. The server sends the choices to the terminal in real time, allowing the user to check them immediately.

[0691] Step 8:

[0692] The device displays suggestions to the user as push notifications or in-app messages. The input is the best choice sent from the server. The device receives the data and displays it in a format that the user can easily access and select.

[0693] (Application Example 1)

[0694] 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".

[0695] Traditional shopping systems tend to offer generic product suggestions to users, lacking personalized recommendations based on individual preferences and behavioral patterns. This means users often have to spend time finding products they're interested in themselves, making it difficult to enjoy an efficient shopping experience.

[0696] 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.

[0697] In this invention, the server includes means for collecting user behavior data and preference data; means for analyzing the data and generating behavior patterns and preference models; means for generating optimal choices for the user based on the patterns and models; and means for locating the user in a real-world location and providing information from commercial facilities in order to provide the choices in relation to commercial activities. This enables the user to appropriately receive product information and promotions tailored to their preferences.

[0698] "User behavior data" refers to information that shows a series of actions taken by a user and the history of those actions.

[0699] "Preference data" refers to information about users' interests and preferences, and indicates tendencies regarding specific behaviors and choices.

[0700] A "behavioral pattern" is a pattern that shows the tendencies and frequency of actions a user takes over a certain period of time.

[0701] A "preference model" is a model that numerically or algorithmically represents a user's preferences and is used to predict their tastes.

[0702] A "means for generating options" refers to a system for creating specific suggestions and options to present to users based on their data.

[0703] "Means for providing in connection with commercial activities" refers to a system for providing users with commercial-related information and suggestions within or near a commercial facility.

[0704] "Means for determining the user's location" refers to a system for acquiring and analyzing the user's current location in real time.

[0705] "Information from commercial facilities" refers to various types of information provided by commercial facilities, such as products, services, promotions, and events.

[0706] This invention features a system that provides users with optimal commercial activity-related options based on their behavioral data and preference data.

[0707] Program Overview:

[0708] The server forms the core of this system, collecting, analyzing, and generating choices based on data sent by the user. The terminal acquires the user's location information in real time and sends it to the server. It also collects the user's purchase history and posts from social networking services. Smartphones are often used for this purpose. The collected data is stored in a database by the server and analyzed using machine learning algorithms.

[0709] Hardware and software:

[0710] It is recommended that the server be located on a cloud service (such as AWS or Google Cloud). Machine learning libraries such as Python's scikit-learn or TensorFlow can be used for data analysis. The devices include iOS or Android mobile devices. These devices send data to the server using an API.

[0711] Use of Generative AI:

[0712] The OpenAI API is used as the generative AI model. The server uses the generative AI to generate personalized product suggestions based on user behavior data. This process includes prompt messages that contain information tailored to the user's interests and current situation.

[0713] Specific example:

[0714] For example, when a user is in a shopping mall, the server suggests stores and products that are likely to interest the user based on their location and past purchase history. These suggestions are delivered to the user via push notifications on their smartphone.

[0715] Example of a prompt:

[0716] "This user has been identified as a fan of mystery novels in the past. Please provide information on mystery-related events and merchandise currently available in bookstores."

[0717] This system allows users to automatically find products that match their interests, providing a more efficient and satisfying shopping experience.

[0718] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0719] Step 1:

[0720] The device obtains location information with the user's permission. This location information is collected using GPS functionality and becomes data to determine the user's current location in real time. This data is sent to a server and linked to a specific location within the commercial facility.

[0721] Step 2:

[0722] The device collects the user's purchase history and posts obtained through social networking service APIs. This data, which reflects the user's past behavior and preferences, is sent to the server. This information is sent in text data format and used to generate preference models.

[0723] Step 3:

[0724] The server receives collected location data, purchase history, and data from social media, and stores it in a database. The stored data is then analyzed using a Python machine learning library (e.g., scikit-learn) to generate behavioral patterns and preference models.

[0725] Step 4:

[0726] The server generates the most suitable options for the user from the analyzed data. This process uses a generative AI model (e.g., OpenAI's API) to create prompts for products and events that match the user's preferences. These generated prompts serve as a guide for extracting the most relevant commercial information.

[0727] Step 5:

[0728] The server compiles information from commercial facilities based on the generated choices and sends it to the terminal. The terminal displays this information to the user as a push notification. This allows the user to receive recommended product and event information in real time.

[0729] 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.

[0730] This invention is a system that provides more personalized choices by collecting and analyzing emotional data in addition to user behavioral data and preference data. The system consists of a server, a terminal, and a user, and is equipped with a function to recognize the user's emotional state using an emotion engine.

