system

Abstract

Provide a system. [Solution] a means for obtaining data from a user data source; a means for cleansing the acquired data; means for generating a profile of the user based on the cleansed data; means for generating a digital twin based on the generated profile; A means for performing a simulation using the generated digital twin; A means of analyzing the simulation results and providing users with the best options; A system including:

Description

[Technical Field]

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

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

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

[0004] In recent years, advances in digitalization have led to the collection of large amounts of data. This has created a need to understand the characteristics and behavioral patterns of individual users and provide optimal personalized recommendations. However, current systems have difficulty effectively analyzing the collected data and creating highly accurate profiles that include the user's inner characteristics. Furthermore, they are unable to accurately perform simulations based on these profiles or provide optimal options. This presents a problem in that the information provided often does not match the user's wishes or preferences. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a means for acquiring data from a user's data source, a means for cleansing the acquired data, a means for generating a user profile based on the cleansed data, a means for generating a digital twin based on the generated profile, a means for performing a simulation using the generated digital twin, and a means for analyzing the simulation results and providing the user with optimal options. This allows a highly accurate user profile to be created, and optimal options to be provided to the user through a simulation based on the profile. This makes it possible to provide information that matches the user's wishes and preferences.

[0006] A "data source" is a source of information for collecting user-related data, such as a purchase history database, a social media platform, or a survey system.

[0007] "Means of obtaining data" refers to the process or mechanism for extracting the necessary information from the data source and incorporating it into the program.

[0008] "Data cleansing" refers to the process of preparing collected raw data in a format suitable for analysis by filling in missing values, correcting outliers, and removing duplicates.

[0009] "Means for generating a profile" refers to the process or mechanism that analyzes user characteristics, preferences, behavioral patterns, etc. based on cleansed data, and organizes and builds detailed information about each individual user.

[0010] "Digital twin" refers to a digital model that has duality with a physical user and reproduces the user's inner thoughts and behavioral characteristics in a virtual space.

[0011] "Means for generating a digital twin" refers to the programs and processes for constructing a digital twin based on the generated user profile and placing it in a virtual space.

[0012] "Means for performing simulation" refers to the process or mechanism for virtually experimenting with specific scenarios using the generated digital twin, and observing and analyzing the reactions and results.

[0013] "Means for analyzing the simulation results" refers to the process or mechanism for evaluating the data obtained through the simulation and analyzing the user's behavioral tendencies and reaction patterns.

[0014] "Means for providing optimal options" refers to the process or mechanism for presenting optimal proposals and information to individual users based on the analysis of simulation results. [Brief explanation of the drawings]

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

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

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

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

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

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention details a system that collects and analyzes user-related data and generates a digital twin of the user. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is explained below.

[0037] Data collection

[0038] The server first obtains the necessary data from the user's data source. Data sources include the user's purchase history, social media activity history, survey responses, etc. For example, the server accesses a purchase history database via an API and obtains a list of products that User A has purchased in the past.

[0039] Data Preprocessing

[0040] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in missing values, and standardizing the format. This ensures the quality of the data.

[0041] Data profiling

[0042] Based on the cleansed data, the server generates a user profile, which includes the user's characteristics, preferences, behavioral patterns, etc. For example, if user A frequently purchases high-quality handbags, the characteristic "luxury-oriented" is extracted.

[0043] Digital Twin Generation

[0044] Based on the generated profile, the server creates a digital twin of the user. The digital twin is placed in a virtual space and also reflects the user's internal characteristics. For example, User A's digital twin has the characteristics of being "luxury-oriented" and "fashion-conscious."

[0045] Building a simulation environment

[0046] The server uses the digital twins to run specific simulation scenarios, such as a new product market launch scenario, and observes how the digital twins react. Through this simulation, the server determines whether many digital twins are interested in the new product.

[0047] Simulation result analysis and feedback

[0048] The server analyzes the data obtained from the simulation and calculates the optimal option for each user. For example, if User A's digital twin shows interest in a new product, the server will recommend, "An eco-friendly handbag would be perfect for you."

[0049] User notification and action support

[0050] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[0051] Through the above process, this system can provide optimal suggestions that match the user's characteristics and increase satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each user, and providing the user with the optimal options.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user, and temporarily stores the data returned by the API in data storage.

[0055] Step 2:

[0056] The server cleanses the collected data, specifically removing duplicates, filling in incomplete data, correcting outliers, and standardizing the data format to make it easier to analyze.

[0057] Step 3:

[0058] The server then uses the cleansed data to profile the user. This process involves using machine learning algorithms (such as clustering and decision trees) to analyze the user's behavioral patterns and preferences and extract detailed characteristics, which then create a user profile.

[0059] Step 4:

[0060] The server then creates a digital twin based on the generated profile, which reflects the user's personality and behavioral characteristics and is placed in a virtual space.

[0061] Step 5:

[0062] The server sets up a simulation scenario and places the digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The simulation is run multiple times and the reaction patterns are recorded.

[0063] Step 6:

[0064] The server analyzes the results of the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server clarifies the user's preferences and behavioral trends and makes specific suggestions.

[0065] Step 7:

[0066] The server then sends notifications to each user based on the analysis results, for example, recommending a new eco-friendly handbag to the user.

[0067] Step 8:

[0068] The device receives notifications from the server and displays them to the user. Notifications are delivered to the user as push notifications or in-app messages, providing information in a visually easy-to-understand format.

[0069] Step 9:

[0070] The user checks the notification from the device and takes action based on the suggested option, for example, clicking on a purchase link for the suggested product and actually purchasing the product.

[0071] By going through these steps, the system can provide the user with the best options and increase user satisfaction.

[0072] Example 1

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

[0074] In today's digital society, there is a demand for personalized services based on individual user preferences and behavioral patterns. However, despite the vast amount of user data available, systems that can efficiently collect and analyze this data and provide optimal suggestions to users have not yet been fully established. Furthermore, further improvements are needed in methods that use digital twins to reproduce user characteristics in virtual space and provide real-time feedback based on the simulation results. Therefore, there is a need for new systems that can solve these issues and improve user satisfaction.

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

[0076] In this invention, the server includes means for acquiring data from a user information source, means for cleaning the acquired data, means for generating user characteristic information based on the cleaned data, means for generating a virtual user model based on the generated characteristic information, means for performing a simulation using the generated virtual user model, means for analyzing the simulation results and providing the user with an optimal selection, and means for notifying the user, thereby making it possible to provide personalized suggestions based on the user's characteristics in real time.

[0077] "User information sources" refers to multiple databases and information systems that store data related to the user.

[0078] "Data cleaning" is the process of correcting and removing duplicates, missing data, improper formats, etc. from acquired data, and preparing it in a form suitable for analysis.

[0079] "User characteristic information" is data that indicates characteristics such as user preferences and behavioral patterns, extracted from the cleaned data.

[0080] A "virtual user model" is a digital twin that is generated based on the user's characteristic information and reproduces the user's behavior and reactions in a virtual space.

[0081] "Simulation" is the process of using virtual user models to virtually perform and observe reactions to specific scenarios.

[0082] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and deriving the optimal choices and actions for the user.

[0083] "Notification" refers to the act of sending information to users via means such as push notifications or in-app messages to inform them of the analysis results.

[0084] This invention is a system that collects user data, generates a digital twin, performs simulations, and presents optimal options to the user based on the results. The program processing of this system will be described in detail below.

[0085] First, the server obtains data from the user's information sources. These information sources include a purchase history database, social media activity history, and survey results. The server accesses these data sources through APIs to obtain the necessary data. For example, the server can obtain "User A's purchase history for the past 12 months."

[0086] Next, the server cleans the acquired data. Because the data often contains duplicates and missing data, these are deleted and supplemented, and the data format is standardized. Specific actions at this stage include deleting duplicate data, supplementing missing values ​​with appropriate values, and standardizing the date format to "YYYY-MM-DD."

[0087] The server then generates user characteristic information based on the cleaned data. This characteristic information includes the user's preferences and behavioral patterns. For example, the characteristic "luxury-oriented" can be identified from the information that "User A has purchased high-quality handbags five times in the past six months."

[0088] Next, the server generates a virtual user model (digital twin) based on the generated characteristic information. To do this, a machine learning model is used to construct a user model that is reproduced in a virtual space using the characteristic information as input data. Specifically, a neural network is constructed using a machine learning framework such as TENSORFLOW (registered trademark), and a digital twin that reflects the user's characteristic information is generated.

[0089] The server then runs a simulation using the generated digital twin. For example, it sets up a market introduction scenario for a new product and observes how the digital twin responds to that scenario. This simulation allows the server to collect data such as how much interest the digital twin shows in the new product.

[0090] After obtaining the simulation results, the server analyzes them and implements measures to provide the user with the optimal choice. For example, if the digital twin shows high interest in a new product, the server will recommend to the user, "An eco-friendly handbag would be perfect for you."

[0091] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, and provides a product link or purchase button so that the user can take immediate action based on the recommendation. For example, it can say, "Show a purchase link for an eco-friendly handbag."

[0092] This system performs detailed profiling and simulations based on user data, and makes personalized suggestions in real time, thereby increasing user satisfaction.

[0093] Example prompt sentence:

[0094] Create a fashion-oriented digital twin based on purchase history, social media data, and survey results. Then, simulate a market introduction scenario for a new product, "Eco-Friendly Handbags," and recommend the product to User A based on the reaction shown by the digital twin.

[0095] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0096] Step 1: Data collection

[0097] The server obtains data from user information sources, including purchase history databases, social media activity history, survey results, and other data sources.

[0098] Input: API request to data source

[0099] Specific behavior:

[0100] The server sends a request to an API endpoint.

[0101] For example, obtain JSON data containing "User A's purchase history for the past 12 months."

[0102] Output: Raw data obtained (e.g., purchase history in JSON format)

[0103] Step 2: Data Preprocessing

[0104] The server then cleans the data it receives, which is the process of correcting and removing duplicates, missing data, improper formats, etc.

[0105] Input: Raw data (e.g., purchase history in JSON format)

[0106] Specific behavior:

[0107] The server detects and removes duplicate data.

[0108] To impute missing values, fill in the missing parts with the appropriate values.

[0109] Standardize date formats, currency units, etc. Example: Convert to "YYYY-MM-DD" format.

[0110] Output: Cleaned data

[0111] Step 3: Data profiling

[0112] The server generates user characteristic information based on the cleaned data, which includes the user's preferences and behavioral patterns.

[0113] Input: Cleaned data

[0114] Specific behavior:

[0115] The server analyzes the purchase history data and extracts the user's preferences.

[0116] For example, the characteristic "luxury-oriented" can be extracted from the information that "User A has purchased high-quality handbags five times in the past six months."

[0117] Output: User characteristics information

[0118] Step 4: Generate the digital twin

[0119] The server generates a virtual user model based on the generated characteristic information, which is called a digital twin.

[0120] Input: User characteristics information

[0121] Specific behavior:

[0122] The server inputs the characteristic information into the machine learning model.

[0123] For example, TensorFlow is used to build a neural network and generate a virtual user model.

[0124] Output: The generated digital twin

[0125] Step 5: Building the simulation environment

[0126] The server uses the digital twin to set up and run specific simulation scenarios.

[0127] Input: Digital twin, simulation scenario

[0128] Specific behavior:

[0129] The server sets up a market introduction scenario for a new product.

[0130] Simulate how your digital twin will react based on scenarios.

[0131] Output: Simulation results

[0132] Step 6: Analysis and feedback of simulation results

[0133] The server analyzes the simulation results and provides the user with the optimal options.

[0134] Input: Simulation results

[0135] Specific behavior:

[0136] The server analyzes the simulation data and derives optimal suggestions for the user.

[0137] For example, if the digital twin shows high interest in a new product, it will recommend, "This eco-friendly handbag is perfect for you."

[0138] Output: Optimal recommendations for the user

[0139] Step 7: Notify users and support their actions

[0140] The device receives notifications from the server and displays them to the user, either through push notifications or in-app messages.

[0141] Input: Notification from the server

[0142] Specific behavior:

[0143] The device displays a push notification.

[0144] For example, "Show links to buy eco-friendly handbags."

[0145] Output: Notify user and display purchase link

[0146] (Application example 1)

[0147] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0148] In modern online shopping, inappropriate product recommendations to users can lead to a decline in user satisfaction. To make appropriate product recommendations, it is necessary to fully understand the user's purchasing history and interests and make personalized recommendations based on that. However, current systems often lack the accuracy of recommendations due to insufficient user profiling and digital twin generation.

[0149] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0150] In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the simulation results, thereby enabling highly accurate product recommendations based on the user's interests.

[0151] "User data sources" refers to information sources such as a user's purchasing history, social media activity history, and survey responses.

[0152] "Means for obtaining data" refers to the method by which the server gathers the required data from the user's data source.

[0153] "Data cleansing" refers to the process of removing duplicates from acquired data, filling in missing values, and standardizing the format.

[0154] "Means for generating a user profile" refers to technology that identifies and organizes a user's characteristics, preferences, and behavioral patterns based on cleansed data.

[0155] A "digital twin" refers to a digital model that is generated in a virtual space based on a user's profile and reflects the user's internal characteristics.

[0156] "Means for performing simulation" refers to a method of using the generated digital twin to execute specific scenarios in a virtual space and observe the reactions.

[0157] "Means for analyzing the simulation results and providing the user with the optimal option" refers to a method for analyzing the data obtained from the simulation and calculating the optimal option for the user.

[0158] "Means for recommending products" refers to a mechanism that presents the most suitable products to users based on the results of the simulation.

[0159] This invention is a system that collects and analyzes data related to a user, generates a digital twin, and recommends optimal products to the user. Here, as a specific embodiment, the configuration and operation of this system will be described.

[0160] System configuration

[0161] This system consists of the following main components:

[0162] Server: Collects data, cleanses it, creates profiles, generates digital twins, performs simulations, and performs analysis.

[0163] Device: Provides notifications and action support to users. Devices include smartphones, PCs, etc.

[0164] Hardware

[0165] The main hardware required to realize the system includes:

[0166] Cloud server: Data storage and processing on the cloud

[0167] User device: smartphone or PC

[0168] software

[0169] The software includes the following:

[0170] Data collection module: Acquires purchase history, social media activity history, and survey responses via API

[0171] Data cleansing module: remove duplicates, impute missing values, and unify formats

[0172] Profile generation module: Analyzes user characteristics, preferences, and behavioral patterns

[0173] Digital twin generation module: Generates a digital model in a virtual space based on the user's characteristics

[0174] Simulation module: Run specific scenarios and observe the reactions

[0175] Analysis module: Analyzes the simulation results and calculates the best options for the user

[0176] Notification and support module: Notify users of recommended products and support their purchasing actions

[0177] Operation flow

[0178] 1. Data collection: The server obtains users' purchase history, social media activity history, survey responses, etc. through the API.

[0179] 2. Data cleansing: The server removes duplicates from the retrieved data, fills in missing values, and standardizes the format.

[0180] 3. Profile generation: The server analyzes the user's characteristics and preferences based on the cleansed data and generates a profile.

[0181] 4. Digital twin generation: The server generates a digital twin in the virtual space based on the generated profile, creating a digital model that reflects the user's characteristics.

[0182] 5. Simulation: The server uses the digital twin to run a specific scenario (e.g., introducing a new product to the market) and observe the reaction.

[0183] 6. Analysis and feedback: The server analyzes the simulation results and calculates the best product and service options for the user.

[0184] 7. Notification and action support: The device notifies the user of the recommendation results from the server and displays links and buttons so that the user can take immediate action.

[0185] Specific examples

[0186] For example, for a user with user ID 1, the system operates as follows: The server collects the user's purchase history, social media activity history, and survey responses via API and cleanses them. The server then creates a profile of the user's characteristics and preferences, and generates a digital twin in a virtual space based on that profile. Next, it runs a specific simulation scenario and observes the digital twin's reaction. Based on the results, it recommends products such as "Luxury handbags" and "Designer shoes" to the user, and notifies the user's device, allowing the user to immediately purchase these products.

[0187] Prompt Sentence Examples

[0188] "For user ID 1, please collect data on his / her purchasing history and social media activity, and generate a digital twin. Then, please run a simulation to recommend new fashion items, and notify the user of the recommendation results."

