system

Abstract

We provide the system. [Solution] Information gathering means for collecting publicly available information from users, An analytical method that analyzes collected public information to identify users' hobbies and preferences, A proxy generation means that generates a virtual proxy for a user based on their identified hobbies and preferences, A means by which a virtual agent operates within a virtual environment and acquires additional data, A report generation means that analyzes the acquired additional data and generates a report, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, various data of users have been accumulated online in the digital environment. However, it is still difficult for companies to collect and utilize these data with high quality and efficiency. In particular, accurately identifying users' hobbies and preferences from public data and performing detailed behavioral analysis based on them is complex, and there is a problem that sufficient accuracy and efficiency cannot be ensured by conventional methods.

Means for Solving the Problems

[0005] This invention provides a system that generates a virtual surrogate for a user by collecting and analyzing publicly available user information to identify their hobbies and preferences. This virtual surrogate operates within a virtual environment, interacting with other virtual surrogates to acquire additional data, and analyzing this data to detect detailed user behavior patterns and changes in interests. This invention enables companies to efficiently acquire high-quality data and support strategic decision-making based on user needs.

[0006] "Information gathering means" refers to a function or device for collecting publicly available information from users.

[0007] "Analysis means" refers to a function or device used to analyze collected information and identify the user's hobbies and preferences.

[0008] "Proxy generation means" refers to a function or device for generating a virtual proxy for a user based on analyzed hobbies and preferences.

[0009] "Activation means" refers to a function or device for operating a virtual agent within a virtual environment and acquiring additional data.

[0010] "Report generation means" refers to a function or device for analyzing data acquired by a virtual agent and generating a report.

[0011] A "virtual proxy" is a program or entity that is generated based on the user's hobbies and preferences and operates within a virtual environment.

[0012] A "virtual environment" is a simulated space or platform built on a computer for virtual agents to operate.

[0013] "Changes in interest" refers to the phenomenon or tendency of users' interests changing over time. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The present invention is implemented as a series of programs and related processes in a system built on a cloud environment. Its specific form is described below.

[0036] First, the server automatically collects users' publicly available information via the internet. This information includes text posted by users on social media, public profile data, and public follower lists. The collected information is securely stored in the server's data storage.

[0037] Next, the server feeds the collected information into an analysis engine, which uses natural language processing technology to analyze the text data. This analysis allows the server to identify the user's hobbies and preferences. For example, if a user frequently posts words like "travel" or "cooking," these are classified as the user's interests.

[0038] Based on the analysis results, the server programmatically generates a virtual proxy that resembles the user. This virtual proxy is designed to replicate the user's hobbies and preferences, and for example, it operates within the virtual environment as a "travel-loving agent."

[0039] The generated virtual agent begins its activities in a virtual environment on the server. These activities include participating in forums aligned with the user's interests and communicating with other virtual agents. Over time, the virtual agent absorbs information within the virtual environment and can discover new interests.

[0040] The additional data obtained as a result of the virtual proxy's activities is analyzed again by the server and incorporated into the user's dataset as detailed behavioral patterns. This process makes it possible to continuously track how the user's interests are changing and what new interests they are developing.

[0041] As described above, this system allows companies to use data obtained from users' publicly available information to gain deeper insights through virtual agents. For example, if user A posts about a new movie, virtual agent A can participate in a virtual movie community and learn about movie reviews from other virtual agents. This activity allows companies to gain a deeper understanding of user A's movie interests.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server initiates a process to collect publicly available user information via the internet. This involves using SNS APIs and web scraping to gather profile information, posts, and public follower information. This data is then stored in the server's database.

[0045] Step 2:

[0046] The server sends the collected data to the analysis engine. The analysis engine uses natural language processing technology to extract the user's hobbies and preferences from the text. It analyzes frequently occurring topics and keywords to identify the user's areas of interest.

[0047] Step 3:

[0048] Based on the analysis results, the server generates a virtual proxy that mimics the user. This virtual proxy reflects the user's hobbies and preferences, and this data is recorded as agent characteristics.

[0049] Step 4:

[0050] A virtual agent (a virtual entity on a server) begins its activities in a virtual environment. Other virtual agents also exist in this environment and participate in virtual communities and forums. According to their configured preferences, virtual agents take an interest in relevant topics and interact with other agents.

[0051] Step 5:

[0052] The server continuously monitors and logs the activity of virtual agents, tracking which communities they participate in and what new data they collect. This provides additional insights into user interests.

[0053] Step 6:

[0054] The server re-analyzes the recorded activity logs, identifies new interests and behavioral changes, and updates the user's data profile accordingly. This information is generated as a report and imported into the company's data analytics tools.