[0731] The user's device uses an emotion engine to analyze voice and text data and determine the user's emotions in real time. This emotion data is sent to the server along with location information, purchase history, and social networking service data. The collection of emotion data is non-invasive and done with the user's permission.

[0732] The server stores various data sent from the terminal in a database and uses this data to analyze the user's behavior patterns, preference models, and emotional state. The data generated by the emotion engine is a crucial source of information, particularly in generating choices, enabling suggestions tailored to the user's current emotions. For example, when a user is stressed, the server might suggest options that are beneficial for relaxation.

[0733] Using a generative AI model, the server generates optimal choices adapted to the user's current state based on insights gained from analysis. These choices reflect the user's emotional needs at that moment by taking into account emotional state data.

[0734] For example, if the emotion engine detects "fatigue" while a user is browsing social media on their device during a break at work, the server will suggest nearby cafes where they can relax or stretching videos to help them change their mood. In this way, users can make appropriate choices based on their emotional state, leading to a more satisfying daily life.

[0735] This system aims to improve users' quality of life by providing a more personalized experience through an emotion engine that considers the user's emotions when making choices.

[0736] The following describes the processing flow.

[0737] Step 1:

[0738] Device: Obtain user consent and enable voice input and text analysis tools. This prepares the device for real-time collection of sentiment data from user speech and entered text.

[0739] Step 2:

[0740] Device: In addition to the user's daily behavioral data (location information, purchase history, social media posts), it collects acquired emotional data. This emotional data is analyzed by an emotion engine designed to identify a variety of emotions such as joy, sadness, and stress.

[0741] Step 3:

[0742] Terminal: Collects behavioral and emotional data and sends it to the server within the user's permission. Transmission occurs periodically, according to the frequency specified by the user.

[0743] Step 4:

[0744] Server: Integrates received data into the database and organizes information for each user. During this process, filtering and cleaning processes are performed to maintain data consistency.

[0745] Step 5:

[0746] Server: Analyzes integrated data and updates user behavior patterns and preference models. Emotional data is particularly important and influences the generation of situation-appropriate choices.

[0747] Step 6:

[0748] Server: Using a generative AI model, it generates the most suitable options for the user based on all the collected data. This process incorporates the user's current emotional state; for example, if the user is feeling stressed, it will create suggestions that promote relaxation.

[0749] Step 7:

[0750] Server: Sorts the generated options according to priority and sends them to the user's terminal.

[0751] Step 8:

[0752] Terminal: Receives selections from the server and notifies the user. Notifications are delivered using push notifications, in-app messages, and widgets, and are designed for easy user access.

[0753] Step 9:

[0754] User: Check notifications from their device, select options of interest, and decide on their next action. Based on their selection, they begin a new experience or action.

[0755] This series of steps allows users to make choices that align with their emotional state at any given time, resulting in a more personalized experience.

[0756] (Example 2)

[0757] 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".

[0758] In today's information society, it is difficult for users to choose the best option from a vast array of choices. In particular, there is a lack of systems that provide appropriate choices based on the user's emotional state. Choices that ignore emotional information cannot adequately increase user satisfaction and may even negatively impact their quality of life.

[0759] 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.

[0760] In this invention, the server includes means for collecting user behavior information, preference information, and emotional information; means for analyzing the information and generating behavior patterns, preference models, and emotional states; and means for generating choices suitable for the user based on the patterns, models, and states. This makes it possible to provide personalized choices that correspond to the user's emotional state.

[0761] "User behavior information" refers to data about the actions and tendencies that users perform on a daily basis.

[0762] "Preference information" refers to data about a user's preferences and interests.

[0763] "Emotional information" refers to data that indicates a user's emotional state or psychological condition.

[0764] "Options" refer to multiple possible actions or decisions presented to the user.

[0765] A "generative model" is an algorithm or computational method used to analyze data and generate new information or options.

[0766] A "behavioral pattern" is a model that shows the regularity or common tendencies in user behavior.

[0767] A "preference model" is a data model built to represent and utilize user preferences.

[0768] "Emotional state" refers to the user's emotions and psychological condition at a specific moment in time.

[0769] "Communication network service information" refers to data about a user's online activities, and is information provided via a communication network.

[0770] In an embodiment for carrying out this invention, the system consists of three elements: a server, a terminal, and a user.

[0771] Users first generate behavioral, preference, and emotional information through their daily use of their devices. These devices are equipped with voice and text input capabilities, and analysis software called an emotion engine analyzes this data in real time to determine the user's emotional state. This emotion engine identifies voice tone and keywords within the text to classify the user's emotions.

[0772] The device transmits location information, transaction history, and communication network service information, along with analyzed emotional information, to the server. The server stores this information in a database and generates user behavior patterns and preference models. It also records the emotional state based on the generated data and uses this information to provide the user with the most suitable options.