[0189] This invention makes it possible to recommend products with high accuracy based on the user's interests, and is expected to improve user satisfaction.

[0190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0191] Step 1:

[0192] The server retrieves data from the user's data source. The input in this step is the user ID, and the output is a set of data such as purchase history, social media activity history, and survey responses. Specifically, these data sources are accessed through APIs to collect user-specific data.

[0193] Step 2:

[0194] The server cleanses the acquired data. The input in this step is the data acquired in the previous step, and the output is cleansed, high-quality data. Specifically, it removes duplicate data, fills in missing values, and standardizes the data format. This results in data suitable for analysis.

[0195] Step 3:

[0196] The server generates a user profile based on the cleansed data. The input in this step is the cleansed data, and the output is profile data that shows the user's characteristics, preferences, and behavioral patterns. Specifically, characteristics such as whether the user prefers high-priced items are extracted from purchase history and social media activity.

[0197] Step 4:

[0198] The server generates a digital twin based on the generated profile. The input in this step is the user profile, and the output is a digital twin placed in a virtual space. Specifically, a virtual model reflecting the user's interests and behavioral patterns is generated and placed in the virtual space.

[0199] Step 5:

[0200] The server runs a simulation using the generated digital twin. The inputs in this step are the digital twin and the simulation scenario, and the output is the simulation results. Specifically, for example, a scenario for introducing a new product to the market is set up, and how the digital twin reacts to that product is observed.

[0201] Step 6:

[0202] The server analyzes the simulation results and provides the user with the optimal options. The input in this step is the simulation results, and the output is recommendation data for the user. Specifically, if the digital twin shows interest in a new product, that product is presented to the user as a recommendation.

[0203] Step 7:

[0204] The device provides the notification from the server to the user. The input in this step is the recommendation data, and the output is a notification and action link for the user. Specifically, a product link and purchase button are displayed via push notification or in-app message, allowing the user to easily check the information and take action.

[0205] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0206] This invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is described below.

[0207] Data collection

[0208] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. In addition, an emotion engine is used to collect emotion data from user posts on social media and in surveys.

[0209] Data Preprocessing

[0210] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds their emotional state to the library.

[0211] Data profiling

[0212] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the characteristics of "luxury-oriented" and "positive thinking" are extracted.

[0213] Digital Twin Generation

[0214] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. For example, User A's digital twin has the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[0215] Building a simulation environment

[0216] The server uses the digital twin to run specific simulation scenarios, such as setting up a market launch scenario for a new product, and observing how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations.

[0217] Simulation result analysis and feedback

[0218] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend, "An eco-friendly handbag is perfect for you."

[0219] User notification and action support

[0220] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[0221] Through the above process, this system can provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each individual user, and providing the user with the optimal options.

[0222] The processing flow will be explained below.

[0223] Step 1:

[0224] The server sends API requests to user data sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. At the same time, an emotion engine is used to collect emotion data from social media and survey text.

[0225] Step 2:

[0226] The server cleanses the collected data, eliminating duplicates, filling in incomplete data, and standardizing formats. An emotion engine also extracts the user's emotional state through text analysis and adds it to the cleansed data.

[0227] Step 3:

[0228] The server uses machine learning algorithms (such as clustering and decision trees) to generate a user profile based on the cleansed data. The profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and displays many positive emotions, the characteristics "luxury-oriented" and "positive thinking" can be derived.

[0229] Step 4:

[0230] The server generates a digital twin of the user based on the generated profile. The digital twin simulates the user's personality, behavioral characteristics, and emotional state and is placed in a virtual space. User A's digital twin has characteristics such as "luxury-oriented," "fashion-conscious," and "positive thinking."

[0231] Step 5:

[0232] The server sets up a simulation scenario and places the generated digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The emotion engine monitors the digital twin's emotional state in real time and records in detail how the user feels within the scenario.

[0233] Step 6:

[0234] The server analyzes the results of the simulation and calculates the optimal option for the user. The analysis makes specific suggestions based on the digital twin's behavioral patterns and emotional transitions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend something like, "This eco-friendly handbag is perfect for you."

[0235] Step 7:

[0236] The server then sends notifications to each user based on the analysis results. Notifications can be sent via push notifications or in-app messages, and include detailed information and links about the recommended products.

[0237] Step 8:

[0238] The device receives notifications from the server and displays them to the user. An intuitive interface is provided so that users can easily check the notifications. For example, purchase links and detailed information are displayed in the form of easy-to-click buttons.

[0239] Step 9:

[0240] The user checks the notification from the device and takes action based on the options presented, for example, clicking on a link in the notification and purchasing the recommended product.

[0241] Through these steps, the system can provide users with optimal suggestions that match their characteristics and emotions, improving satisfaction.

[0242] Example 2

[0243] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0244] In recent years, there has been a demand for personalized services based on users' preferences, personalities, and emotions, but the challenge is that it is difficult to integrate diverse user data and provide effective information. In particular, conventional systems are unable to adequately analyze emotional data, generate digital twins, or analyze simulation results, making it difficult to provide users with optimal options.

[0245] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0246] In this invention, the server includes means for acquiring data from a user's information source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, means for collecting and preprocessing data, means for collecting and analyzing emotional data using an emotion analysis engine, means for setting and executing a specific simulation scenario, and means for analyzing the simulation data and calculating optimal options. This makes it possible to integrate a variety of user data, achieve highly accurate profiling and simulation including emotional data, and provide the user with optimal options.

[0247] A "user" is an individual or organization that uses the system to receive services or information.

[0248] A "source" is an external database or platform that provides data relevant to a user.

[0249] "Data cleansing" is the process of removing duplicate and incomplete data from acquired data and standardizing the data format.

[0250] A "user profile" is information that represents a user's characteristics, preferences, behavioral patterns, and emotional state, generated based on cleansed data.

[0251] A "digital twin" is a digital representation of a user that is generated in a virtual space based on the user's real-world profile.

[0252] "Simulation" is the process of using a digital twin to recreate a specific scenario in a virtual environment and observe the results.

[0253] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and calculating the optimal options for the user.

[0254] An "emotion analysis engine" is software or an algorithm for analyzing a user's emotions from text or statements.

[0255] A "simulation scenario" is an item that refers to a specific situation or condition that is set when a simulation is performed.

[0256] The present invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides optimal options to the user based on the results.

[0257] Data collection

[0258] The server sends API requests to user information sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The collected data is temporarily stored in data storage. A sentiment analysis engine is also used to collect emotional data from user posts on social media and in surveys. The hardware used for this is a high-performance server, and software such as OpenAI (registered trademark) and IBM Watson (registered trademark) is used for sentiment analysis.

[0259] Data Preprocessing

[0260] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. This process uses the Python Pandas library. A sentiment analysis engine analyzes text from social media and surveys and adds the user's emotional state to the library.

[0261] Data profiling

[0262] Based on the cleansed data, the server creates a user profile. This profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the server extracts the characteristics of "luxury-oriented" and "positive thinking." This profiling is performed using a machine learning model (scikit-learn).

[0263] Digital Twin Generation

[0264] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is placed in a virtual space. This process uses virtual reality software such as Unity or Unreal Engine. For example, User A's digital twin would have the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[0265] Building a simulation environment

[0266] The server runs specific simulation scenarios using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. An emotion analysis engine monitors the emotional state of the digital twin in real time during the simulation, enabling more accurate simulations. The simulation is performed using simulation software such as MATLAB® and Simulink.

[0267] Simulation result analysis and feedback

[0268] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the user's preferences, behavioral tendencies, and emotional state can be clarified and specific suggestions can be made. For example, if User A's digital twin has a very positive reaction to a new product, the server will recommend, "An eco-friendly handbag would be perfect for you." This analysis is performed using Python's NumPy and SciPy libraries.

[0269] User notification and action support

[0270] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message. To make it easy for the user to check the information, the device provides a product link or purchase button so that the user can take immediate action based on the suggestion. For example, a purchase link for an eco-friendly handbag is displayed. This notification is sent using a notification service such as Firebase Cloud Messaging (FCM).

[0271] This system can provide optimal suggestions that match the user's characteristics and emotions, increasing satisfaction. A concrete example is the case where User A purchased a new product and his satisfaction increased.

[0272] Examples of prompt statements

[0273] "Please provide a step-by-step guide to create a program that analyzes emotions from users' social media posts and builds a recommendation system based on the results."

[0274] "Please explain in detail the algorithm used to generate a user's digital twin using purchase history data and social media sentiment data."

[0275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0276] Step 1: Data collection

[0277] The server sends API requests to user information sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The input is the user's ID and search query, and the output is raw data in JSON format. Specifically, the server uses the Python requests library to send requests to the API and temporarily saves the retrieved data in data storage. It also calls a sentiment analysis engine to collect emotional data from social media and surveys.

[0278] Step 2: Cleanse the data

[0279] The server cleanses the acquired data. The input is the raw data collected in step 1, and the output is cleansed data with duplicate data removed, incomplete data completed, and a unified format. Specifically, the server uses the Python Pandas library to create a data frame, remove duplicate data, and complete incomplete data. The sentiment analysis engine also analyzes the data and adds the emotional state to the library.

[0280] Step 3: Data profiling

[0281] The server profiles users based on the cleansed data. The input is the cleansed data, and the output is a profile that includes the user's characteristics, preferences, behavioral patterns, and emotional state. Specifically, the server analyzes the data using a machine learning model (scikit-learn) to extract user characteristics. For example, if a particular user frequently purchases high-quality products and expresses a lot of positive emotions, the server can profile the user's characteristics based on that.

[0282] Step 4: Generate the digital twin

[0283] The server generates a digital twin based on the generated profile. The input is the user's profile, and the output is a digital twin placed in a virtual space. Specifically, the server generates the digital twin using virtual reality software such as Unity or Unreal Engine. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is capable of acting in the virtual space.

[0284] Step 5: Building the simulation environment

[0285] The server runs a specific simulation scenario using the digital twin. The input is the settings for the specific simulation scenario, and the output is the simulation data. Specifically, the server uses simulation software such as MATLAB or Simulink to set up and run the simulation scenario. The emotion analysis engine monitors the emotional state of the digital twin in real time, enabling more accurate simulations.

[0286] Step 6: Analysis and feedback of simulation results

[0287] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. The input is the simulation data, and the output is a specific recommendation for the user. Specifically, the server analyzes the simulation data using Python's NumPy and SciPy libraries to clarify the user's preferences, behavioral tendencies, and emotional state. For example, if User A's digital twin reacts positively to a new product, the server will recommend, "This eco-friendly handbag is perfect for you."

[0288] Step 7: Notify users and support their actions

[0289] The device (user's smartphone or PC) receives notifications from the server and displays them to the user. The input is the notification data from the server, and the output is the notification message that is displayed to the user. Specifically, the device receives push notifications using services such as Firebase Cloud Messaging (FCM) and displays them as in-app messages. Actions such as product links and purchase buttons are provided so that users can easily check the information. For example, a purchase link for an eco-friendly handbag may be displayed.

[0290] Through this system, it is possible to provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction.

[0291] (Application example 2)

[0292] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0293] In conventional shopping experiences, it has been difficult to accurately understand a user's purchasing behavior, preferences, and emotional state, and to recommend optimal products based on that. In particular, there is a lack of systems that perform real-time emotion analysis and provide personalized product recommendations, making it difficult to increase user satisfaction.

[0294] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the analysis results. This enables personalized product recommendations in real time that accurately reflect the user's preferences and emotional state.

[0295] "User" refers to an individual consumer or end user of the System.

[0296] "Data source" refers to the original source of information that provides information related to a user, such as a user's purchase history, social media posts, or survey responses.

[0297] "Data cleansing" refers to the process of removing duplicates from collected data, completing incomplete data, and standardizing the format.

[0298] A "profile" refers to a digital data collection that includes a user's characteristics, preferences, and emotional state, generated based on cleansed data.

[0299] "Digital twin" refers to a digital model that is generated based on a user's profile and can simulate the user's behavior and reactions in a virtual space.

[0300] "Simulation" refers to the process of using the generated digital twin to try out reactions and actions in a virtual space in response to a specific scenario.

[0301] "Providing options" refers to the act of analyzing the simulation results and recommending the best proposals and products for the user.

[0302] "Means for recommending products" refers to the system's ability to present products and services suited to the user based on the user's profile and simulation results.

[0303] The present invention relates to a system that analyzes user data and emotions and generates a digital twin. This system provides the user with optimal options based on a simulation in a virtual space. Specific embodiments of the present invention will be described below.

[0304] Data collection

[0305] The server sends API requests to retrieve data from the user's data sources (e.g., purchase history database, social media platform, survey system). The collected data is temporarily stored in data storage. It also uses an emotion engine to collect emotion data from user posts on social media and surveys. The hardware used is a general-purpose server, and the software uses a RESTful API.

[0306] Data Preprocessing

[0307] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds the emotional state to the library. The tool used for data cleansing is the Python pandas library.

[0308] Data profiling

[0309] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if a user frequently purchases luxury handbags and expresses many positive emotions on social media, the characteristics "luxury-oriented" and "positive thinking" can be extracted. Machine learning algorithms (such as the scikit-learn library) are used for profiling.

[0310] Digital Twin Generation

[0311] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. The digital twin is created using Python's object-oriented programming method.

[0312] Building a simulation environment

[0313] The server runs specific simulation scenarios using the digital twin. For example, it sets up a scenario for introducing a new product to the market and observes how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time, enabling more accurate simulations. The simulations are run using Unity and other virtual environment building tools.

[0314] Simulation result analysis and feedback

[0315] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. This analysis is performed using Python's numpy and pandas libraries. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if the user's digital twin responds very positively to a new product, it can recommend an eco-friendly handbag.

[0316] User notification and action support

[0317] The user's device (smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device then provides a product link or purchase button so that the user can take immediate action based on the suggestion, allowing the user to make a quick decision.

[0318] Specific examples and generated AI prompts

[0319] Specific examples

[0320] For example, if a user's purchasing history indicates a preference for luxury goods and they post many positive comments on social media, the system can use this information to create a digital twin. If a new product, an eco-friendly handbag, is introduced and the user's digital twin responds very positively, the system can recommend it directly to the user.

[0321] Example of a generated AI prompt

[0322] "A user posts on social media, 'I love eco-friendly handbags!' Based on this post, please analyze the user's sentiment data and recommend the most suitable products."

[0323] As can be seen, the system of the present invention is able to leverage user data and sentiment data to provide real-time personalized recommendations and enrich the user's shopping experience.

[0324] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0325] Step 1:

[0326] The server retrieves data from the user's data source. Specifically, it sends API requests to a purchase history database, a social media platform, a survey system, etc. The input is the user's identification information, and the output is raw data such as the user's purchase history and social media posts. This data is temporarily stored in data storage.

[0327] Step 2:

[0328] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. The data is organized using the Python pandas library. The input is the raw data acquired in step 1, and the output is the cleansed data.

[0329] Step 3:

[0330] The server generates a user profile based on the cleansed data. Specifically, it compiles preferences and behavioral patterns into a profile based on the user's purchasing history and emotional data. It uses a machine learning algorithm (scikit-learn library). The input is the cleansed data, and the output is a detailed user profile.

[0331] Step 4:

[0332] The server generates a digital twin based on the generated profile. It uses Python object-oriented programming techniques to build a digital twin that reflects the profile. The input is the user profile, and the output is the digital twin.

[0333] Step 5:

[0334] The server runs a specific simulation scenario using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. It uses Unity or other virtual environment building tools. The input is the digital twin, and the output is the simulation result data.

[0335] Step 6:

[0336] The server analyzes the simulation results and calculates the optimal option for the user. It uses Python's numpy and pandas libraries to analyze the simulation results. The input is the simulation result data, and the output is specific recommendations for the user.

[0337] Step 7:

[0338] The device (smartphone or PC) receives notifications from the server and displays them to the user. Notifications are sent via push notifications or in-app messages, allowing users to easily check the information. The input is the recommendation content sent from the server, and the output is the recommended information displayed on the user's screen.