[0055] (Example 1)

[0056] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0057] In modern society, where people's interests and preferences are diversifying, it is crucial to provide information and services tailored to individual users. However, conventional technologies have struggled to track changes in users' hobbies and preferences in real time, limiting the provision of personalized services. Furthermore, they have been unable to accurately capture users' dynamic interests, resulting in insufficient responses in situations where a high level of personalization is required.

[0058] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0059] In this invention, the server includes data collection means for collecting publicly available user information via a communication network, data analysis means for analyzing the collected data using natural language processing technology to extract the user's interests and preferences, and entity generation means for creating a pseudo-entity that mimics the user based on the extracted interests and preferences. This enables tracking of the user's diverse interests and preferences in real time and provides highly accurate personalized services.

[0060] "Data collection means" refers to a function that automatically acquires users' publicly available information via a communication network.

[0061] "Data analysis means" refers to a function that analyzes collected information using natural language processing technology to extract users' interests and preferences.

[0062] "Entity generation means" refers to a function that creates a pseudo-entity that mimics the user based on the user's interests and preferences obtained through analysis.

[0063] "Activity control means" refers to a function that controls how pseudo-entities act in a virtual space and acquire additional information.

[0064] "Information update means" refers to a function that re-analyzes acquired additional information and updates user behavior information.

[0065] A "pseudo-entity" refers to a virtual proxy that reflects the user's interests and preferences, and acts on behalf of the user within the virtual space.

[0066] This invention is a system designed to collect and analyze user-generated public information using data processing technology. In implementing the invention, the server includes a set of software and hardware environments necessary to collect and analyze data via a communication network and to generate pseudo-entities that can operate in a virtual environment.

[0067] First, the server uses API requests over the internet to collect publicly available user information from platforms such as social networking services (SNS). This includes text, profiles, and follow lists. The data is stored in a database on the server in JSON format.

[0068] The server analyzes the collected information using Python's natural language processing libraries (e.g., NLTK and SpaCy). This extracts user interests and preferences from the text and structures the data accordingly.

[0069] Based on the analysis results, the server generates pseudo-entities using Python scripts. These entities are designed as virtual proxies to simulate activities within a virtual space while reflecting the user's interests. A 3D simulation tool (e.g., Unity) is used for the virtual space.

[0070] For example, when a user frequently posts about travel, the server uses that data to generate a "travel-loving agent," who then participates in a virtual travel forum. Through such simulations, companies can gain deep insights into users' interests.

[0071] An example of a prompt message would be, "Please describe a system that generates a virtual proxy based on a user's SNS activity and simulates their activity in the community." This invention forms the foundation for providing personalized information services by gaining a deeper understanding of users' interests.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects users' publicly available information via the communication network. Specifically, the server uses the SNS API to retrieve users' posted text, profile information, and follower lists. It receives the SNS's public ID as input and stores the data based on this ID in the database as collected data.

[0075] Step 2:

[0076] The server feeds the collected public information into a natural language processing engine. It analyzes the input text data using a natural language processing library (e.g., NLTK or SpaCy). By tokenizing the text data and performing keyword extraction and sentiment analysis, it understands the user's interests and preferences. As output, it generates a list of analyzed interest keywords.

[0077] Step 3:

[0078] The server generates virtual agents based on the analysis results. This uses an agent generation algorithm that sets attributes that reflect the user's interests and preferences. Based on the input interest keywords, it sets a profile for the pseudo-entity and outputs a virtual agent that is ready to operate in the virtual space.

[0079] Step 4:

[0080] The generated virtual agent begins its activities within a virtual environment. This virtual environment is built using a simulation platform (e.g., Unity). The server schedules the agent's participation in forums related to its interests and its communication with other virtual agents. It receives the virtual agent's profile and activity schedule as input and consequently records an activity log within the virtual environment.

[0081] Step 5:

[0082] The server re-analyzes the data obtained as a result of the virtual agent's activities. Specifically, it aggregates the acquired activity logs using data analysis tools (e.g., Pandas, NumPy) and organizes behavioral patterns. It evaluates the new insights gained by the virtual agent and updates the user's data profile. This allows for continuous tracking of changes in the user's interests and provides feedback to the database as needed.

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] In today's information society, accurately understanding users' hobbies and preferences from vast amounts of data and providing them with relevant advertisements based on that information is difficult. Traditional methods struggle to track changes in user interests in real time and instantly present personalized advertisements, which contributes to a decline in marketing effectiveness.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes data collection means, data analysis means, and agent generation means. This makes it possible to generate a virtual agent based on the user's publicly available information, track the user's interests in real time, and dynamically generate and present personalized advertisements.

[0088] "Data collection means" refers to a device or program that has the function of automatically collecting publicly available information of users from the internet.