[0773] As a concrete example, if the emotion engine detects "fatigue" while a user is browsing entertainment information on their device during their lunch break, the server will use a generative AI model to suggest a nearby quiet cafe or a short relaxation video to the user. This suggestion is instructed to the generative AI model as a prompt: "Please provide options to alleviate the fatigue the user is currently feeling."

[0774] As described above, the system aims to improve user satisfaction and quality of life by utilizing real-time user sentiment data and providing personalized options tailored to individual needs.

[0775] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0776] Step 1:

[0777] The user inputs voice and text data through the device. The device collects this data and inputs it into the emotion engine. Specifically, it uses speech recognition technology to convert the voice data into text and prepares it for emotion analysis by combining it with the text data.

[0778] Step 2:

[0779] The device's emotion engine analyzes voice and text data to determine the user's emotional state. In this process, the emotion engine extracts features from the input data and compares them with an existing emotion database to output an emotion category (e.g., "joy," "sadness," "fatigue," etc.). Specifically, it performs matching based on voice tone and keywords in the text.

[0780] Step 3:

[0781] The device acquires emotional data, location information, purchase history, and communication network service information, and sends this data to the server. Specifically, it obtains the current location from location services and purchase history from past transaction logs, and prepares to send all the information as packets to the server.

[0782] Step 4:

[0783] The server stores the received data in a database and analyzes the user's behavior patterns, preference models, and emotional states. The input consists of multiple user data points stored in the database, and new patterns and models are generated based on this data. This process utilizes data mining techniques to extract useful patterns and generates behavioral pattern models and preference models as output.

[0784] Step 5:

[0785] The server uses a generative AI model to generate suitable options for the user based on the analysis results. Here, the generative AI model receives instructions using prompts and outputs appropriate options (e.g., relaxation locations, stretching videos, etc.) based on the input data. Specifically, the generative AI model searches the cloud or database for resources that match the analyzed emotional state and generates suggestions that meet the user's needs.

[0786] Step 6:

[0787] The server sends the generated options to the user's device and presents them. The device receives this and notifies the user visually or audibly. Specific actions include displaying information in the notification bar or prompting suggestions with voice guidance.

[0788] (Application Example 2)

[0789] 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".

[0790] When users engage with digital content, there is a challenge in providing them with appropriate choices that align with their emotional state at any given moment. Furthermore, traditional methods struggle to achieve deep personalization that considers not only user preferences and behavioral data but also their real-time emotional state.

[0791] 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.

[0792] In this invention, the server includes means for collecting user behavior data, preference data, and emotional data; means for analyzing the data and generating behavior patterns, preference models, and emotional states; and means for generating optimal choices for the user based on the patterns, models, and emotional states. This makes it possible to provide personalized content based on the user's emotional state.

[0793] "Behavioral data" refers to information that records a user's activities and usage patterns.

[0794] "Preference data" refers to information about the content and services that users prefer.

[0795] "Emotional data" refers to information about a user's emotional state, analyzed from sources such as voice and text.

[0796] "Behavioral patterns" refer to typical behavioral tendencies and habits analyzed from user behavior data.

[0797] A "preference model" is a model that shows individualized preference trends derived from user preference data.

[0798] "Emotional state" represents the user's current emotional condition and is a real-time analysis result.

[0799] "Options" refer to the suggested actions or content presented to the user.

[0800] "Content" refers to information resources such as movies, music, and videos that are provided to users.

[0801] A "generative artificial intelligence model" is an artificial intelligence model used to generate appropriate choices using data analysis.

[0802] The system implementing this invention mainly consists of a server, a terminal, and a user. The terminal is a device that provides a user interface, such as a smartphone or smart glasses. The terminal is equipped with an emotion recognition engine that analyzes the user's voice and text data in real time. The analyzed emotion data is sent to the server along with the user's geographical location data, purchase history data, and social networking service data.

[0803] Based on this data, the server generates customized behavioral patterns, preference models, and emotional states for each user. A generative artificial intelligence model is used for data analysis and choice generation. This model considers the generated behavioral patterns, preference models, and emotional states to propose a list of content optimized for the user.

[0804] For example, when a user is using a streaming service, if the emotion engine detects fatigue or stress, it will recommend uplifting comedy movies or relaxing music. This suggestion will be notified to the user and displayed on their device as available content.

[0805] As an example of a prompt message that a generative AI model might use to generate choices, we can use a sentence like, "Your current emotional state has been detected as 'fatigue.' Please recommend a relaxing movie." This allows users to smoothly select content that matches their emotional state, providing a highly satisfying experience.