[0339] The above steps enable real-time personalized product recommendations.

[0340] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0341] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0342] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0343] [Second embodiment]

[0344] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0345] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0346] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0347] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0348] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0349] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0350] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0351] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0352] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0353] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0354] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0355] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0356] This invention details a system that collects and analyzes user-related data and generates a digital twin of the user. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is explained below.

[0357] Data collection

[0358] The server first obtains the necessary data from the user's data source. Data sources include the user's purchase history, social media activity history, survey responses, etc. For example, the server accesses a purchase history database via an API and obtains a list of products that User A has purchased in the past.

[0359] Data Preprocessing

[0360] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in missing values, and standardizing the format. This ensures the quality of the data.

[0361] Data profiling

[0362] Based on the cleansed data, the server generates a user profile, which includes the user's characteristics, preferences, behavioral patterns, etc. For example, if user A frequently purchases high-quality handbags, the characteristic "luxury-oriented" is extracted.

[0363] Digital Twin Generation

[0364] Based on the generated profile, the server creates a digital twin of the user. The digital twin is placed in a virtual space and also reflects the user's internal characteristics. For example, User A's digital twin has the characteristics of being "luxury-oriented" and "fashion-conscious."

[0365] Building a simulation environment

[0366] The server uses the digital twins to run specific simulation scenarios, such as a new product market launch scenario, and observes how the digital twins react. Through this simulation, the server determines whether many digital twins are interested in the new product.

[0367] Simulation result analysis and feedback

[0368] The server analyzes the data obtained from the simulation and calculates the optimal option for each user. For example, if User A's digital twin shows interest in a new product, the server will recommend, "An eco-friendly handbag would be perfect for you."

[0369] User notification and action support

[0370] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[0371] Through the above process, this system can provide optimal suggestions that match the user's characteristics and increase satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each user, and providing the user with the optimal options.

[0372] The processing flow will be explained below.

[0373] Step 1:

[0374] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user, and temporarily stores the data returned by the API in data storage.

[0375] Step 2:

[0376] The server cleanses the collected data, specifically removing duplicates, filling in incomplete data, correcting outliers, and standardizing the data format to make it easier to analyze.

[0377] Step 3:

[0378] The server then uses the cleansed data to profile the user. This process involves using machine learning algorithms (such as clustering and decision trees) to analyze the user's behavioral patterns and preferences and extract detailed characteristics, which then create a user profile.

[0379] Step 4:

[0380] The server then creates a digital twin based on the generated profile, which reflects the user's personality and behavioral characteristics and is placed in a virtual space.

[0381] Step 5:

[0382] The server sets up a simulation scenario and places the digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The simulation is run multiple times and the reaction patterns are recorded.

[0383] Step 6:

[0384] The server analyzes the results of the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server clarifies the user's preferences and behavioral trends and makes specific suggestions.

[0385] Step 7:

[0386] The server then sends notifications to each user based on the analysis results, for example, recommending a new eco-friendly handbag to the user.

[0387] Step 8:

[0388] The device receives notifications from the server and displays them to the user. Notifications are delivered to the user as push notifications or in-app messages, providing information in a visually easy-to-understand format.

[0389] Step 9:

[0390] The user checks the notification from the device and takes action based on the suggested option, for example, clicking on a purchase link for the suggested product and actually purchasing the product.

[0391] By going through these steps, the system can provide the user with the best options and increase user satisfaction.

[0392] Example 1

[0393] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0394] In today's digital society, there is a demand for personalized services based on individual user preferences and behavioral patterns. However, despite the vast amount of user data available, systems that can efficiently collect and analyze this data and provide optimal suggestions to users have not yet been fully established. Furthermore, further improvements are needed in methods that use digital twins to reproduce user characteristics in virtual space and provide real-time feedback based on the simulation results. Therefore, there is a need for new systems that can solve these issues and improve user satisfaction.

[0395] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0396] In this invention, the server includes means for acquiring data from a user information source, means for cleaning the acquired data, means for generating user characteristic information based on the cleaned data, means for generating a virtual user model based on the generated characteristic information, means for performing a simulation using the generated virtual user model, means for analyzing the simulation results and providing the user with an optimal selection, and means for notifying the user, thereby making it possible to provide personalized suggestions based on the user's characteristics in real time.

[0397] "User information sources" refers to multiple databases and information systems that store data related to the user.

[0398] "Data cleaning" is the process of correcting and removing duplicates, missing data, improper formats, etc. from acquired data, and preparing it in a form suitable for analysis.

[0399] "User characteristic information" is data that indicates characteristics such as user preferences and behavioral patterns, extracted from the cleaned data.

[0400] A "virtual user model" is a digital twin that is generated based on the user's characteristic information and reproduces the user's behavior and reactions in a virtual space.

[0401] "Simulation" is the process of using virtual user models to virtually perform and observe reactions to specific scenarios.

[0402] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and deriving the optimal choices and actions for the user.

[0403] "Notification" refers to the act of sending information to users via means such as push notifications or in-app messages to inform them of the analysis results.

[0404] This invention is a system that collects user data, generates a digital twin, performs simulations, and presents optimal options to the user based on the results. The program processing of this system will be described in detail below.

[0405] First, the server obtains data from the user's information sources. These information sources include a purchase history database, social media activity history, and survey results. The server accesses these data sources through APIs to obtain the necessary data. For example, the server can obtain "User A's purchase history for the past 12 months."

[0406] Next, the server cleans the acquired data. Because the data often contains duplicates and missing data, these are deleted and supplemented, and the data format is standardized. Specific actions at this stage include deleting duplicate data, supplementing missing values ​​with appropriate values, and standardizing the date format to "YYYY-MM-DD."

[0407] The server then generates user characteristic information based on the cleaned data. This characteristic information includes the user's preferences and behavioral patterns. For example, the characteristic "luxury-oriented" can be identified from the information that "User A has purchased high-quality handbags five times in the past six months."

[0408] Next, the server generates a virtual user model (digital twin) based on the generated characteristic information. To do this, a machine learning model is used, and the characteristic information is used as input data to build a user model that is reproduced in virtual space. Specifically, a neural network is built using a machine learning framework such as TensorFlow, and a digital twin that reflects the user's characteristic information is generated.

[0409] The server then runs a simulation using the generated digital twin. For example, it sets up a market introduction scenario for a new product and observes how the digital twin responds to that scenario. This simulation allows the server to collect data such as how much interest the digital twin shows in the new product.

[0410] After obtaining the simulation results, the server analyzes them and implements measures to provide the user with the optimal choice. For example, if the digital twin shows high interest in a new product, the server will recommend to the user, "An eco-friendly handbag would be perfect for you."

[0411] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, and provides a product link or purchase button so that the user can take immediate action based on the recommendation. For example, it can say, "Show a purchase link for an eco-friendly handbag."

[0412] This system performs detailed profiling and simulations based on user data, and makes personalized suggestions in real time, thereby increasing user satisfaction.

[0413] Example prompt sentence:

[0414] Create a fashion-oriented digital twin based on purchase history, social media data, and survey results. Then, simulate a market introduction scenario for a new product, "Eco-Friendly Handbags," and recommend the product to User A based on the reaction shown by the digital twin.

[0415] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0416] Step 1: Data collection

[0417] The server obtains data from user information sources, including purchase history databases, social media activity history, survey results, and other data sources.

[0418] Input: API request to data source

[0419] Specific behavior:

[0420] The server sends a request to an API endpoint.

[0421] For example, obtain JSON data containing "User A's purchase history for the past 12 months."

[0422] Output: Raw data obtained (e.g., purchase history in JSON format)

[0423] Step 2: Data Preprocessing

[0424] The server then cleans the data it receives, which is the process of correcting and removing duplicates, missing data, improper formats, etc.

[0425] Input: Raw data (e.g., purchase history in JSON format)

[0426] Specific behavior:

[0427] The server detects and removes duplicate data.

[0428] To impute missing values, fill in the missing parts with the appropriate values.

[0429] Standardize date formats, currency units, etc. Example: Convert to "YYYY-MM-DD" format.

[0430] Output: Cleaned data

[0431] Step 3: Data profiling

[0432] The server generates user characteristic information based on the cleaned data, which includes the user's preferences and behavioral patterns.

[0433] Input: Cleaned data

[0434] Specific behavior:

[0435] The server analyzes the purchase history data and extracts the user's preferences.

[0436] For example, the characteristic "luxury-oriented" can be extracted from the information that "User A has purchased high-quality handbags five times in the past six months."

[0437] Output: User characteristics information

[0438] Step 4: Generate the digital twin

[0439] The server generates a virtual user model based on the generated characteristic information, which is called a digital twin.

[0440] Input: User characteristics information

[0441] Specific behavior:

[0442] The server inputs the characteristic information into the machine learning model.

[0443] For example, TensorFlow is used to build a neural network and generate a virtual user model.

[0444] Output: The generated digital twin

[0445] Step 5: Building the simulation environment

[0446] The server uses the digital twin to set up and run specific simulation scenarios.

[0447] Input: Digital twin, simulation scenario

[0448] Specific behavior:

[0449] The server sets up a market introduction scenario for a new product.

[0450] Simulate how your digital twin will react based on scenarios.

[0451] Output: Simulation results

[0452] Step 6: Analysis and feedback of simulation results

[0453] The server analyzes the simulation results and provides the user with the optimal options.

[0454] Input: Simulation results

[0455] Specific behavior:

[0456] The server analyzes the simulation data and derives optimal suggestions for the user.

[0457] For example, if the digital twin shows high interest in a new product, it will recommend, "This eco-friendly handbag is perfect for you."

[0458] Output: Optimal recommendations for the user

[0459] Step 7: Notify users and support their actions

[0460] The device receives notifications from the server and displays them to the user, either through push notifications or in-app messages.

[0461] Input: Notification from the server

[0462] Specific behavior:

[0463] The device displays a push notification.

[0464] For example, "Show links to buy eco-friendly handbags."

[0465] Output: Notify user and display purchase link

[0466] (Application example 1)

[0467] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] In modern online shopping, inappropriate product recommendations to users can lead to a decline in user satisfaction. To make appropriate product recommendations, it is necessary to fully understand the user's purchasing history and interests and make personalized recommendations based on that. However, current systems often lack the accuracy of recommendations due to insufficient user profiling and digital twin generation.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0470] In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the simulation results, thereby enabling highly accurate product recommendations based on the user's interests.

[0471] "User data sources" refers to information sources such as a user's purchasing history, social media activity history, and survey responses.

[0472] "Means for obtaining data" refers to the method by which the server gathers the required data from the user's data source.

[0473] "Data cleansing" refers to the process of removing duplicates from acquired data, filling in missing values, and standardizing the format.

[0474] "Means for generating a user profile" refers to technology that identifies and organizes a user's characteristics, preferences, and behavioral patterns based on cleansed data.

[0475] A "digital twin" refers to a digital model that is generated in a virtual space based on a user's profile and reflects the user's internal characteristics.

[0476] "Means for performing simulation" refers to a method of using the generated digital twin to execute specific scenarios in a virtual space and observe the reactions.

[0477] "Means for analyzing the simulation results and providing the user with the optimal option" refers to a method for analyzing the data obtained from the simulation and calculating the optimal option for the user.

[0478] "Means for recommending products" refers to a mechanism that presents the most suitable products to users based on the results of the simulation.

[0479] This invention is a system that collects and analyzes data related to a user, generates a digital twin, and recommends optimal products to the user. Here, as a specific embodiment, the configuration and operation of this system will be described.

[0480] System configuration

[0481] This system consists of the following main components:

[0482] Server: Collects data, cleanses it, creates profiles, generates digital twins, performs simulations, and performs analysis.

[0483] Device: Provides notifications and action support to users. Devices include smartphones, PCs, etc.

[0484] Hardware

[0485] The main hardware required to realize the system includes:

[0486] Cloud server: Data storage and processing on the cloud

[0487] User device: smartphone or PC

[0488] software

[0489] The software includes the following:

[0490] Data collection module: Acquires purchase history, social media activity history, and survey responses via API

[0491] Data cleansing module: remove duplicates, impute missing values, and unify formats

[0492] Profile generation module: Analyzes user characteristics, preferences, and behavioral patterns

[0493] Digital twin generation module: Generates a digital model in a virtual space based on the user's characteristics

[0494] Simulation module: Run specific scenarios and observe the reactions

[0495] Analysis module: Analyzes the simulation results and calculates the best options for the user

[0496] Notification and support module: Notify users of recommended products and support their purchasing actions

[0497] Operation flow

[0498] 1. Data collection: The server obtains users' purchase history, social media activity history, survey responses, etc. through the API.

[0499] 2. Data cleansing: The server removes duplicates from the retrieved data, fills in missing values, and standardizes the format.

[0500] 3. Profile generation: The server analyzes the user's characteristics and preferences based on the cleansed data and generates a profile.

[0501] 4. Digital twin generation: The server generates a digital twin in the virtual space based on the generated profile, creating a digital model that reflects the user's characteristics.

[0502] 5. Simulation: The server uses the digital twin to run a specific scenario (e.g., introducing a new product to the market) and observe the reaction.

[0503] 6. Analysis and feedback: The server analyzes the simulation results and calculates the best product and service options for the user.

[0504] 7. Notification and action support: The device notifies the user of the recommendation results from the server and displays links and buttons so that the user can take immediate action.

[0505] Specific examples

[0506] For example, for a user with user ID 1, the system operates as follows: The server collects the user's purchase history, social media activity history, and survey responses via API and cleanses them. The server then creates a profile of the user's characteristics and preferences, and generates a digital twin in a virtual space based on that profile. Next, it runs a specific simulation scenario and observes the digital twin's reaction. Based on the results, it recommends products such as "Luxury handbags" and "Designer shoes" to the user, and notifies the user's device, allowing the user to immediately purchase these products.

[0507] Prompt Sentence Examples

[0508] "For user ID 1, please collect data on his / her purchasing history and social media activity, and generate a digital twin. Then, please run a simulation to recommend new fashion items, and notify the user of the recommendation results."

[0509] This invention makes it possible to recommend products with high accuracy based on the user's interests, and is expected to improve user satisfaction.

[0510] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0511] Step 1:

[0512] The server retrieves data from the user's data source. The input in this step is the user ID, and the output is a set of data such as purchase history, social media activity history, and survey responses. Specifically, these data sources are accessed through APIs to collect user-specific data.

[0513] Step 2:

[0514] The server cleanses the acquired data. The input in this step is the data acquired in the previous step, and the output is cleansed, high-quality data. Specifically, it removes duplicate data, fills in missing values, and standardizes the data format. This results in data suitable for analysis.

[0515] Step 3:

[0516] The server generates a user profile based on the cleansed data. The input in this step is the cleansed data, and the output is profile data that shows the user's characteristics, preferences, and behavioral patterns. Specifically, characteristics such as whether the user prefers high-priced items are extracted from purchase history and social media activity.

[0517] Step 4:

[0518] The server generates a digital twin based on the generated profile. The input in this step is the user profile, and the output is a digital twin placed in a virtual space. Specifically, a virtual model reflecting the user's interests and behavioral patterns is generated and placed in the virtual space.

[0519] Step 5:

[0520] The server runs a simulation using the generated digital twin. The inputs in this step are the digital twin and the simulation scenario, and the output is the simulation results. Specifically, for example, a scenario for introducing a new product to the market is set up, and how the digital twin reacts to that product is observed.

[0521] Step 6:

[0522] The server analyzes the simulation results and provides the user with the optimal options. The input in this step is the simulation results, and the output is recommendation data for the user. Specifically, if the digital twin shows interest in a new product, that product is presented to the user as a recommendation.

[0523] Step 7:

[0524] The device provides the notification from the server to the user. The input in this step is the recommendation data, and the output is a notification and action link for the user. Specifically, a product link and purchase button are displayed via push notification or in-app message, allowing the user to easily check the information and take action.

[0525] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0526] This invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is described below.

[0527] Data collection

[0528] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. In addition, an emotion engine is used to collect emotion data from user posts on social media and in surveys.

[0529] Data Preprocessing

[0530] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds their emotional state to the library.