[0089] A "data analysis tool" is a program that uses natural language processing technology to analyze collected information and identify the user's hobbies and preferences.

[0090] "Agent generation means" refers to a device or program that has the function of generating a virtual agent based on the hobbies and preferences of a specified user.

[0091] "Process execution means" refers to a device or program that has the function of allowing a virtual agent to operate within a virtual environment and collect and update information.

[0092] "Output generation means" refers to a device or program that has the function of analyzing additional data acquired based on the activities of a virtual agent and outputting the results in a report or other format.

[0093] "Advertising generation and display means" refers to a device or program that has the function of generating appropriate advertisements based on the user's interests and preferences and displaying them on the user's device.

[0094] The system implementing this invention centers around a server built on a cloud environment. The server automatically collects users' publicly available information via the internet using data collection means. Specifically, it uses SNS APIs to store users' posts and public profile information in the server's data storage. Cloud services (e.g., AWS®, Google® Cloud) are used for the hardware.

[0095] Next, the server processes the collected information using data analysis tools. This analysis utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract hobbies and preferences from the text data. This identifies areas of interest based on keywords frequently mentioned by the user.

[0096] Based on extracted hobbies and preferences, the server uses an agent generation mechanism to create a virtual proxy for the user. The virtual proxy is programmed to replicate the user's characteristics and begins activities within the virtual environment. During these activities, the process execution mechanism absorbs information from relevant forums, leading to the discovery of new interests.

[0097] The results of the virtual agent's activities are re-analyzed by the output generation mechanism, and detailed behavioral patterns are generated as a report. Based on this, the server utilizes the ad generation and display mechanism to display personalized advertisements on the user's device. For example, if the user shows interest in a "new smartphone," advertisements for related new products will be displayed on the smartphone.

[0098] To effectively manage this process, a generative AI model can be used, and the following prompt message is entered into the generative AI model: "Design a process that analyzes user interests based on data obtained from social media, generates virtual agents, and then generates and displays the most suitable advertisements to users through those agents." This enables real-time ad optimization.

[0099] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0100] Step 1:

[0101] The server collects users' social media and other publicly available information via the internet using data collection methods. The collected data, including user posts and public profile information, is stored in data storage. The specific input is text data obtained via API, and the output is data stored in the database.

[0102] Step 2:

[0103] The server analyzes the collected information using data analysis tools. This process utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract keywords related to hobbies and preferences from the text data. The input is the text data collected in step 1, and the analysis results output data that identifies the user's interests. Specifically, the frequent occurrence of the word "travel" suggests an interest in travel.

[0104] Step 3:

[0105] The server uses an agent generation mechanism based on the analysis results to generate a virtual proxy for the user. This proxy is designed to reflect the user's interests and operate in a virtual environment. The input is the interest data extracted in step 2, and the output is the generation of a virtual proxy with the configured characteristics.

[0106] Step 4:

[0107] The device displays personalized advertisements to the user using ad generation and display mechanisms. The content of the advertisements is determined based on the activities of the virtual agent. The input is the recommendations obtained from the activities of the virtual agent, and the output is the advertisement displayed on the user's device. As a concrete example, advertisements for gadgets that the user has shown interest in are displayed.

[0108] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0109] This invention is implemented as a system that not only identifies hobbies and preferences from users' publicly available information, but also recognizes emotions using an emotion engine and reflects them in the activities of a virtual surrogate, thereby enabling more detailed data collection and analysis. This system consists of multiple modules managed on the cloud.

[0110] The server first collects information from users' social media and publicly available online sources through various data collection methods. This information includes text, images, and videos. This prepares the server to understand the overall picture of the user's online activities.

[0111] Next, the server analyzes the collected data using analytical tools to identify the user's hobbies and preferences. Natural language processing (NLP) technology is used for this purpose, enabling a deep understanding of the text data's content. Simultaneously, an emotion engine analyzes the sentiment of the text and posts within the data. This identifies emotions such as positive, negative, and neutral.

[0112] Based on the analysis results obtained, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy reflects the user's interests and emotions and can act based on different scenarios in the virtual environment. For example, if the user is interested in movies and has positive emotions, the virtual proxy will actively participate in movie-related forums.

[0113] When a virtual agent performs activities within the virtual environment, the server tracks these activities and records activity logs. Furthermore, the emotion engine analyzes emotions from the virtual agent's interactions and activities, and uses the results in the report generation system. Based on this data, the report generation system creates a detailed report and provides it in a format that can be used by the company.

[0114] For example, if user B has positive feelings about a "new music album" and frequently mentions it, virtual avatar B will become more active in the music community and exchange opinions with other avatars. Through this activity, subtle changes in user B's musical preferences and emotions can be analyzed, and the company can use this information to develop targeted marketing strategies.