[0806] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0807] Step 1:

[0808] The device sends the user's voice and text data as input to an emotion recognition engine, which analyzes the emotional state in real time. As a result of the analysis, it outputs the user's current emotional state.

[0809] Step 2:

[0810] The device transmits user emotional state data, geographical location data, purchase history data, and social networking service data to the server. This data serves as input necessary for generating user behavior patterns and preference models.

[0811] Step 3:

[0812] The server uses data analysis software to generate user behavior patterns and preference models based on the received data. As a result of the analysis, it outputs customized behavior patterns, preference models, and emotional states for each user.

[0813] Step 4:

[0814] The server uses the behavioral patterns, preference models, and emotional states generated by the artificial intelligence model as input to generate a list of user-optimized content. This process utilizes prompt statements to generate choices. The generated results are output as choices suggested to the user.

[0815] Step 5:

[0816] The server sends the generated content list to the device. Based on the received list, the device notifies the user and displays content on the screen that matches their emotional state. By using the suggested content, the user can have a more satisfying experience.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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."

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] The following is further disclosed regarding the embodiments described above.

[0839] (Claim 1)

[0840] Means for collecting user behavior data and preference data,

[0841] A means for analyzing the aforementioned data and generating behavioral patterns and preference models,

[0842] Means for generating the optimal choice for the user based on the aforementioned patterns and models,

[0843] A means for notifying the user of the aforementioned options,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, wherein the data collection means includes location information data, purchase history data, and social network service data.

[0847] (Claim 3)

[0848] The system according to claim 1, wherein the option generation means uses a generation AI model.

[0849] "Example 1"

[0850] (Claim 1)

[0851] Means for collecting user characteristic data,

[0852] A means for analyzing the aforementioned data and generating a user behavior pattern and preference model,

[0853] A means for creating the optimal choice for the user based on the aforementioned behavioral patterns and preference models,

[0854] A means for immediately transmitting the aforementioned optimal selection to the user terminal,

[0855] The user terminal includes means for displaying suggestions to the user,

[0856] A system that includes this.

[0857] (Claim 2)

[0858] The system according to claim 1, wherein the characteristic data collection means includes location information, purchase history, and information sharing service data.

[0859] (Claim 3)

[0860] The system according to claim 1, wherein the means for generating the optimal choice is to use a generative AI model.

[0861] "Application Example 1"

[0862] (Claim 1)

[0863] Means for collecting user behavior data and preference data,

[0864] A means for analyzing the aforementioned data and generating behavioral patterns and preference models,

[0865] Means for generating the optimal choice for the user based on the aforementioned patterns and models,

[0866] A means for notifying the user of the aforementioned options,

[0867] In order to provide the aforementioned options in relation to commercial activities, means for identifying the user's location in a real-world place and providing information from a commercial facility,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, wherein the data collection means includes location information data, purchase history data, and social network service data.

[0871] (Claim 3)

[0872] The system according to claim 1, wherein the option generation means uses a generation AI model.

[0873] "Example 2 of combining an emotion engine"

[0874] (Claim 1)

[0875] Means for collecting user behavior information, preference information, and emotional information,

[0876] A means for analyzing the aforementioned information and generating behavioral patterns, preference models, and emotional states,

[0877] Means for generating suitable options for the user based on the aforementioned patterns, models, and states,

[0878] A means of presenting the aforementioned options to the user,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, wherein the information gathering means includes location information, transaction history, and communication network service information.

[0882] (Claim 3)

[0883] The system according to claim 1, wherein the aforementioned option generation means uses a generation model.

[0884] "Application example 2 when combining with an emotional engine"

[0885] (Claim 1)

[0886] Means for collecting user behavior data, preference data, and emotional data,

[0887] A means for analyzing the aforementioned data and generating behavioral patterns, preference models, and emotional states,

[0888] Means for generating the optimal choice for the user based on the aforementioned patterns, models, and emotional states,

[0889] A means of notifying the user of the aforementioned options and suggesting content that matches the user's emotional state,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, wherein the data collection means includes geographic location data, purchase history data, and social networking service data.

[0893] (Claim 3)

[0894] The system according to claim 1, wherein the option generation means uses a generative artificial intelligence model. [Explanation of Symbols]

[0895] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting user behavior data and preference data, A means for analyzing the aforementioned data and generating behavioral patterns and preference models, Means for generating the optimal choice for the user based on the aforementioned patterns and models, A means for notifying the user of the aforementioned options, A system that includes this.

2. The system according to claim 1, wherein the data collection means includes location information data, purchase history data, and social network service data.

3. The system according to claim 1, wherein the aforementioned option generation means uses a generation AI model.

Images