[0531] Data profiling

[0532] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the characteristics of "luxury-oriented" and "positive thinking" are extracted.

[0533] Digital Twin Generation

[0534] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. For example, User A's digital twin has the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[0535] Building a simulation environment

[0536] The server uses the digital twin to run specific simulation scenarios, such as setting up a market launch scenario for a new product, and observing how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations.

[0537] Simulation result analysis and feedback

[0538] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend, "An eco-friendly handbag is perfect for you."

[0539] User notification and action support

[0540] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[0541] Through the above process, this system can provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each individual user, and providing the user with the optimal options.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] The server sends API requests to user data sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. At the same time, an emotion engine is used to collect emotion data from social media and survey text.

[0545] Step 2:

[0546] The server cleanses the collected data, eliminating duplicates, filling in incomplete data, and standardizing formats. An emotion engine also extracts the user's emotional state through text analysis and adds it to the cleansed data.

[0547] Step 3:

[0548] The server uses machine learning algorithms (such as clustering and decision trees) to generate a user profile based on the cleansed data. The profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and displays many positive emotions, the characteristics "luxury-oriented" and "positive thinking" can be derived.

[0549] Step 4:

[0550] The server generates a digital twin of the user based on the generated profile. The digital twin simulates the user's personality, behavioral characteristics, and emotional state and is placed in a virtual space. User A's digital twin has characteristics such as "luxury-oriented," "fashion-conscious," and "positive thinking."

[0551] Step 5:

[0552] The server sets up a simulation scenario and places the generated digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The emotion engine monitors the digital twin's emotional state in real time and records in detail how the user feels within the scenario.

[0553] Step 6:

[0554] The server analyzes the results of the simulation and calculates the optimal option for the user. The analysis makes specific suggestions based on the digital twin's behavioral patterns and emotional transitions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend something like, "This eco-friendly handbag is perfect for you."

[0555] Step 7:

[0556] The server then sends notifications to each user based on the analysis results. Notifications can be sent via push notifications or in-app messages, and include detailed information and links about the recommended products.

[0557] Step 8:

[0558] The device receives notifications from the server and displays them to the user. An intuitive interface is provided so that users can easily check the notifications. For example, purchase links and detailed information are displayed in the form of easy-to-click buttons.

[0559] Step 9:

[0560] The user checks the notification from the device and takes action based on the options presented, for example, clicking on a link in the notification and purchasing the recommended product.

[0561] Through these steps, the system can provide users with optimal suggestions that match their characteristics and emotions, improving satisfaction.

[0562] Example 2

[0563] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0564] In recent years, there has been a demand for personalized services based on users' preferences, personalities, and emotions, but the challenge is that it is difficult to integrate diverse user data and provide effective information. In particular, conventional systems are unable to adequately analyze emotional data, generate digital twins, or analyze simulation results, making it difficult to provide users with optimal options.

[0565] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0566] In this invention, the server includes means for acquiring data from a user's information source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, means for collecting and preprocessing data, means for collecting and analyzing emotional data using an emotion analysis engine, means for setting and executing a specific simulation scenario, and means for analyzing the simulation data and calculating optimal options. This makes it possible to integrate a variety of user data, achieve highly accurate profiling and simulation including emotional data, and provide the user with optimal options.

[0567] A "user" is an individual or organization that uses the system to receive services or information.

[0568] A "source" is an external database or platform that provides data relevant to a user.

[0569] "Data cleansing" is the process of removing duplicate and incomplete data from acquired data and standardizing the data format.

[0570] A "user profile" is information that represents a user's characteristics, preferences, behavioral patterns, and emotional state, generated based on cleansed data.

[0571] A "digital twin" is a digital representation of a user that is generated in a virtual space based on the user's real-world profile.

[0572] "Simulation" is the process of using a digital twin to recreate a specific scenario in a virtual environment and observe the results.

[0573] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and calculating the optimal options for the user.

[0574] An "emotion analysis engine" is software or an algorithm for analyzing a user's emotions from text or statements.

[0575] A "simulation scenario" is an item that refers to a specific situation or condition that is set when a simulation is performed.

[0576] The present invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides optimal options to the user based on the results.

[0577] Data collection

[0578] The server sends API requests to user information sources (such as purchase history databases, social media platforms, and survey systems) to collect data related to each user. The collected data is temporarily stored in data storage. A sentiment analysis engine is also used to collect emotional data from user posts on social media and in surveys. The hardware used for this is a high-performance server, and software such as OpenAI and IBM Watson is used for sentiment analysis.

[0579] Data Preprocessing

[0580] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. This process uses the Python Pandas library. A sentiment analysis engine analyzes text from social media and surveys and adds the user's emotional state to the library.

[0581] Data profiling

[0582] Based on the cleansed data, the server creates a user profile. This profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the server extracts the characteristics of "luxury-oriented" and "positive thinking." This profiling is performed using a machine learning model (scikit-learn).

[0583] Digital Twin Generation

[0584] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is placed in a virtual space. This process uses virtual reality software such as Unity or Unreal Engine. For example, User A's digital twin would have the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[0585] Building a simulation environment

[0586] The server runs specific simulation scenarios using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. An emotion analysis engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations. The simulations are performed using simulation software such as MATLAB and Simulink.

[0587] Simulation result analysis and feedback

[0588] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the user's preferences, behavioral tendencies, and emotional state can be clarified and specific suggestions can be made. For example, if User A's digital twin has a very positive reaction to a new product, the server will recommend, "An eco-friendly handbag would be perfect for you." This analysis is performed using Python's NumPy and SciPy libraries.

[0589] User notification and action support

[0590] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message. To make it easy for the user to check the information, the device provides a product link or purchase button so that the user can take immediate action based on the suggestion. For example, a purchase link for an eco-friendly handbag is displayed. This notification is sent using a notification service such as Firebase Cloud Messaging (FCM).

[0591] This system can provide optimal suggestions that match the user's characteristics and emotions, increasing satisfaction. A concrete example is the case where User A purchased a new product and his satisfaction increased.

[0592] Examples of prompt statements

[0593] "Please provide a step-by-step guide to create a program that analyzes emotions from users' social media posts and builds a recommendation system based on the results."

[0594] "Please explain in detail the algorithm used to generate a user's digital twin using purchase history data and social media sentiment data."

[0595] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0596] Step 1: Data collection

[0597] The server sends API requests to user information sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The input is the user's ID and search query, and the output is raw data in JSON format. Specifically, the server uses the Python requests library to send requests to the API and temporarily saves the retrieved data in data storage. It also calls a sentiment analysis engine to collect emotional data from social media and surveys.

[0598] Step 2: Cleanse the data

[0599] The server cleanses the acquired data. The input is the raw data collected in step 1, and the output is cleansed data with duplicate data removed, incomplete data completed, and a unified format. Specifically, the server uses the Python Pandas library to create a data frame, remove duplicate data, and complete incomplete data. The sentiment analysis engine also analyzes the data and adds the emotional state to the library.

[0600] Step 3: Data profiling

[0601] The server profiles users based on the cleansed data. The input is the cleansed data, and the output is a profile that includes the user's characteristics, preferences, behavioral patterns, and emotional state. Specifically, the server analyzes the data using a machine learning model (scikit-learn) to extract user characteristics. For example, if a particular user frequently purchases high-quality products and expresses a lot of positive emotions, the server can profile the user's characteristics based on that.

[0602] Step 4: Generate the digital twin

[0603] The server generates a digital twin based on the generated profile. The input is the user's profile, and the output is a digital twin placed in a virtual space. Specifically, the server generates the digital twin using virtual reality software such as Unity or Unreal Engine. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is capable of acting in the virtual space.

[0604] Step 5: Building the simulation environment

[0605] The server runs a specific simulation scenario using the digital twin. The input is the settings for the specific simulation scenario, and the output is the simulation data. Specifically, the server uses simulation software such as MATLAB or Simulink to set up and run the simulation scenario. The emotion analysis engine monitors the emotional state of the digital twin in real time, enabling more accurate simulations.

[0606] Step 6: Analysis and feedback of simulation results

[0607] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. The input is the simulation data, and the output is a specific recommendation for the user. Specifically, the server analyzes the simulation data using Python's NumPy and SciPy libraries to clarify the user's preferences, behavioral tendencies, and emotional state. For example, if User A's digital twin reacts positively to a new product, the server will recommend, "This eco-friendly handbag is perfect for you."

[0608] Step 7: Notify users and support their actions

[0609] The device (user's smartphone or PC) receives notifications from the server and displays them to the user. The input is the notification data from the server, and the output is the notification message that is displayed to the user. Specifically, the device receives push notifications using services such as Firebase Cloud Messaging (FCM) and displays them as in-app messages. Actions such as product links and purchase buttons are provided so that users can easily check the information. For example, a purchase link for an eco-friendly handbag may be displayed.

[0610] Through this system, it is possible to provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction.

[0611] (Application example 2)

[0612] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0613] In conventional shopping experiences, it has been difficult to accurately understand a user's purchasing behavior, preferences, and emotional state, and to recommend optimal products based on that. In particular, there is a lack of systems that perform real-time emotion analysis and provide personalized product recommendations, making it difficult to increase user satisfaction.

[0614] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the analysis results. This enables personalized product recommendations in real time that accurately reflect the user's preferences and emotional state.

[0615] "User" refers to an individual consumer or end user of the System.

[0616] "Data source" refers to the original source of information that provides information related to a user, such as a user's purchase history, social media posts, or survey responses.

[0617] "Data cleansing" refers to the process of removing duplicates from collected data, completing incomplete data, and standardizing the format.

[0618] A "profile" refers to a digital data collection that includes a user's characteristics, preferences, and emotional state, generated based on cleansed data.

[0619] "Digital twin" refers to a digital model that is generated based on a user's profile and can simulate the user's behavior and reactions in a virtual space.

[0620] "Simulation" refers to the process of using the generated digital twin to try out reactions and actions in a virtual space in response to a specific scenario.

[0621] "Providing options" refers to the act of analyzing the simulation results and recommending the best proposals and products for the user.

[0622] "Means for recommending products" refers to the system's ability to present products and services suited to the user based on the user's profile and simulation results.

[0623] The present invention relates to a system that analyzes user data and emotions and generates a digital twin. This system provides the user with optimal options based on a simulation in a virtual space. Specific embodiments of the present invention will be described below.

[0624] Data collection

[0625] The server sends API requests to retrieve data from the user's data sources (e.g., purchase history database, social media platform, survey system). The collected data is temporarily stored in data storage. It also uses an emotion engine to collect emotion data from user posts on social media and surveys. The hardware used is a general-purpose server, and the software uses a RESTful API.

[0626] Data Preprocessing

[0627] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds the emotional state to the library. The tool used for data cleansing is the Python pandas library.

[0628] Data profiling

[0629] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if a user frequently purchases luxury handbags and expresses many positive emotions on social media, the characteristics "luxury-oriented" and "positive thinking" can be extracted. Machine learning algorithms (such as the scikit-learn library) are used for profiling.

[0630] Digital Twin Generation

[0631] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. The digital twin is created using Python's object-oriented programming method.

[0632] Building a simulation environment

[0633] The server runs specific simulation scenarios using the digital twin. For example, it sets up a scenario for introducing a new product to the market and observes how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time, enabling more accurate simulations. The simulations are run using Unity and other virtual environment building tools.

[0634] Simulation result analysis and feedback

[0635] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. This analysis is performed using Python's numpy and pandas libraries. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if the user's digital twin responds very positively to a new product, it can recommend an eco-friendly handbag.

[0636] User notification and action support

[0637] The user's device (smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device then provides a product link or purchase button so that the user can take immediate action based on the suggestion, allowing the user to make a quick decision.

[0638] Specific examples and generated AI prompts

[0639] Specific examples

[0640] For example, if a user's purchasing history indicates a preference for luxury goods and they post many positive comments on social media, the system can use this information to create a digital twin. If a new product, an eco-friendly handbag, is introduced and the user's digital twin responds very positively, the system can recommend it directly to the user.

[0641] Example of a generated AI prompt

[0642] "A user posts on social media, 'I love eco-friendly handbags!' Based on this post, please analyze the user's sentiment data and recommend the most suitable products."

[0643] As can be seen, the system of the present invention is able to leverage user data and sentiment data to provide real-time personalized recommendations and enrich the user's shopping experience.

[0644] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0645] Step 1:

[0646] The server retrieves data from the user's data source. Specifically, it sends API requests to a purchase history database, a social media platform, a survey system, etc. The input is the user's identification information, and the output is raw data such as the user's purchase history and social media posts. This data is temporarily stored in data storage.

[0647] Step 2:

[0648] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. The data is organized using the Python pandas library. The input is the raw data acquired in step 1, and the output is the cleansed data.

[0649] Step 3:

[0650] The server generates a user profile based on the cleansed data. Specifically, it compiles preferences and behavioral patterns into a profile based on the user's purchasing history and emotional data. It uses a machine learning algorithm (scikit-learn library). The input is the cleansed data, and the output is a detailed user profile.

[0651] Step 4:

[0652] The server generates a digital twin based on the generated profile. It uses Python object-oriented programming techniques to build a digital twin that reflects the profile. The input is the user profile, and the output is the digital twin.

[0653] Step 5:

[0654] The server runs a specific simulation scenario using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. It uses Unity or other virtual environment building tools. The input is the digital twin, and the output is the simulation result data.

[0655] Step 6:

[0656] The server analyzes the simulation results and calculates the optimal option for the user. It uses Python's numpy and pandas libraries to analyze the simulation results. The input is the simulation result data, and the output is specific recommendations for the user.

[0657] Step 7:

[0658] The device (smartphone or PC) receives notifications from the server and displays them to the user. Notifications are sent via push notifications or in-app messages, allowing users to easily check the information. The input is the recommendation content sent from the server, and the output is the recommended information displayed on the user's screen.

[0659] The above steps enable real-time personalized product recommendations.

[0660] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0661] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0662] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0663] [Third embodiment]

[0664] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0665] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0666] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0667] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0668] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0669] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0670] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0671] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0672] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0673] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0674] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0675] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0676] This invention details a system that collects and analyzes user-related data and generates a digital twin of the user. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is explained below.

[0677] Data collection

[0678] The server first obtains the necessary data from the user's data source. Data sources include the user's purchase history, social media activity history, survey responses, etc. For example, the server accesses a purchase history database via an API and obtains a list of products that User A has purchased in the past.

[0679] Data Preprocessing

[0680] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in missing values, and standardizing the format. This ensures the quality of the data.

[0681] Data profiling

[0682] Based on the cleansed data, the server generates a user profile, which includes the user's characteristics, preferences, behavioral patterns, etc. For example, if user A frequently purchases high-quality handbags, the characteristic "luxury-oriented" is extracted.

[0683] Digital Twin Generation

[0684] Based on the generated profile, the server creates a digital twin of the user. The digital twin is placed in a virtual space and also reflects the user's internal characteristics. For example, User A's digital twin has the characteristics of being "luxury-oriented" and "fashion-conscious."

[0685] Building a simulation environment

[0686] The server uses the digital twins to run specific simulation scenarios, such as a new product market launch scenario, and observes how the digital twins react. Through this simulation, the server determines whether many digital twins are interested in the new product.

[0687] Simulation result analysis and feedback

[0688] The server analyzes the data obtained from the simulation and calculates the optimal option for each user. For example, if User A's digital twin shows interest in a new product, the server will recommend, "An eco-friendly handbag would be perfect for you."

[0689] User notification and action support

[0690] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[0691] Through the above process, this system can provide optimal suggestions that match the user's characteristics and increase satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each user, and providing the user with the optimal options.

[0692] The processing flow will be explained below.

[0693] Step 1:

[0694] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user, and temporarily stores the data returned by the API in data storage.

[0695] Step 2:

[0696] The server cleanses the collected data, specifically removing duplicates, filling in incomplete data, correcting outliers, and standardizing the data format to make it easier to analyze.

[0697] Step 3:

[0698] The server then uses the cleansed data to profile the user. This process involves using machine learning algorithms (such as clustering and decision trees) to analyze the user's behavioral patterns and preferences and extract detailed characteristics, which then create a user profile.