[0115] Thus, the present invention enables more sophisticated data analysis that takes user emotions into account, and can support strategic decision-making by companies.

[0116] The following describes the processing flow.

[0117] Step 1:

[0118] The server automatically collects users' publicly available information from online platforms (such as social networking services and blogs). This information includes text, images, and videos, and is collected using public APIs and web scraping techniques.

[0119] Step 2:

[0120] The server feeds the collected information into the analysis engine. The analysis engine uses natural language processing technology to analyze the text data and identify the user's hobbies and preferences. The identified information is stored in a database. At the same time, the emotion engine analyzes the emotions in the text and records that information as well.

[0121] Step 3:

[0122] The server generates a virtual proxy based on the analysis results. Using the proxy generation mechanism, it constructs a virtual proxy that reflects the user's hobbies and emotions. This virtual proxy is a program that mimics the user's behavior and acts according to the set scenario.

[0123] Step 4:

[0124] A virtual proxy (operating via a server) begins its activities within a virtual environment. Various communities exist within this virtual environment, and the proxy participates in forums and chat groups related to the user's hobbies. The virtual proxy interacts with other proxies and acquires new data through these interactions.

[0125] Step 5:

[0126] The server monitors the virtual proxy's activities in real time and stores activity logs. The server meticulously records what content the proxy views and what kind of communication it engages in.

[0127] Step 6:

[0128] The server re-analyzes the accumulated activity logs. Using an emotion engine, it analyzes new emotional information obtained from the virtual proxy's activities to detect changes in the user's behavior patterns and interests. The results of this analysis are provided to the company as a report.

[0129] Through this process, companies can gain deep insights into users' emotions and interests, which they can then use to develop strategies for improving the customer experience.

[0130] (Example 2)

[0131] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0132] Conventional information gathering and analysis systems have the drawback of only identifying users' hobbies and preferences, without adequately performing data analysis and optimizing marketing strategies based on users' emotions and emotional changes. Furthermore, there has been a lack of effective data collection through virtual environment proxy activities and the provision of detailed reports based on that data.

[0133] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0134] In this invention, the server includes information gathering means for collecting publicly available information of users, analysis means for analyzing the collected information using natural language processing technology and analyzing emotions along with hobbies and preferences, and proxy generation means for generating virtual proxies based on the identified information. This enables analysis that includes changes in users' emotions and behavior, allowing companies to optimize their marketing strategies.

[0135] "Information gathering means" refers to a system that collects publicly available data on the internet and has the function of comprehensively obtaining information about users' online activities.

[0136] The "analysis method" is a system that utilizes natural language processing technology to identify users' hobbies and preferences from collected data, and further analyzes their emotions.

[0137] A "proxy generation means" is a device that has the function of generating a virtual proxy that reflects the user's hobbies, preferences, and emotions based on the analysis results.

[0138] "Means of activity" refers to a system in which a virtual agent operates within a virtual environment and has the function of acquiring meaningful data while exchanging information with other virtual agents.

[0139] The "report generation means" is a system that analyzes additional data acquired by the virtual agent and generates a detailed report in a format that can be used by the company.

[0140] This invention realizes a system that provides detailed data reports based on the user's emotions and interests through information gathering, data analysis, virtual proxy generation, and activity tracking. Specific embodiments of this system are described below.

[0141] First, the server uses information gathering tools to collect publicly available information from the internet, particularly from social networking services (SNS), including user text, images, and videos. This process typically involves utilizing APIs to acquire data from the internet; for example, this can be achieved by building analysis software that integrates with the Twitter API using Python.

[0142] Next, the server applies analytical methods to the collected data. Here, natural language processing (NLP) techniques are used to extract the user's hobbies and preferences from text information, and an emotion engine is used to determine emotional states such as positive, negative, and neutral. Specifically, natural language processing libraries such as NLTK and spaCy are used, and a BERT-based model is integrated for emotion analysis to perform complex text analysis.

[0143] Based on the analysis results, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy is designed to faithfully reflect the detected user's hobbies and emotions. The virtual proxy is created to operate within a virtual environment, and its activities are used in strategic planning in the company's relevant fields.

[0144] Furthermore, the activities of virtual agents are tracked in real time within the virtual environment through the activity mechanism and recorded by the server. This allows companies to gain a detailed understanding of changes in users' interests and emotional trends based on the information obtained from the activity logs.

[0145] Ultimately, the server uses a report generation mechanism to create a detailed report summarizing the analysis results, which is then provided to companies in a format that can be used for marketing strategies and product development.