[0699] Step 4:

[0700] The server then creates a digital twin based on the generated profile, which reflects the user's personality and behavioral characteristics and is placed in a virtual space.

[0701] Step 5:

[0702] The server sets up a simulation scenario and places the digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The simulation is run multiple times and the reaction patterns are recorded.

[0703] Step 6:

[0704] The server analyzes the results of the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server clarifies the user's preferences and behavioral trends and makes specific suggestions.

[0705] Step 7:

[0706] The server then sends notifications to each user based on the analysis results, for example, recommending a new eco-friendly handbag to the user.

[0707] Step 8:

[0708] The device receives notifications from the server and displays them to the user. Notifications are delivered to the user as push notifications or in-app messages, providing information in a visually easy-to-understand format.

[0709] Step 9:

[0710] The user checks the notification from the device and takes action based on the suggested option, for example, clicking on a purchase link for the suggested product and actually purchasing the product.

[0711] By going through these steps, the system can provide the user with the best options and increase user satisfaction.

[0712] Example 1

[0713] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0714] In today's digital society, there is a demand for personalized services based on individual user preferences and behavioral patterns. However, despite the vast amount of user data available, systems that can efficiently collect and analyze this data and provide optimal suggestions to users have not yet been fully established. Furthermore, further improvements are needed in methods that use digital twins to reproduce user characteristics in virtual space and provide real-time feedback based on the simulation results. Therefore, there is a need for new systems that can solve these issues and improve user satisfaction.

[0715] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0716] In this invention, the server includes means for acquiring data from a user information source, means for cleaning the acquired data, means for generating user characteristic information based on the cleaned data, means for generating a virtual user model based on the generated characteristic information, means for performing a simulation using the generated virtual user model, means for analyzing the simulation results and providing the user with an optimal selection, and means for notifying the user, thereby making it possible to provide personalized suggestions based on the user's characteristics in real time.

[0717] "User information sources" refers to multiple databases and information systems that store data related to the user.

[0718] "Data cleaning" is the process of correcting and removing duplicates, missing data, improper formats, etc. from acquired data, and preparing it in a form suitable for analysis.

[0719] "User characteristic information" is data that indicates characteristics such as user preferences and behavioral patterns, extracted from the cleaned data.

[0720] A "virtual user model" is a digital twin that is generated based on the user's characteristic information and reproduces the user's behavior and reactions in a virtual space.

[0721] "Simulation" is the process of using virtual user models to virtually perform and observe reactions to specific scenarios.

[0722] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and deriving the optimal choices and actions for the user.

[0723] "Notification" refers to the act of sending information to users via means such as push notifications or in-app messages to inform them of the analysis results.

[0724] This invention is a system that collects user data, generates a digital twin, performs simulations, and presents optimal options to the user based on the results. The program processing of this system will be described in detail below.

[0725] First, the server obtains data from the user's information sources. These information sources include a purchase history database, social media activity history, and survey results. The server accesses these data sources through APIs to obtain the necessary data. For example, the server can obtain "User A's purchase history for the past 12 months."

[0726] Next, the server cleans the acquired data. Because the data often contains duplicates and missing data, these are deleted and supplemented, and the data format is standardized. Specific actions at this stage include deleting duplicate data, supplementing missing values ​​with appropriate values, and standardizing the date format to "YYYY-MM-DD."

[0727] The server then generates user characteristic information based on the cleaned data. This characteristic information includes the user's preferences and behavioral patterns. For example, the characteristic "luxury-oriented" can be identified from the information that "User A has purchased high-quality handbags five times in the past six months."

[0728] Next, the server generates a virtual user model (digital twin) based on the generated characteristic information. To do this, a machine learning model is used, and the characteristic information is used as input data to build a user model that is reproduced in virtual space. Specifically, a neural network is built using a machine learning framework such as TensorFlow, and a digital twin that reflects the user's characteristic information is generated.

[0729] The server then runs a simulation using the generated digital twin. For example, it sets up a market introduction scenario for a new product and observes how the digital twin responds to that scenario. This simulation allows the server to collect data such as how much interest the digital twin shows in the new product.

[0730] After obtaining the simulation results, the server analyzes them and implements measures to provide the user with the optimal choice. For example, if the digital twin shows high interest in a new product, the server will recommend to the user, "An eco-friendly handbag would be perfect for you."

[0731] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, and provides a product link or purchase button so that the user can take immediate action based on the recommendation. For example, it can say, "Show a purchase link for an eco-friendly handbag."

[0732] This system performs detailed profiling and simulations based on user data, and makes personalized suggestions in real time, thereby increasing user satisfaction.

[0733] Example prompt sentence:

[0734] Create a fashion-oriented digital twin based on purchase history, social media data, and survey results. Then, simulate a market introduction scenario for a new product, "Eco-Friendly Handbags," and recommend the product to User A based on the reaction shown by the digital twin.

[0735] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0736] Step 1: Data collection

[0737] The server obtains data from user information sources, including purchase history databases, social media activity history, survey results, and other data sources.

[0738] Input: API request to data source

[0739] Specific behavior:

[0740] The server sends a request to an API endpoint.

[0741] For example, obtain JSON data containing "User A's purchase history for the past 12 months."

[0742] Output: Raw data obtained (e.g., purchase history in JSON format)

[0743] Step 2: Data Preprocessing

[0744] The server then cleans the data it receives, which is the process of correcting and removing duplicates, missing data, improper formats, etc.

[0745] Input: Raw data (e.g., purchase history in JSON format)

[0746] Specific behavior:

[0747] The server detects and removes duplicate data.

[0748] To impute missing values, fill in the missing parts with the appropriate values.

[0749] Standardize date formats, currency units, etc. Example: Convert to "YYYY-MM-DD" format.

[0750] Output: Cleaned data

[0751] Step 3: Data profiling

[0752] The server generates user characteristic information based on the cleaned data, which includes the user's preferences and behavioral patterns.

[0753] Input: Cleaned data

[0754] Specific behavior:

[0755] The server analyzes the purchase history data and extracts the user's preferences.

[0756] For example, the characteristic "luxury-oriented" can be extracted from the information that "User A has purchased high-quality handbags five times in the past six months."

[0757] Output: User characteristics information

[0758] Step 4: Generate the digital twin

[0759] The server generates a virtual user model based on the generated characteristic information, which is called a digital twin.

[0760] Input: User characteristics information

[0761] Specific behavior:

[0762] The server inputs the characteristic information into the machine learning model.

[0763] For example, TensorFlow is used to build a neural network and generate a virtual user model.

[0764] Output: The generated digital twin

[0765] Step 5: Building the simulation environment

[0766] The server uses the digital twin to set up and run specific simulation scenarios.

[0767] Input: Digital twin, simulation scenario

[0768] Specific behavior:

[0769] The server sets up a market introduction scenario for a new product.

[0770] Simulate how your digital twin will react based on scenarios.

[0771] Output: Simulation results

[0772] Step 6: Analysis and feedback of simulation results

[0773] The server analyzes the simulation results and provides the user with the optimal options.

[0774] Input: Simulation results

[0775] Specific behavior:

[0776] The server analyzes the simulation data and derives optimal suggestions for the user.

[0777] For example, if the digital twin shows high interest in a new product, it will recommend, "This eco-friendly handbag is perfect for you."

[0778] Output: Optimal recommendations for the user

[0779] Step 7: Notify users and support their actions

[0780] The device receives notifications from the server and displays them to the user, either through push notifications or in-app messages.

[0781] Input: Notification from the server

[0782] Specific behavior:

[0783] The device displays a push notification.

[0784] For example, "Show links to buy eco-friendly handbags."

[0785] Output: Notify user and display purchase link

[0786] (Application example 1)

[0787] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0788] In modern online shopping, inappropriate product recommendations to users can lead to a decline in user satisfaction. To make appropriate product recommendations, it is necessary to fully understand the user's purchasing history and interests and make personalized recommendations based on that. However, current systems often lack the accuracy of recommendations due to insufficient user profiling and digital twin generation.

[0789] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0790] In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the simulation results, thereby enabling highly accurate product recommendations based on the user's interests.

[0791] "User data sources" refers to information sources such as a user's purchasing history, social media activity history, and survey responses.

[0792] "Means for obtaining data" refers to the method by which the server gathers the required data from the user's data source.

[0793] "Data cleansing" refers to the process of removing duplicates from acquired data, filling in missing values, and standardizing the format.

[0794] "Means for generating a user profile" refers to technology that identifies and organizes a user's characteristics, preferences, and behavioral patterns based on cleansed data.

[0795] A "digital twin" refers to a digital model that is generated in a virtual space based on a user's profile and reflects the user's internal characteristics.

[0796] "Means for performing simulation" refers to a method of using the generated digital twin to execute specific scenarios in a virtual space and observe the reactions.

[0797] "Means for analyzing the simulation results and providing the user with the optimal option" refers to a method for analyzing the data obtained from the simulation and calculating the optimal option for the user.

[0798] "Means for recommending products" refers to a mechanism that presents the most suitable products to users based on the results of the simulation.

[0799] This invention is a system that collects and analyzes data related to a user, generates a digital twin, and recommends optimal products to the user. Here, as a specific embodiment, the configuration and operation of this system will be described.

[0800] System configuration

[0801] This system consists of the following main components:

[0802] Server: Collects data, cleanses it, creates profiles, generates digital twins, performs simulations, and performs analysis.

[0803] Device: Provides notifications and action support to users. Devices include smartphones, PCs, etc.

[0804] Hardware

[0805] The main hardware required to realize the system includes:

[0806] Cloud server: Data storage and processing on the cloud

[0807] User device: smartphone or PC

[0808] software

[0809] The software includes the following:

[0810] Data collection module: Acquires purchase history, social media activity history, and survey responses via API

[0811] Data cleansing module: remove duplicates, impute missing values, and unify formats

[0812] Profile generation module: Analyzes user characteristics, preferences, and behavioral patterns

[0813] Digital twin generation module: Generates a digital model in a virtual space based on the user's characteristics

[0814] Simulation module: Run specific scenarios and observe the reactions

[0815] Analysis module: Analyzes the simulation results and calculates the best options for the user

[0816] Notification and support module: Notify users of recommended products and support their purchasing actions

[0817] Operation flow

[0818] 1. Data collection: The server obtains users' purchase history, social media activity history, survey responses, etc. through the API.

[0819] 2. Data cleansing: The server removes duplicates from the retrieved data, fills in missing values, and standardizes the format.

[0820] 3. Profile generation: The server analyzes the user's characteristics and preferences based on the cleansed data and generates a profile.

[0821] 4. Digital twin generation: The server generates a digital twin in the virtual space based on the generated profile, creating a digital model that reflects the user's characteristics.

[0822] 5. Simulation: The server uses the digital twin to run a specific scenario (e.g., introducing a new product to the market) and observe the reaction.

[0823] 6. Analysis and feedback: The server analyzes the simulation results and calculates the best product and service options for the user.

[0824] 7. Notification and action support: The device notifies the user of the recommendation results from the server and displays links and buttons so that the user can take immediate action.

[0825] Specific examples

[0826] For example, for a user with user ID 1, the system operates as follows: The server collects the user's purchase history, social media activity history, and survey responses via API and cleanses them. The server then creates a profile of the user's characteristics and preferences, and generates a digital twin in a virtual space based on that profile. Next, it runs a specific simulation scenario and observes the digital twin's reaction. Based on the results, it recommends products such as "Luxury handbags" and "Designer shoes" to the user, and notifies the user's device, allowing the user to immediately purchase these products.

[0827] Prompt Sentence Examples

[0828] "For user ID 1, please collect data on his / her purchasing history and social media activity, and generate a digital twin. Then, please run a simulation to recommend new fashion items, and notify the user of the recommendation results."

[0829] This invention makes it possible to recommend products with high accuracy based on the user's interests, and is expected to improve user satisfaction.

[0830] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0831] Step 1:

[0832] The server retrieves data from the user's data source. The input in this step is the user ID, and the output is a set of data such as purchase history, social media activity history, and survey responses. Specifically, these data sources are accessed through APIs to collect user-specific data.

[0833] Step 2:

[0834] The server cleanses the acquired data. The input in this step is the data acquired in the previous step, and the output is cleansed, high-quality data. Specifically, it removes duplicate data, fills in missing values, and standardizes the data format. This results in data suitable for analysis.

[0835] Step 3:

[0836] The server generates a user profile based on the cleansed data. The input in this step is the cleansed data, and the output is profile data that shows the user's characteristics, preferences, and behavioral patterns. Specifically, characteristics such as whether the user prefers high-priced items are extracted from purchase history and social media activity.

[0837] Step 4:

[0838] The server generates a digital twin based on the generated profile. The input in this step is the user profile, and the output is a digital twin placed in a virtual space. Specifically, a virtual model reflecting the user's interests and behavioral patterns is generated and placed in the virtual space.

[0839] Step 5:

[0840] The server runs a simulation using the generated digital twin. The inputs in this step are the digital twin and the simulation scenario, and the output is the simulation results. Specifically, for example, a scenario for introducing a new product to the market is set up, and how the digital twin reacts to that product is observed.

[0841] Step 6:

[0842] The server analyzes the simulation results and provides the user with the optimal options. The input in this step is the simulation results, and the output is recommendation data for the user. Specifically, if the digital twin shows interest in a new product, that product is presented to the user as a recommendation.

[0843] Step 7:

[0844] The device provides the notification from the server to the user. The input in this step is the recommendation data, and the output is a notification and action link for the user. Specifically, a product link and purchase button are displayed via push notification or in-app message, allowing the user to easily check the information and take action.

[0845] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0846] This invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is described below.

[0847] Data collection

[0848] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. In addition, an emotion engine is used to collect emotion data from user posts on social media and in surveys.

[0849] Data Preprocessing

[0850] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds their emotional state to the library.

[0851] Data profiling

[0852] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the characteristics of "luxury-oriented" and "positive thinking" are extracted.

[0853] Digital Twin Generation

[0854] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. For example, User A's digital twin has the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[0855] Building a simulation environment

[0856] The server uses the digital twin to run specific simulation scenarios, such as setting up a market launch scenario for a new product, and observing how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations.

[0857] Simulation result analysis and feedback

[0858] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend, "An eco-friendly handbag is perfect for you."

[0859] User notification and action support

[0860] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[0861] Through the above process, this system can provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each individual user, and providing the user with the optimal options.

[0862] The processing flow will be explained below.

[0863] Step 1:

[0864] The server sends API requests to user data sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. At the same time, an emotion engine is used to collect emotion data from social media and survey text.

[0865] Step 2:

[0866] The server cleanses the collected data, eliminating duplicates, filling in incomplete data, and standardizing formats. An emotion engine also extracts the user's emotional state through text analysis and adds it to the cleansed data.

[0867] Step 3:

[0868] The server uses machine learning algorithms (such as clustering and decision trees) to generate a user profile based on the cleansed data. The profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and displays many positive emotions, the characteristics "luxury-oriented" and "positive thinking" can be derived.

[0869] Step 4:

[0870] The server generates a digital twin of the user based on the generated profile. The digital twin simulates the user's personality, behavioral characteristics, and emotional state and is placed in a virtual space. User A's digital twin has characteristics such as "luxury-oriented," "fashion-conscious," and "positive thinking."

[0871] Step 5:

[0872] The server sets up a simulation scenario and places the generated digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The emotion engine monitors the digital twin's emotional state in real time and records in detail how the user feels within the scenario.

[0873] Step 6:

[0874] The server analyzes the results of the simulation and calculates the optimal option for the user. The analysis makes specific suggestions based on the digital twin's behavioral patterns and emotional transitions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend something like, "This eco-friendly handbag is perfect for you."

[0875] Step 7:

[0876] The server then sends notifications to each user based on the analysis results. Notifications can be sent via push notifications or in-app messages, and include detailed information and links about the recommended products.

[0877] Step 8:

[0878] The device receives notifications from the server and displays them to the user. An intuitive interface is provided so that users can easily check the notifications. For example, purchase links and detailed information are displayed in the form of easy-to-click buttons.

[0879] Step 9:

[0880] The user checks the notification from the device and takes action based on the options presented, for example, clicking on a link in the notification and purchasing the recommended product.

[0881] Through these steps, the system can provide users with optimal suggestions that match their characteristics and emotions, improving satisfaction.

[0882] Example 2

[0883] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0884] In recent years, there has been a demand for personalized services based on users' preferences, personalities, and emotions, but the challenge is that it is difficult to integrate diverse user data and provide effective information. In particular, conventional systems are unable to adequately analyze emotional data, generate digital twins, or analyze simulation results, making it difficult to provide users with optimal options.

[0885] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0886] In this invention, the server includes means for acquiring data from a user's information source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, means for collecting and preprocessing data, means for collecting and analyzing emotional data using an emotion analysis engine, means for setting and executing a specific simulation scenario, and means for analyzing the simulation data and calculating optimal options. This makes it possible to integrate a variety of user data, achieve highly accurate profiling and simulation including emotional data, and provide the user with optimal options.

[0887] A "user" is an individual or organization that uses the system to receive services or information.

[0888] A "source" is an external database or platform that provides data relevant to a user.

[0889] "Data cleansing" is the process of removing duplicate and incomplete data from acquired data and standardizing the data format.

[0890] A "user profile" is information that represents a user's characteristics, preferences, behavioral patterns, and emotional state, generated based on cleansed data.

[0891] A "digital twin" is a digital representation of a user that is generated in a virtual space based on the user's real-world profile.

[0892] "Simulation" is the process of using a digital twin to recreate a specific scenario in a virtual environment and observe the results.

[0893] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and calculating the optimal options for the user.

[0894] An "emotion analysis engine" is software or an algorithm for analyzing a user's emotions from text or statements.

[0895] A "simulation scenario" is an item that refers to a specific situation or condition that is set when a simulation is performed.

[0896] The present invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides optimal options to the user based on the results.

[0897] Data collection

[0898] The server sends API requests to user information sources (such as purchase history databases, social media platforms, and survey systems) to collect data related to each user. The collected data is temporarily stored in data storage. A sentiment analysis engine is also used to collect emotional data from user posts on social media and in surveys. The hardware used for this is a high-performance server, and software such as OpenAI and IBM Watson is used for sentiment analysis.

[0899] Data Preprocessing

[0900] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. This process uses the Python Pandas library. A sentiment analysis engine analyzes text from social media and surveys and adds the user's emotional state to the library.

[0901] Data profiling

[0902] Based on the cleansed data, the server creates a user profile. This profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the server extracts the characteristics of "luxury-oriented" and "positive thinking." This profiling is performed using a machine learning model (scikit-learn).

[0903] Digital Twin Generation

[0904] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is placed in a virtual space. This process uses virtual reality software such as Unity or Unreal Engine. For example, User A's digital twin would have the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[0905] Building a simulation environment

[0906] The server runs specific simulation scenarios using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. An emotion analysis engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations. The simulations are performed using simulation software such as MATLAB and Simulink.

[0907] Simulation result analysis and feedback

[0908] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the user's preferences, behavioral tendencies, and emotional state can be clarified and specific suggestions can be made. For example, if User A's digital twin has a very positive reaction to a new product, the server will recommend, "An eco-friendly handbag would be perfect for you." This analysis is performed using Python's NumPy and SciPy libraries.

[0909] User notification and action support

[0910] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message. To make it easy for the user to check the information, the device provides a product link or purchase button so that the user can take immediate action based on the suggestion. For example, a purchase link for an eco-friendly handbag is displayed. This notification is sent using a notification service such as Firebase Cloud Messaging (FCM).

[0911] This system can provide optimal suggestions that match the user's characteristics and emotions, increasing satisfaction. A concrete example is the case where User A purchased a new product and his satisfaction increased.

[0912] Examples of prompt statements

[0913] "Please provide a step-by-step guide to create a program that analyzes emotions from users' social media posts and builds a recommendation system based on the results."

[0914] "Please explain in detail the algorithm used to generate a user's digital twin using purchase history data and social media sentiment data."

[0915] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0916] Step 1: Data collection

[0917] The server sends API requests to user information sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The input is the user's ID and search query, and the output is raw data in JSON format. Specifically, the server uses the Python requests library to send requests to the API and temporarily saves the retrieved data in data storage. It also calls a sentiment analysis engine to collect emotional data from social media and surveys.

[0918] Step 2: Cleanse the data

[0919] The server cleanses the acquired data. The input is the raw data collected in step 1, and the output is cleansed data with duplicate data removed, incomplete data completed, and a unified format. Specifically, the server uses the Python Pandas library to create a data frame, remove duplicate data, and complete incomplete data. The sentiment analysis engine also analyzes the data and adds the emotional state to the library.

[0920] Step 3: Data profiling

[0921] The server profiles users based on the cleansed data. The input is the cleansed data, and the output is a profile that includes the user's characteristics, preferences, behavioral patterns, and emotional state. Specifically, the server analyzes the data using a machine learning model (scikit-learn) to extract user characteristics. For example, if a particular user frequently purchases high-quality products and expresses a lot of positive emotions, the server can profile the user's characteristics based on that.

[0922] Step 4: Generate the digital twin

[0923] The server generates a digital twin based on the generated profile. The input is the user's profile, and the output is a digital twin placed in a virtual space. Specifically, the server generates the digital twin using virtual reality software such as Unity or Unreal Engine. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is capable of acting in the virtual space.

[0924] Step 5: Building the simulation environment

[0925] The server runs a specific simulation scenario using the digital twin. The input is the settings for the specific simulation scenario, and the output is the simulation data. Specifically, the server uses simulation software such as MATLAB or Simulink to set up and run the simulation scenario. The emotion analysis engine monitors the emotional state of the digital twin in real time, enabling more accurate simulations.

[0926] Step 6: Analysis and feedback of simulation results

[0927] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. The input is the simulation data, and the output is a specific recommendation for the user. Specifically, the server analyzes the simulation data using Python's NumPy and SciPy libraries to clarify the user's preferences, behavioral tendencies, and emotional state. For example, if User A's digital twin reacts positively to a new product, the server will recommend, "This eco-friendly handbag is perfect for you."

[0928] Step 7: Notify users and support their actions

[0929] The device (user's smartphone or PC) receives notifications from the server and displays them to the user. The input is the notification data from the server, and the output is the notification message that is displayed to the user. Specifically, the device receives push notifications using services such as Firebase Cloud Messaging (FCM) and displays them as in-app messages. Actions such as product links and purchase buttons are provided so that users can easily check the information. For example, a purchase link for an eco-friendly handbag may be displayed.

[0930] Through this system, it is possible to provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction.

[0931] (Application example 2)

[0932] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0933] In conventional shopping experiences, it has been difficult to accurately understand a user's purchasing behavior, preferences, and emotional state, and to recommend optimal products based on that. In particular, there is a lack of systems that perform real-time emotion analysis and provide personalized product recommendations, making it difficult to increase user satisfaction.

[0934] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the analysis results. This enables personalized product recommendations in real time that accurately reflect the user's preferences and emotional state.

[0935] "User" refers to an individual consumer or end user of the System.

[0936] "Data source" refers to the original source of information that provides information related to a user, such as a user's purchase history, social media posts, or survey responses.

[0937] "Data cleansing" refers to the process of removing duplicates from collected data, completing incomplete data, and standardizing the format.

[0938] A "profile" refers to a digital data collection that includes a user's characteristics, preferences, and emotional state, generated based on cleansed data.

[0939] "Digital twin" refers to a digital model that is generated based on a user's profile and can simulate the user's behavior and reactions in a virtual space.

[0940] "Simulation" refers to the process of using the generated digital twin to try out reactions and actions in a virtual space in response to a specific scenario.

[0941] "Providing options" refers to the act of analyzing the simulation results and recommending the best proposals and products for the user.

[0942] "Means for recommending products" refers to the system's ability to present products and services suited to the user based on the user's profile and simulation results.

[0943] The present invention relates to a system that analyzes user data and emotions and generates a digital twin. This system provides the user with optimal options based on a simulation in a virtual space. Specific embodiments of the present invention will be described below.

[0944] Data collection

[0945] The server sends API requests to retrieve data from the user's data sources (e.g., purchase history database, social media platform, survey system). The collected data is temporarily stored in data storage. It also uses an emotion engine to collect emotion data from user posts on social media and surveys. The hardware used is a general-purpose server, and the software uses a RESTful API.

[0946] Data Preprocessing

[0947] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds the emotional state to the library. The tool used for data cleansing is the Python pandas library.

[0948] Data profiling

[0949] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if a user frequently purchases luxury handbags and expresses many positive emotions on social media, the characteristics "luxury-oriented" and "positive thinking" can be extracted. Machine learning algorithms (such as the scikit-learn library) are used for profiling.

[0950] Digital Twin Generation

[0951] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. The digital twin is created using Python's object-oriented programming method.

[0952] Building a simulation environment

[0953] The server runs specific simulation scenarios using the digital twin. For example, it sets up a scenario for introducing a new product to the market and observes how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time, enabling more accurate simulations. The simulations are run using Unity and other virtual environment building tools.

[0954] Simulation result analysis and feedback

[0955] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. This analysis is performed using Python's numpy and pandas libraries. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if the user's digital twin responds very positively to a new product, it can recommend an eco-friendly handbag.

[0956] User notification and action support

[0957] The user's device (smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device then provides a product link or purchase button so that the user can take immediate action based on the suggestion, allowing the user to make a quick decision.

[0958] Specific examples and generated AI prompts

[0959] Specific examples

[0960] For example, if a user's purchasing history indicates a preference for luxury goods and they post many positive comments on social media, the system can use this information to create a digital twin. If a new product, an eco-friendly handbag, is introduced and the user's digital twin responds very positively, the system can recommend it directly to the user.

[0961] Example of a generated AI prompt

[0962] "A user posts on social media, 'I love eco-friendly handbags!' Based on this post, please analyze the user's sentiment data and recommend the most suitable products."

[0963] As can be seen, the system of the present invention is able to leverage user data and sentiment data to provide real-time personalized recommendations and enrich the user's shopping experience.

[0964] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0965] Step 1:

[0966] The server retrieves data from the user's data source. Specifically, it sends API requests to a purchase history database, a social media platform, a survey system, etc. The input is the user's identification information, and the output is raw data such as the user's purchase history and social media posts. This data is temporarily stored in data storage.

[0967] Step 2:

[0968] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. The data is organized using the Python pandas library. The input is the raw data acquired in step 1, and the output is the cleansed data.

[0969] Step 3:

[0970] The server generates a user profile based on the cleansed data. Specifically, it compiles preferences and behavioral patterns into a profile based on the user's purchasing history and emotional data. It uses a machine learning algorithm (scikit-learn library). The input is the cleansed data, and the output is a detailed user profile.

[0971] Step 4:

[0972] The server generates a digital twin based on the generated profile. It uses Python object-oriented programming techniques to build a digital twin that reflects the profile. The input is the user profile, and the output is the digital twin.

[0973] Step 5:

[0974] The server runs a specific simulation scenario using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. It uses Unity or other virtual environment building tools. The input is the digital twin, and the output is the simulation result data.

[0975] Step 6:

[0976] The server analyzes the simulation results and calculates the optimal option for the user. It uses Python's numpy and pandas libraries to analyze the simulation results. The input is the simulation result data, and the output is specific recommendations for the user.

[0977] Step 7:

[0978] The device (smartphone or PC) receives notifications from the server and displays them to the user. Notifications are sent via push notifications or in-app messages, allowing users to easily check the information. The input is the recommendation content sent from the server, and the output is the recommended information displayed on the user's screen.

[0979] The above steps enable real-time personalized product recommendations.

[0980] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0981] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0982] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0983] [Fourth embodiment]

[0984] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0985] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0986] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0987] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0988] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0989] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0990] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0991] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0992] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0993] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0994] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0995] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0996] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0997] This invention details a system that collects and analyzes user-related data and generates a digital twin of the user. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is explained below.

[0998] Data collection

[0999] The server first obtains the necessary data from the user's data source. Data sources include the user's purchase history, social media activity history, survey responses, etc. For example, the server accesses a purchase history database via an API and obtains a list of products that User A has purchased in the past.

[1000] Data Preprocessing

[1001] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in missing values, and standardizing the format. This ensures the quality of the data.

[1002] Data profiling

[1003] Based on the cleansed data, the server generates a user profile, which includes the user's characteristics, preferences, behavioral patterns, etc. For example, if user A frequently purchases high-quality handbags, the characteristic "luxury-oriented" is extracted.

[1004] Digital Twin Generation

[1005] Based on the generated profile, the server creates a digital twin of the user. The digital twin is placed in a virtual space and also reflects the user's internal characteristics. For example, User A's digital twin has the characteristics of being "luxury-oriented" and "fashion-conscious."

[1006] Building a simulation environment

[1007] The server uses the digital twins to run specific simulation scenarios, such as a new product market launch scenario, and observes how the digital twins react. Through this simulation, the server determines whether many digital twins are interested in the new product.

[1008] Simulation result analysis and feedback

[1009] The server analyzes the data obtained from the simulation and calculates the optimal option for each user. For example, if User A's digital twin shows interest in a new product, the server will recommend, "An eco-friendly handbag would be perfect for you."

[1010] User notification and action support

[1011] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[1012] Through the above process, this system can provide optimal suggestions that match the user's characteristics and increase satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each user, and providing the user with the optimal options.

[1013] The processing flow will be explained below.

[1014] Step 1:

[1015] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user, and temporarily stores the data returned by the API in data storage.

[1016] Step 2:

[1017] The server cleanses the collected data, specifically removing duplicates, filling in incomplete data, correcting outliers, and standardizing the data format to make it easier to analyze.

[1018] Step 3:

[1019] The server then uses the cleansed data to profile the user. This process involves using machine learning algorithms (such as clustering and decision trees) to analyze the user's behavioral patterns and preferences and extract detailed characteristics, which then create a user profile.

[1020] Step 4:

[1021] The server then creates a digital twin based on the generated profile, which reflects the user's personality and behavioral characteristics and is placed in a virtual space.

[1022] Step 5:

[1023] The server sets up a simulation scenario and places the digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The simulation is run multiple times and the reaction patterns are recorded.

[1024] Step 6:

[1025] The server analyzes the results of the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server clarifies the user's preferences and behavioral trends and makes specific suggestions.

[1026] Step 7:

[1027] The server then sends notifications to each user based on the analysis results, for example, recommending a new eco-friendly handbag to the user.

[1028] Step 8:

[1029] The device receives notifications from the server and displays them to the user. Notifications are delivered to the user as push notifications or in-app messages, providing information in a visually easy-to-understand format.

[1030] Step 9:

[1031] The user checks the notification from the device and takes action based on the suggested option, for example, clicking on a purchase link for the suggested product and actually purchasing the product.

[1032] By going through these steps, the system can provide the user with the best options and increase user satisfaction.

[1033] Example 1

[1034] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1035] In today's digital society, there is a demand for personalized services based on individual user preferences and behavioral patterns. However, despite the vast amount of user data available, systems that can efficiently collect and analyze this data and provide optimal suggestions to users have not yet been fully established. Furthermore, further improvements are needed in methods that use digital twins to reproduce user characteristics in virtual space and provide real-time feedback based on the simulation results. Therefore, there is a need for new systems that can solve these issues and improve user satisfaction.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1037] In this invention, the server includes means for acquiring data from a user information source, means for cleaning the acquired data, means for generating user characteristic information based on the cleaned data, means for generating a virtual user model based on the generated characteristic information, means for performing a simulation using the generated virtual user model, means for analyzing the simulation results and providing the user with an optimal selection, and means for notifying the user, thereby making it possible to provide personalized suggestions based on the user's characteristics in real time.

[1038] "User information sources" refers to multiple databases and information systems that store data related to the user.

[1039] "Data cleaning" is the process of correcting and removing duplicates, missing data, improper formats, etc. from acquired data, and preparing it in a form suitable for analysis.

[1040] "User characteristic information" is data that indicates characteristics such as user preferences and behavioral patterns, extracted from the cleaned data.

[1041] A "virtual user model" is a digital twin that is generated based on the user's characteristic information and reproduces the user's behavior and reactions in a virtual space.