[0146] For example, if a user expresses positive feelings towards a "new music album," this information is reflected in the virtual agent's activities in a virtual environment. The virtual agent actively exchanges opinions in music-related forums and provides consumer behavior data based on new music trends.

[0147] An example of a prompt for a generative AI model is: "Use data collected from social media to identify user preferences and emotions, and show how to utilize this information in marketing strategies through virtual representations."

[0148] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0149] Step 1:

[0150] The server collects publicly available data from the internet using various information gathering methods. Specifically, it uses SNS APIs to retrieve user posts and profile information in text, image, and video formats. User IDs and hashtags are provided as input, and a dataset of the retrieved multimedia content is generated as output.

[0151] Step 2:

[0152] The server processes the collected data using analytical tools. It uses natural language processing (NLP) techniques to analyze user interests from text data. Specifically, it uses the Python library NLTK to extract specific keywords and perform contextual analysis. The input is the text data collected in step 1, and the output is profile data indicating the user's hobbies and preferences.

[0153] Step 3:

[0154] Similarly, the server uses an emotion engine to analyze the sentiment of the text data. The BERT sentiment analysis model is used to determine whether the text is positive, negative, or neutral. The input is the text data from step 1, and the output is an evaluation value based on the sentiment analysis.

[0155] Step 4:

[0156] The server generates a virtual surrogate using a surrogate generation mechanism based on hobby, preference, and emotion data obtained from the analysis mechanism. This virtual surrogate is prepared to operate within the virtual environment with specific settings tailored to the user's profile. The analysis results from steps 2 and 3 are used as input, and the virtual surrogate's configuration data is generated as output.

[0157] Step 5:

[0158] Virtual agents operate within a virtual environment through various means of activity. They exchange information with other agents on specific forums and social media platforms. Input is the agent's configuration data, and output is logs of new data and information exchanges obtained during their activities.

[0159] Step 6:

[0160] The server analyzes the data acquired through the activity tools and generates a detailed report using the report generation tool. This report shows changes in user emotions and the evolution of their interests, which companies can use in their marketing strategies. The input is the activity data obtained in step 5, and the output is a detailed report for companies.

[0161] (Application Example 2)

[0162] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0163] In today's world, there is a demand for advertising personalization based on users' online activities. However, conventional systems are unable to accurately reflect users' emotions and real-time changes in their interests, resulting in ineffective ad delivery. This invention aims to solve this problem and provide a system that enables ad delivery that dynamically reflects users' emotions and interests.

[0164] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0165] In this invention, the server includes information acquisition means for collecting publicly available information of users, data analysis means for analyzing the collected publicly available information and identifying the user's hobbies and preferences, and proxy generation means for generating a virtual proxy for the user based on the identified hobbies, preferences, and emotional state. This makes it possible to generate and deliver advertisements based on the dynamic changes in the user's emotions and hobbies.

[0166] "User" refers to an individual or group that uses a system or device.

[0167] "Public information" refers to information such as text, images, and videos that are made publicly available on social media and the web.

[0168] "Means of information acquisition" refers to the mechanisms and processes for collecting publicly available information.

[0169] "Data analysis methods" refer to technologies and methods that analyze collected publicly available information to identify users' hobbies and preferences.

[0170] A "proxy generation method" refers to a process or system for generating a virtual proxy that reflects the user's interests and emotions.

[0171] A "virtual proxy" is a virtual entity that mimics the characteristics of a user and operates within an electronic environment.

[0172] "Electronic environment" refers to a virtually constructed information space, such as the internet or digital platforms.

[0173] "Means of activity" refers to the mechanism by which virtual agents generate and deliver advertisements within the electronic environment.

[0174] "Display method" refers to a method of displaying generated advertisements on a user's device and obtaining their response.

[0175] "Result generation means" refers to the technology and methods used to analyze data obtained based on user responses and create a final report.

[0176] "Response" refers to the actions or feedback that users give in response to the advertisements they see.

[0177] This invention is a system for realizing personalized advertising based on users' online activities. This system is configured as follows:

[0178] The server first collects publicly available information from users' social media and web presence using information acquisition tools. This information collection is performed using APIs and can handle various data formats such as text, images, and videos. The data analysis tool uses natural language processing (NLP) libraries (e.g., NLTK and SpaCy) to deeply analyze the collected data and identify the user's hobbies and preferences. Furthermore, sentiment analysis tools (e.g., IBM Watson® and Google Cloud Natural Language) are used to identify emotions such as positive, negative, and neutral.

[0179] Next, the proxy generation means generates a virtual proxy based on identified preferences and emotional states. This virtual proxy operates within the electronic environment, dynamically generating and delivering personalized advertisements that respond to the user's emotional state. The advertisements are displayed on the user's device through the display means, and user responses are collected in real time. This creates a feedback loop for understanding the effectiveness of the advertisements.