[1042] "Simulation" is the process of using virtual user models to virtually perform and observe reactions to specific scenarios.

[1043] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and deriving the optimal choices and actions for the user.

[1044] "Notification" refers to the act of sending information to users via means such as push notifications or in-app messages to inform them of the analysis results.

[1045] This invention is a system that collects user data, generates a digital twin, performs simulations, and presents optimal options to the user based on the results. The program processing of this system will be described in detail below.

[1046] First, the server obtains data from the user's information sources. These information sources include a purchase history database, social media activity history, and survey results. The server accesses these data sources through APIs to obtain the necessary data. For example, the server can obtain "User A's purchase history for the past 12 months."

[1047] Next, the server cleans the acquired data. Because the data often contains duplicates and missing data, these are deleted and supplemented, and the data format is standardized. Specific actions at this stage include deleting duplicate data, supplementing missing values ​​with appropriate values, and standardizing the date format to "YYYY-MM-DD."

[1048] The server then generates user characteristic information based on the cleaned data. This characteristic information includes the user's preferences and behavioral patterns. For example, the characteristic "luxury-oriented" can be identified from the information that "User A has purchased high-quality handbags five times in the past six months."

[1049] Next, the server generates a virtual user model (digital twin) based on the generated characteristic information. To do this, a machine learning model is used, and the characteristic information is used as input data to build a user model that is reproduced in virtual space. Specifically, a neural network is built using a machine learning framework such as TensorFlow, and a digital twin that reflects the user's characteristic information is generated.

[1050] The server then runs a simulation using the generated digital twin. For example, it sets up a market introduction scenario for a new product and observes how the digital twin responds to that scenario. This simulation allows the server to collect data such as how much interest the digital twin shows in the new product.

[1051] After obtaining the simulation results, the server analyzes them and implements measures to provide the user with the optimal choice. For example, if the digital twin shows high interest in a new product, the server will recommend to the user, "An eco-friendly handbag would be perfect for you."

[1052] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, and provides a product link or purchase button so that the user can take immediate action based on the recommendation. For example, it can say, "Show a purchase link for an eco-friendly handbag."

[1053] This system performs detailed profiling and simulations based on user data, and makes personalized suggestions in real time, thereby increasing user satisfaction.

[1054] Example prompt sentence:

[1055] Create a fashion-oriented digital twin based on purchase history, social media data, and survey results. Then, simulate a market introduction scenario for a new product, "Eco-Friendly Handbags," and recommend the product to User A based on the reaction shown by the digital twin.

[1056] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1057] Step 1: Data collection

[1058] The server obtains data from user information sources, including purchase history databases, social media activity history, survey results, and other data sources.

[1059] Input: API request to data source

[1060] Specific behavior:

[1061] The server sends a request to an API endpoint.

[1062] For example, obtain JSON data containing "User A's purchase history for the past 12 months."

[1063] Output: Raw data obtained (e.g., purchase history in JSON format)

[1064] Step 2: Data Preprocessing

[1065] The server then cleans the data it receives, which is the process of correcting and removing duplicates, missing data, improper formats, etc.

[1066] Input: Raw data (e.g., purchase history in JSON format)

[1067] Specific behavior:

[1068] The server detects and removes duplicate data.

[1069] To impute missing values, fill in the missing parts with the appropriate values.

[1070] Standardize date formats, currency units, etc. Example: Convert to "YYYY-MM-DD" format.

[1071] Output: Cleaned data

[1072] Step 3: Data profiling

[1073] The server generates user characteristic information based on the cleaned data, which includes the user's preferences and behavioral patterns.

[1074] Input: Cleaned data

[1075] Specific behavior:

[1076] The server analyzes the purchase history data and extracts the user's preferences.

[1077] For example, the characteristic "luxury-oriented" can be extracted from the information that "User A has purchased high-quality handbags five times in the past six months."

[1078] Output: User characteristics information

[1079] Step 4: Generate the digital twin

[1080] The server generates a virtual user model based on the generated characteristic information, which is called a digital twin.

[1081] Input: User characteristics information

[1082] Specific behavior:

[1083] The server inputs the characteristic information into the machine learning model.

[1084] For example, TensorFlow is used to build a neural network and generate a virtual user model.

[1085] Output: The generated digital twin

[1086] Step 5: Building the simulation environment

[1087] The server uses the digital twin to set up and run specific simulation scenarios.

[1088] Input: Digital twin, simulation scenario

[1089] Specific behavior:

[1090] The server sets up a market introduction scenario for a new product.

[1091] Simulate how your digital twin will react based on scenarios.

[1092] Output: Simulation results

[1093] Step 6: Analysis and feedback of simulation results

[1094] The server analyzes the simulation results and provides the user with the optimal options.

[1095] Input: Simulation results

[1096] Specific behavior:

[1097] The server analyzes the simulation data and derives optimal suggestions for the user.

[1098] For example, if the digital twin shows high interest in a new product, it will recommend, "This eco-friendly handbag is perfect for you."

[1099] Output: Optimal recommendations for the user

[1100] Step 7: Notify users and support their actions

[1101] The device receives notifications from the server and displays them to the user, either through push notifications or in-app messages.

[1102] Input: Notification from the server

[1103] Specific behavior:

[1104] The device displays a push notification.

[1105] For example, "Show links to buy eco-friendly handbags."

[1106] Output: Notify user and display purchase link

[1107] (Application example 1)

[1108] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1109] In modern online shopping, inappropriate product recommendations to users can lead to a decline in user satisfaction. To make appropriate product recommendations, it is necessary to fully understand the user's purchasing history and interests and make personalized recommendations based on that. However, current systems often lack the accuracy of recommendations due to insufficient user profiling and digital twin generation.

[1110] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1111] In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the simulation results, thereby enabling highly accurate product recommendations based on the user's interests.

[1112] "User data sources" refers to information sources such as a user's purchasing history, social media activity history, and survey responses.

[1113] "Means for obtaining data" refers to the method by which the server gathers the required data from the user's data source.

[1114] "Data cleansing" refers to the process of removing duplicates from acquired data, filling in missing values, and standardizing the format.

[1115] "Means for generating a user profile" refers to technology that identifies and organizes a user's characteristics, preferences, and behavioral patterns based on cleansed data.

[1116] A "digital twin" refers to a digital model that is generated in a virtual space based on a user's profile and reflects the user's internal characteristics.

[1117] "Means for performing simulation" refers to a method of using the generated digital twin to execute specific scenarios in a virtual space and observe the reactions.

[1118] "Means for analyzing the simulation results and providing the user with the optimal option" refers to a method for analyzing the data obtained from the simulation and calculating the optimal option for the user.

[1119] "Means for recommending products" refers to a mechanism that presents the most suitable products to users based on the results of the simulation.

[1120] This invention is a system that collects and analyzes data related to a user, generates a digital twin, and recommends optimal products to the user. Here, as a specific embodiment, the configuration and operation of this system will be described.

[1121] System configuration

[1122] This system consists of the following main components:

[1123] Server: Collects data, cleanses it, creates profiles, generates digital twins, performs simulations, and performs analysis.

[1124] Device: Provides notifications and action support to users. Devices include smartphones, PCs, etc.

[1125] Hardware

[1126] The main hardware required to realize the system includes:

[1127] Cloud server: Data storage and processing on the cloud

[1128] User device: smartphone or PC

[1129] software

[1130] The software includes the following:

[1131] Data collection module: Acquires purchase history, social media activity history, and survey responses via API

[1132] Data cleansing module: remove duplicates, impute missing values, and unify formats

[1133] Profile generation module: Analyzes user characteristics, preferences, and behavioral patterns

[1134] Digital twin generation module: Generates a digital model in a virtual space based on the user's characteristics

[1135] Simulation module: Run specific scenarios and observe the reactions

[1136] Analysis module: Analyzes the simulation results and calculates the best options for the user

[1137] Notification and support module: Notify users of recommended products and support their purchasing actions

[1138] Operation flow

[1139] 1. Data collection: The server obtains users' purchase history, social media activity history, survey responses, etc. through the API.

[1140] 2. Data cleansing: The server removes duplicates from the retrieved data, fills in missing values, and standardizes the format.

[1141] 3. Profile generation: The server analyzes the user's characteristics and preferences based on the cleansed data and generates a profile.

[1142] 4. Digital twin generation: The server generates a digital twin in the virtual space based on the generated profile, creating a digital model that reflects the user's characteristics.

[1143] 5. Simulation: The server uses the digital twin to run a specific scenario (e.g., introducing a new product to the market) and observe the reaction.

[1144] 6. Analysis and feedback: The server analyzes the simulation results and calculates the best product and service options for the user.

[1145] 7. Notification and action support: The device notifies the user of the recommendation results from the server and displays links and buttons so that the user can take immediate action.

[1146] Specific examples

[1147] For example, for a user with user ID 1, the system operates as follows: The server collects the user's purchase history, social media activity history, and survey responses via API and cleanses them. The server then creates a profile of the user's characteristics and preferences, and generates a digital twin in a virtual space based on that profile. Next, it runs a specific simulation scenario and observes the digital twin's reaction. Based on the results, it recommends products such as "Luxury handbags" and "Designer shoes" to the user, and notifies the user's device, allowing the user to immediately purchase these products.

[1148] Prompt Sentence Examples

[1149] "For user ID 1, please collect data on his / her purchasing history and social media activity, and generate a digital twin. Then, please run a simulation to recommend new fashion items, and notify the user of the recommendation results."

[1150] This invention makes it possible to recommend products with high accuracy based on the user's interests, and is expected to improve user satisfaction.

[1151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1152] Step 1:

[1153] The server retrieves data from the user's data source. The input in this step is the user ID, and the output is a set of data such as purchase history, social media activity history, and survey responses. Specifically, these data sources are accessed through APIs to collect user-specific data.

[1154] Step 2:

[1155] The server cleanses the acquired data. The input in this step is the data acquired in the previous step, and the output is cleansed, high-quality data. Specifically, it removes duplicate data, fills in missing values, and standardizes the data format. This results in data suitable for analysis.

[1156] Step 3:

[1157] The server generates a user profile based on the cleansed data. The input in this step is the cleansed data, and the output is profile data that shows the user's characteristics, preferences, and behavioral patterns. Specifically, characteristics such as whether the user prefers high-priced items are extracted from purchase history and social media activity.

[1158] Step 4:

[1159] The server generates a digital twin based on the generated profile. The input in this step is the user profile, and the output is a digital twin placed in a virtual space. Specifically, a virtual model reflecting the user's interests and behavioral patterns is generated and placed in the virtual space.

[1160] Step 5:

[1161] The server runs a simulation using the generated digital twin. The inputs in this step are the digital twin and the simulation scenario, and the output is the simulation results. Specifically, for example, a scenario for introducing a new product to the market is set up, and how the digital twin reacts to that product is observed.

[1162] Step 6:

[1163] The server analyzes the simulation results and provides the user with the optimal options. The input in this step is the simulation results, and the output is recommendation data for the user. Specifically, if the digital twin shows interest in a new product, that product is presented to the user as a recommendation.

[1164] Step 7:

[1165] The device provides the notification from the server to the user. The input in this step is the recommendation data, and the output is a notification and action link for the user. Specifically, a product link and purchase button are displayed via push notification or in-app message, allowing the user to easily check the information and take action.

[1166] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1167] This invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides the user with optimal options based on the results. The specific processing of this program is described below.

[1168] Data collection

[1169] The server sends API requests to the user's data sources (e.g., purchase history databases, social media platforms, survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. In addition, an emotion engine is used to collect emotion data from user posts on social media and in surveys.

[1170] Data Preprocessing

[1171] Since the acquired data is often incomplete or unsuitable for analysis, the server cleanses the data by removing duplicates, filling in incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds their emotional state to the library.

[1172] Data profiling

[1173] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the characteristics of "luxury-oriented" and "positive thinking" are extracted.

[1174] Digital Twin Generation

[1175] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. For example, User A's digital twin has the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[1176] Building a simulation environment

[1177] The server uses the digital twin to run specific simulation scenarios, such as setting up a market launch scenario for a new product, and observing how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations.

[1178] Simulation result analysis and feedback

[1179] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend, "An eco-friendly handbag is perfect for you."

[1180] User notification and action support

[1181] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device also provides product links and purchase buttons so that the user can take immediate action based on the recommendation. For example, a link to purchase an eco-friendly handbag is displayed.

[1182] Through the above process, this system can provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction. A specific example is the case where User A purchased a new product and his satisfaction increased. The present invention has the effect of realizing highly accurate profiling and simulation for each individual user, and providing the user with the optimal options.

[1183] The processing flow will be explained below.

[1184] Step 1:

[1185] The server sends API requests to user data sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The data returned from the API is temporarily stored in data storage. At the same time, an emotion engine is used to collect emotion data from social media and survey text.

[1186] Step 2:

[1187] The server cleanses the collected data, eliminating duplicates, filling in incomplete data, and standardizing formats. An emotion engine also extracts the user's emotional state through text analysis and adds it to the cleansed data.

[1188] Step 3:

[1189] The server uses machine learning algorithms (such as clustering and decision trees) to generate a user profile based on the cleansed data. The profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and displays many positive emotions, the characteristics "luxury-oriented" and "positive thinking" can be derived.

[1190] Step 4:

[1191] The server generates a digital twin of the user based on the generated profile. The digital twin simulates the user's personality, behavioral characteristics, and emotional state and is placed in a virtual space. User A's digital twin has characteristics such as "luxury-oriented," "fashion-conscious," and "positive thinking."

[1192] Step 5:

[1193] The server sets up a simulation scenario and places the generated digital twin into that scenario. For example, it sets up a scenario for introducing a new product to the market and observes the digital twin's reaction. The emotion engine monitors the digital twin's emotional state in real time and records in detail how the user feels within the scenario.

[1194] Step 6:

[1195] The server analyzes the results of the simulation and calculates the optimal option for the user. The analysis makes specific suggestions based on the digital twin's behavioral patterns and emotional transitions. For example, if User A's digital twin reacts very positively to a new product, the server will recommend something like, "This eco-friendly handbag is perfect for you."

[1196] Step 7:

[1197] The server then sends notifications to each user based on the analysis results. Notifications can be sent via push notifications or in-app messages, and include detailed information and links about the recommended products.

[1198] Step 8:

[1199] The device receives notifications from the server and displays them to the user. An intuitive interface is provided so that users can easily check the notifications. For example, purchase links and detailed information are displayed in the form of easy-to-click buttons.

[1200] Step 9:

[1201] The user checks the notification from the device and takes action based on the options presented, for example, clicking on a link in the notification and purchasing the recommended product.

[1202] Through these steps, the system can provide users with optimal suggestions that match their characteristics and emotions, improving satisfaction.

[1203] Example 2

[1204] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1205] In recent years, there has been a demand for personalized services based on users' preferences, personalities, and emotions, but the challenge is that it is difficult to integrate diverse user data and provide effective information. In particular, conventional systems are unable to adequately analyze emotional data, generate digital twins, or analyze simulation results, making it difficult to provide users with optimal options.

[1206] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1207] In this invention, the server includes means for acquiring data from a user's information source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, means for collecting and preprocessing data, means for collecting and analyzing emotional data using an emotion analysis engine, means for setting and executing a specific simulation scenario, and means for analyzing the simulation data and calculating optimal options. This makes it possible to integrate a variety of user data, achieve highly accurate profiling and simulation including emotional data, and provide the user with optimal options.

[1208] A "user" is an individual or organization that uses the system to receive services or information.

[1209] A "source" is an external database or platform that provides data relevant to a user.

[1210] "Data cleansing" is the process of removing duplicate and incomplete data from acquired data and standardizing the data format.

[1211] A "user profile" is information that represents a user's characteristics, preferences, behavioral patterns, and emotional state, generated based on cleansed data.

[1212] A "digital twin" is a digital representation of a user that is generated in a virtual space based on the user's real-world profile.

[1213] "Simulation" is the process of using a digital twin to recreate a specific scenario in a virtual environment and observe the results.

[1214] "Analysis of simulation results" is the process of analyzing the data obtained from the simulation and calculating the optimal options for the user.

[1215] An "emotion analysis engine" is software or an algorithm for analyzing a user's emotions from text or statements.

[1216] A "simulation scenario" is an item that refers to a specific situation or condition that is set when a simulation is performed.

[1217] The present invention relates to a system that analyzes user-related data and user emotions to generate a digital twin. This system performs simulations in a virtual space and provides optimal options to the user based on the results.

[1218] Data collection

[1219] The server sends API requests to user information sources (such as purchase history databases, social media platforms, and survey systems) to collect data related to each user. The collected data is temporarily stored in data storage. A sentiment analysis engine is also used to collect emotional data from user posts on social media and in surveys. The hardware used for this is a high-performance server, and software such as OpenAI and IBM Watson is used for sentiment analysis.

[1220] Data Preprocessing

[1221] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. This process uses the Python Pandas library. A sentiment analysis engine analyzes text from social media and surveys and adds the user's emotional state to the library.

[1222] Data profiling

[1223] Based on the cleansed data, the server creates a user profile. This profile includes the user's characteristics, preferences, behavioral patterns, and emotional state. For example, if User A frequently purchases high-quality handbags and expresses many positive emotions, the server extracts the characteristics of "luxury-oriented" and "positive thinking." This profiling is performed using a machine learning model (scikit-learn).

[1224] Digital Twin Generation

[1225] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is placed in a virtual space. This process uses virtual reality software such as Unity or Unreal Engine. For example, User A's digital twin would have the characteristics of being "luxury-oriented," "fashion-conscious," and "positive-thinking."

[1226] Building a simulation environment

[1227] The server runs specific simulation scenarios using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. An emotion analysis engine monitors the digital twin's emotional state in real time during the simulation, enabling more accurate simulations. The simulations are performed using simulation software such as MATLAB and Simulink.

[1228] Simulation result analysis and feedback

[1229] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. By analyzing the simulation data, the user's preferences, behavioral tendencies, and emotional state can be clarified and specific suggestions can be made. For example, if User A's digital twin has a very positive reaction to a new product, the server will recommend, "An eco-friendly handbag would be perfect for you." This analysis is performed using Python's NumPy and SciPy libraries.

[1230] User notification and action support

[1231] The device (user's smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message. To make it easy for the user to check the information, the device provides a product link or purchase button so that the user can take immediate action based on the suggestion. For example, a purchase link for an eco-friendly handbag is displayed. This notification is sent using a notification service such as Firebase Cloud Messaging (FCM).

[1232] This system can provide optimal suggestions that match the user's characteristics and emotions, increasing satisfaction. A concrete example is the case where User A purchased a new product and his satisfaction increased.

[1233] Examples of prompt statements

[1234] "Please provide a step-by-step guide to create a program that analyzes emotions from users' social media posts and builds a recommendation system based on the results."

[1235] "Please explain in detail the algorithm used to generate a user's digital twin using purchase history data and social media sentiment data."

[1236] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1237] Step 1: Data collection

[1238] The server sends API requests to user information sources (e.g., purchase history databases, social media platforms, and survey systems) to collect data related to each user. The input is the user's ID and search query, and the output is raw data in JSON format. Specifically, the server uses the Python requests library to send requests to the API and temporarily saves the retrieved data in data storage. It also calls a sentiment analysis engine to collect emotional data from social media and surveys.

[1239] Step 2: Cleanse the data

[1240] The server cleanses the acquired data. The input is the raw data collected in step 1, and the output is cleansed data with duplicate data removed, incomplete data completed, and a unified format. Specifically, the server uses the Python Pandas library to create a data frame, remove duplicate data, and complete incomplete data. The sentiment analysis engine also analyzes the data and adds the emotional state to the library.

[1241] Step 3: Data profiling

[1242] The server profiles users based on the cleansed data. The input is the cleansed data, and the output is a profile that includes the user's characteristics, preferences, behavioral patterns, and emotional state. Specifically, the server analyzes the data using a machine learning model (scikit-learn) to extract user characteristics. For example, if a particular user frequently purchases high-quality products and expresses a lot of positive emotions, the server can profile the user's characteristics based on that.

[1243] Step 4: Generate the digital twin

[1244] The server generates a digital twin based on the generated profile. The input is the user's profile, and the output is a digital twin placed in a virtual space. Specifically, the server generates the digital twin using virtual reality software such as Unity or Unreal Engine. The digital twin reflects the user's personality, behavioral characteristics, and emotional state, and is capable of acting in the virtual space.

[1245] Step 5: Building the simulation environment

[1246] The server runs a specific simulation scenario using the digital twin. The input is the settings for the specific simulation scenario, and the output is the simulation data. Specifically, the server uses simulation software such as MATLAB or Simulink to set up and run the simulation scenario. The emotion analysis engine monitors the emotional state of the digital twin in real time, enabling more accurate simulations.

[1247] Step 6: Analysis and feedback of simulation results

[1248] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. The input is the simulation data, and the output is a specific recommendation for the user. Specifically, the server analyzes the simulation data using Python's NumPy and SciPy libraries to clarify the user's preferences, behavioral tendencies, and emotional state. For example, if User A's digital twin reacts positively to a new product, the server will recommend, "This eco-friendly handbag is perfect for you."

[1249] Step 7: Notify users and support their actions

[1250] The device (user's smartphone or PC) receives notifications from the server and displays them to the user. The input is the notification data from the server, and the output is the notification message that is displayed to the user. Specifically, the device receives push notifications using services such as Firebase Cloud Messaging (FCM) and displays them as in-app messages. Actions such as product links and purchase buttons are provided so that users can easily check the information. For example, a purchase link for an eco-friendly handbag may be displayed.

[1251] Through this system, it is possible to provide optimal suggestions that match the user's characteristics and emotions, thereby increasing satisfaction.

[1252] (Application example 2)

[1253] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1254] In conventional shopping experiences, it has been difficult to accurately understand a user's purchasing behavior, preferences, and emotional state, and to recommend optimal products based on that. In particular, there is a lack of systems that perform real-time emotion analysis and provide personalized product recommendations, making it difficult to increase user satisfaction.

[1255] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a user's data source, means for cleansing the acquired data, means for generating a user profile based on the cleansed data, means for generating a digital twin based on the generated profile, means for performing a simulation using the generated digital twin, means for analyzing the simulation results and providing the user with optimal options, and means for recommending products to the user based on the analysis results. This enables personalized product recommendations in real time that accurately reflect the user's preferences and emotional state.

[1256] "User" refers to an individual consumer or end user of the System.

[1257] "Data source" refers to the original source of information that provides information related to a user, such as a user's purchase history, social media posts, or survey responses.

[1258] "Data cleansing" refers to the process of removing duplicates from collected data, completing incomplete data, and standardizing the format.

[1259] A "profile" refers to a digital data collection that includes a user's characteristics, preferences, and emotional state, generated based on cleansed data.

[1260] "Digital twin" refers to a digital model that is generated based on a user's profile and can simulate the user's behavior and reactions in a virtual space.

[1261] "Simulation" refers to the process of using the generated digital twin to try out reactions and actions in a virtual space in response to a specific scenario.

[1262] "Providing options" refers to the act of analyzing the simulation results and recommending the best proposals and products for the user.

[1263] "Means for recommending products" refers to the system's ability to present products and services suited to the user based on the user's profile and simulation results.

[1264] The present invention relates to a system that analyzes user data and emotions and generates a digital twin. This system provides the user with optimal options based on a simulation in a virtual space. Specific embodiments of the present invention will be described below.

[1265] Data collection

[1266] The server sends API requests to retrieve data from the user's data sources (e.g., purchase history database, social media platform, survey system). The collected data is temporarily stored in data storage. It also uses an emotion engine to collect emotion data from user posts on social media and surveys. The hardware used is a general-purpose server, and the software uses a RESTful API.

[1267] Data Preprocessing

[1268] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. During this process, the emotion engine also analyzes the user's emotional data and adds the emotional state to the library. The tool used for data cleansing is the Python pandas library.

[1269] Data profiling

[1270] Based on the cleansed data, the server creates a user profile. The profile includes the user's characteristics, preferences, behavioral patterns, and even emotional state. For example, if a user frequently purchases luxury handbags and expresses many positive emotions on social media, the characteristics "luxury-oriented" and "positive thinking" can be extracted. Machine learning algorithms (such as the scikit-learn library) are used for profiling.

[1271] Digital Twin Generation

[1272] Based on the generated profile, the server creates a digital twin of the user. The digital twin reflects the user's personality, behavioral characteristics, and even emotional state, and is placed in a virtual space. The digital twin is created using Python's object-oriented programming method.

[1273] Building a simulation environment

[1274] The server runs specific simulation scenarios using the digital twin. For example, it sets up a scenario for introducing a new product to the market and observes how the digital twin reacts. The emotion engine monitors the digital twin's emotional state in real time, enabling more accurate simulations. The simulations are run using Unity and other virtual environment building tools.

[1275] Simulation result analysis and feedback

[1276] The server analyzes the data obtained from the simulation and calculates the optimal option for the user. This analysis is performed using Python's numpy and pandas libraries. By analyzing the simulation data, the server can clarify the user's preferences, behavioral tendencies, and emotional state, and make specific suggestions. For example, if the user's digital twin responds very positively to a new product, it can recommend an eco-friendly handbag.

[1277] User notification and action support

[1278] The user's device (smartphone or PC) receives the notification from the server and displays it to the user. The notification is sent via push notification or in-app message, allowing the user to easily check the information. The device then provides a product link or purchase button so that the user can take immediate action based on the suggestion, allowing the user to make a quick decision.

[1279] Specific examples and generated AI prompts

[1280] Specific examples

[1281] For example, if a user's purchasing history indicates a preference for luxury goods and they post many positive comments on social media, the system can use this information to create a digital twin. If a new product, an eco-friendly handbag, is introduced and the user's digital twin responds very positively, the system can recommend it directly to the user.

[1282] Example of a generated AI prompt

[1283] "A user posts on social media, 'I love eco-friendly handbags!' Based on this post, please analyze the user's sentiment data and recommend the most suitable products."

[1284] As can be seen, the system of the present invention is able to leverage user data and sentiment data to provide real-time personalized recommendations and enrich the user's shopping experience.

[1285] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1286] Step 1:

[1287] The server retrieves data from the user's data source. Specifically, it sends API requests to a purchase history database, a social media platform, a survey system, etc. The input is the user's identification information, and the output is raw data such as the user's purchase history and social media posts. This data is temporarily stored in data storage.

[1288] Step 2:

[1289] The server cleanses the acquired data by removing duplicates, completing incomplete data, and standardizing the format. The data is organized using the Python pandas library. The input is the raw data acquired in step 1, and the output is the cleansed data.

[1290] Step 3:

[1291] The server generates a user profile based on the cleansed data. Specifically, it compiles preferences and behavioral patterns into a profile based on the user's purchasing history and emotional data. It uses a machine learning algorithm (scikit-learn library). The input is the cleansed data, and the output is a detailed user profile.

[1292] Step 4:

[1293] The server generates a digital twin based on the generated profile. It uses Python object-oriented programming techniques to build a digital twin that reflects the profile. The input is the user profile, and the output is the digital twin.

[1294] Step 5:

[1295] The server runs a specific simulation scenario using the digital twin. For example, it sets up a market launch scenario for a new product and observes how the digital twin reacts. It uses Unity or other virtual environment building tools. The input is the digital twin, and the output is the simulation result data.

[1296] Step 6:

[1297] The server analyzes the simulation results and calculates the optimal option for the user. It uses Python's numpy and pandas libraries to analyze the simulation results. The input is the simulation result data, and the output is specific recommendations for the user.

[1298] Step 7:

[1299] The device (smartphone or PC) receives notifications from the server and displays them to the user. Notifications are sent via push notifications or in-app messages, allowing users to easily check the information. The input is the recommendation content sent from the server, and the output is the recommended information displayed on the user's screen.

[1300] The above steps enable real-time personalized product recommendations.

[1301] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1302] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1303] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1304] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1305] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1306] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1307] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1308] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1309] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1310] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1311] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1312] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1313] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1314] 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.

[1315] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1316] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1317] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1318] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1319] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1320] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1321] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1322] The following is further disclosed regarding the above embodiment.

[1323] (Claim 1)

[1324] a means for obtaining data from a user data source;

[1325] a means for cleansing the acquired data;

[1326] means for generating a profile of the user based on the cleansed data;

[1327] means for generating a digital twin based on the generated profile;

[1328] A means for performing a simulation using the generated digital twin;

[1329] A means of analyzing the simulation results and providing users with the best options;

[1330] A system including:

[1331] (Claim 2)

[1332] 10. The system of claim 1, further comprising a means for notifying a user.

[1333] (Claim 3)

[1334] 10. The system of claim 1, wherein the simulation relates to a market introduction of a new product.

[1335] "Example 1"

[1336] (Claim 1)

[1337] a means for obtaining data from a user source;

[1338] means for cleaning the acquired data;

[1339] means for generating user characteristic information based on the cleaned data;

[1340] means for generating a virtual user model based on the generated characteristic information;

[1341] means for performing a simulation using the generated virtual user model;

[1342] A means for analyzing the simulation results and providing the user with the optimal selection;

[1343] A system including:

[1344] (Claim 2)

[1345] 10. The system of claim 1, further comprising means for providing a notification to a user.

[1346] (Claim 3)

[1347] 10. The system of claim 1, wherein the simulation relates to a market introduction of a new product.

[1348] "Application Example 1"

[1349] (Claim 1)

[1350] a means for obtaining data from a user data source;

[1351] a means for cleansing the acquired data;

[1352] means for generating a profile of the user based on the cleansed data;

[1353] means for generating a digital twin based on the generated profile;

[1354] A means for performing a simulation using the generated digital twin;

[1355] A means of analyzing the simulation results and providing users with the best options;

[1356] means for recommending products to users based on the simulation results;

[1357] A system including:

[1358] (Claim 2)

[1359] 10. The system of claim 1, further comprising a means for notifying a user.

[1360] (Claim 3)

[1361] 10. The system of claim 1, wherein the simulation relates to a market introduction of a new product.

[1362] "Example 2: Combining Emotion Engines"

[1363] (Claim 1)

[1364] a means for obtaining data from a user source;

[1365] a means for cleansing the acquired data;

[1366] means for generating a profile of the user based on the cleansed data;

[1367] means for generating a digital twin based on the generated profile;

[1368] A means for performing a simulation using the generated digital twin;

[1369] A means of analyzing the simulation results and providing users with the best options;

[1370] a means for data collection and pre-processing;

[1371] means for collecting and analyzing emotion data using an emotion analysis engine;

[1372] A means for setting up and running specific simulation scenarios;

[1373] A means of analyzing simulation data and calculating optimal options;

[1374] A system including:

[1375] (Claim 2)

[1376] 10. The system of claim 1, further comprising a means for notifying a user.

[1377] (Claim 3)

[1378] 10. The system of claim 1, wherein the simulation relates to a market introduction of a new product.

[1379] "Application example 2 when combining emotion engines"

[1380] (Claim 1)

[1381] a means for obtaining data from a user data source;

[1382] a means for cleansing the acquired data;

[1383] means for generating a profile of the user based on the cleansed data;

[1384] means for generating a digital twin based on the generated profile;

[1385] A means for performing a simulation using the generated digital twin;

[1386] A means of analyzing the simulation results and providing users with the best options;

[1387] A means for recommending products to users based on the analysis results;

[1388] A system including:

[1389] (Claim 2)

[1390] 10. The system of claim 1, further comprising a means for notifying a user.

[1391] (Claim 3)

[1392] 10. The system of claim 1, wherein the simulation relates to a market introduction of a new product. [Explanation of symbols]

[1393] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for obtaining data from a user data source; a means for cleansing the acquired data; means for generating a profile of the user based on the cleansed data; means for generating a digital twin based on the generated profile; A means for performing a simulation using the generated digital twin; A means of analyzing the simulation results and providing users with the best options; A system including:

2. 10. The system of claim 1, further comprising a means for notifying a user.

3. The system of claim 1 , wherein the simulation relates to a new product introduction.

Images