[0180] The results generation method analyzes user response data further and generates detailed reports that companies can use. For example, if a user makes a positive post such as, "I want to go to the mountains on my next vacation! I want to relax in nature," this information is analyzed by the system, and advertisements for outdoor equipment and eco-tours are provided. The following prompt is used as input to the AI ​​model: "User's latest post: 'I want to go to the mountains on my next vacation! I want to relax in nature.' Please generate appropriate advertisements based on this post."

[0181] Thus, by implementing the present invention, it becomes possible to conduct advertising campaigns based on users' dynamic emotions and changing preferences, thereby maximizing advertising effectiveness.

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

[0183] Step 1:

[0184] The server collects publicly available information from users' social media and web presence using a valid API. Input is the user's public profile information, and output is text, image, and video data. The server stores this data in a temporary database.

[0185] Step 2:

[0186] The server uses a natural language processing (NLP) library to analyze the collected text data. The input is the text information obtained in step 1, and the output is the identification of the user's hobbies and preferences. Through NLP processing, the server extracts the user's interests from the context of each text and the frequency patterns of words.

[0187] Step 3:

[0188] The server uses sentiment analysis tools to identify emotions from the text in the collected data. The input is the text messages obtained in step 1, and the output is an emotion label such as positive, negative, or neutral. The server analyzes the emotions based on the tone and keywords of the text.

[0189] Step 4:

[0190] The server generates a virtual surrogate based on the user's interests and emotional state. The input is the analysis results from steps 2 and 3, and the output is the virtual surrogate's profile. The server utilizes a generative AI model to design a surrogate that reflects the user's characteristics.

[0191] Step 5:

[0192] The virtual agent operates within the electronic environment, generating and delivering appropriate advertisements. The input consists of the virtual agent's profile and the user's past behavioral history, while the output is personalized advertisements. The virtual agent uses a generative AI model to construct contextually relevant ad content.

[0193] Step 6:

[0194] The device displays advertisements generated by a virtual agent to the user and collects the user's responses. The input is the advertisement generated in step 5, and the output is the user's clicks and interaction information. The device aggregates the information through the user interface.

[0195] Step 7:

[0196] The server analyzes user response data to generate a detailed report. The input is the response information obtained in step 6, and the output is a performance report of the advertising campaign. The server performs data analysis and compiles insights that companies can use for their strategies.

[0197] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0198] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0199] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0200] [Second Embodiment]

[0201] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0202] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0203] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0204] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0205] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0206] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0207] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0208] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0209] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0210] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0211] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0212] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0213] The present invention is implemented as a series of programs and related processes in a system built on a cloud environment. Its specific form is described below.

[0214] First, the server automatically collects users' publicly available information via the internet. This information includes text posted by users on social media, public profile data, and public follower lists. The collected information is securely stored in the server's data storage.

[0215] Next, the server feeds the collected information into an analysis engine, which uses natural language processing technology to analyze the text data. This analysis allows the server to identify the user's hobbies and preferences. For example, if a user frequently posts words like "travel" or "cooking," these are classified as the user's interests.

[0216] Based on the analysis results, the server programmatically generates a virtual proxy that resembles the user. This virtual proxy is designed to replicate the user's hobbies and preferences, and for example, it operates within the virtual environment as a "travel-loving agent."

[0217] The generated virtual agent begins its activities in a virtual environment on the server. These activities include participating in forums aligned with the user's interests and communicating with other virtual agents. Over time, the virtual agent absorbs information within the virtual environment and can discover new interests.

[0218] The additional data obtained as a result of the virtual proxy's activities is analyzed again by the server and incorporated into the user's dataset as detailed behavioral patterns. This process makes it possible to continuously track how the user's interests are changing and what new interests they are developing.

[0219] As described above, this system allows companies to use data obtained from users' publicly available information to gain deeper insights through virtual agents. For example, if user A posts about a new movie, virtual agent A can participate in a virtual movie community and learn about movie reviews from other virtual agents. This activity allows companies to gain a deeper understanding of user A's movie interests.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] The server initiates a process to collect publicly available user information via the internet. This involves using SNS APIs and web scraping to gather profile information, posts, and public follower information. This data is then stored in the server's database.

[0223] Step 2:

[0224] The server sends the collected data to the analysis engine. The analysis engine uses natural language processing technology to extract the user's hobbies and preferences from the text. It analyzes frequently occurring topics and keywords to identify the user's areas of interest.

[0225] Step 3:

[0226] Based on the analysis results, the server generates a virtual proxy that mimics the user. This virtual proxy reflects the user's hobbies and preferences, and this data is recorded as agent characteristics.

[0227] Step 4:

[0228] A virtual agent (a virtual entity on a server) begins its activities in a virtual environment. Other virtual agents also exist in this environment and participate in virtual communities and forums. According to their configured preferences, virtual agents take an interest in relevant topics and interact with other agents.

[0229] Step 5:

[0230] The server continuously monitors and logs the activity of virtual agents, tracking which communities they participate in and what new data they collect. This provides additional insights into user interests.

[0231] Step 6:

[0232] The server re-analyzes the recorded activity logs, identifies new interests and behavioral changes, and updates the user's data profile accordingly. This information is generated as a report and imported into the company's data analytics tools.

[0233] (Example 1)

[0234] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0235] In modern society, where people's interests and preferences are diversifying, it is crucial to provide information and services tailored to individual users. However, conventional technologies have struggled to track changes in users' hobbies and preferences in real time, limiting the provision of personalized services. Furthermore, they have been unable to accurately capture users' dynamic interests, resulting in insufficient responses in situations where a high level of personalization is required.

[0236] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0237] In this invention, the server includes data collection means for collecting publicly available user information via a communication network, data analysis means for analyzing the collected data using natural language processing technology to extract the user's interests and preferences, and entity generation means for creating a pseudo-entity that mimics the user based on the extracted interests and preferences. This enables tracking of the user's diverse interests and preferences in real time and provides highly accurate personalized services.

[0238] "Data collection means" refers to a function that automatically acquires users' publicly available information via a communication network.

[0239] "Data analysis means" refers to a function that analyzes collected information using natural language processing technology to extract users' interests and preferences.

[0240] "Entity generation means" refers to a function that creates a pseudo-entity that mimics the user based on the user's interests and preferences obtained through analysis.

[0241] "Activity control means" refers to a function that controls how pseudo-entities act in a virtual space and acquire additional information.

[0242] "Information update means" refers to a function that re-analyzes acquired additional information and updates user behavior information.

[0243] A "pseudo-entity" refers to a virtual proxy that reflects the user's interests and preferences, and acts on behalf of the user within the virtual space.

[0244] This invention is a system designed to collect and analyze user-generated public information using data processing technology. In implementing the invention, the server includes a set of software and hardware environments necessary to collect and analyze data via a communication network and to generate pseudo-entities that can operate in a virtual environment.

[0245] First, the server uses API requests over the internet to collect publicly available user information from platforms such as social networking services (SNS). This includes text, profiles, and follow lists. The data is stored in a database on the server in JSON format.

[0246] The server analyzes the collected information using Python's natural language processing libraries (e.g., NLTK and SpaCy). This extracts user interests and preferences from the text and structures the data accordingly.

[0247] Based on the analysis results, the server generates pseudo-entities using Python scripts. These entities are designed as virtual proxies to simulate activities within a virtual space while reflecting the user's interests. A 3D simulation tool (e.g., Unity) is used for the virtual space.

[0248] For example, when a user frequently posts about travel, the server uses that data to generate a "travel-loving agent," who then participates in a virtual travel forum. Through such simulations, companies can gain deep insights into users' interests.

[0249] An example of a prompt message would be, "Please describe a system that generates a virtual proxy based on a user's SNS activity and simulates their activity in the community." This invention forms the foundation for providing personalized information services by gaining a deeper understanding of users' interests.

[0250] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0251] Step 1:

[0252] The server collects users' publicly available information via the communication network. Specifically, the server uses the SNS API to retrieve users' posted text, profile information, and follower lists. It receives the SNS's public ID as input and stores the data based on this ID in the database as collected data.

[0253] Step 2:

[0254] The server feeds the collected public information into a natural language processing engine. It analyzes the input text data using a natural language processing library (e.g., NLTK or SpaCy). By tokenizing the text data and performing keyword extraction and sentiment analysis, it understands the user's interests and preferences. As output, it generates a list of analyzed interest keywords.

[0255] Step 3:

[0256] The server generates virtual agents based on the analysis results. This uses an agent generation algorithm that sets attributes that reflect the user's interests and preferences. Based on the input interest keywords, it sets a profile for the pseudo-entity and outputs a virtual agent that is ready to operate in the virtual space.

[0257] Step 4:

[0258] The generated virtual agent begins its activities within a virtual environment. This virtual environment is built using a simulation platform (e.g., Unity). The server schedules the agent's participation in forums related to its interests and its communication with other virtual agents. It receives the virtual agent's profile and activity schedule as input and consequently records an activity log within the virtual environment.

[0259] Step 5:

[0260] The server re-analyzes the data obtained as a result of the virtual agent's activities. Specifically, it aggregates the acquired activity logs using data analysis tools (e.g., Pandas, NumPy) and organizes behavioral patterns. It evaluates the new insights gained by the virtual agent and updates the user's data profile. This allows for continuous tracking of changes in the user's interests and provides feedback to the database as needed.

[0261] (Application Example 1)

[0262] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] In today's information society, accurately understanding users' hobbies and preferences from vast amounts of data and providing them with relevant advertisements based on that information is difficult. Traditional methods struggle to track changes in user interests in real time and instantly present personalized advertisements, which contributes to a decline in marketing effectiveness.

[0264] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0265] In this invention, the server includes data collection means, data analysis means, and agent generation means. This makes it possible to generate a virtual agent based on the user's publicly available information, track the user's interests in real time, and dynamically generate and present personalized advertisements.

[0266] "Data collection means" refers to a device or program that has the function of automatically collecting publicly available information of users from the internet.

[0267] A "data analysis tool" is a program that uses natural language processing technology to analyze collected information and identify the user's hobbies and preferences.

[0268] "Agent generation means" refers to a device or program that has the function of generating a virtual agent based on the hobbies and preferences of a specified user.

[0269] "Process execution means" refers to a device or program that has the function of allowing a virtual agent to operate within a virtual environment and collect and update information.

[0270] "Output generation means" refers to a device or program that has the function of analyzing additional data acquired based on the activities of a virtual agent and outputting the results in a report or other format.

[0271] "Advertising generation and display means" refers to a device or program that has the function of generating appropriate advertisements based on the user's interests and preferences and displaying them on the user's device.

[0272] The system implementing this invention centers around a server built on a cloud environment. The server automatically collects users' publicly available information via the internet using data collection means. Specifically, it uses SNS APIs to store users' posts and public profile information in the server's data storage. Cloud services (e.g., AWS, Google Cloud) are used for the hardware.

[0273] Next, the server processes the collected information using data analysis tools. This analysis utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract hobbies and preferences from the text data. This identifies areas of interest based on keywords frequently mentioned by the user.

[0274] Based on extracted hobbies and preferences, the server uses an agent generation mechanism to create a virtual proxy for the user. The virtual proxy is programmed to replicate the user's characteristics and begins activities within the virtual environment. During these activities, the process execution mechanism absorbs information from relevant forums, leading to the discovery of new interests.

[0275] The results of the virtual agent's activities are re-analyzed by the output generation mechanism, and detailed behavioral patterns are generated as a report. Based on this, the server utilizes the ad generation and display mechanism to display personalized advertisements on the user's device. For example, if the user shows interest in a "new smartphone," advertisements for related new products will be displayed on the smartphone.

[0276] To effectively manage this process, it is possible to use a generative AI model and input the following prompt text into the generative AI model: "Please design a process that analyzes user interests based on data obtained from SNS, generates a virtual agent, and generates and displays optimal advertisements for users through that agent." This enables real-time advertisement optimization.

[0277] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0278] Step 1:

[0279] The server collects the user's SNS and other public information via the Internet using data collection means. The collected data includes the user's posted content and public profile information and is stored in data storage. The specific input is text data obtained via an API, and the output is the data stored in the database.

[0280] Step 2:

[0281] The server analyzes the collected information using data analysis means. In this process, natural language processing technologies (e.g., NLTK, spaCy) are used to extract keywords related to hobbies and preferences from the text data. The input is the text data collected in Step 1, and the output is data identifying the user's interests as the analysis result. Specifically, it is determined that there is an interest in travel from the frequently occurring word "travel".

[0282] Step 3:

[0283] The server uses agent generation means based on the analysis result to generate a virtual agent for the user. This agent reflects the user's interests and is designed to operate in a virtual environment. The input is the data related to the interests extracted in Step 2, and the output is the generation of a virtual agent with the set characteristics.

[0284] Step 4:

[0285] The terminal uses advertisement generation and display means to display personalized advertisements to the user. The content of the advertisement is determined based on the activities of the virtual agent. The input is the recommendations obtained from the activities of the virtual agent, and the output is the advertisement displayed on the user terminal. As a specific operation, there is an example where an advertisement for a gadget that the user has shown interest in is displayed.

[0286] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0287] The present invention is implemented as a system that not only identifies hobbies and preferences from the public information of users, but also recognizes emotions using an emotion engine and reflects them in the activities of the virtual agent, thereby collecting and analyzing more detailed data. This system is composed of a plurality of modules managed on the cloud.

[0288] First, the server collects the public information of the user on the SNS and the web through the information collection means. At this time, the information collected includes text, images, videos, etc. This prepares to grasp the overall picture of the user's online activities.

[0289] Subsequently, the server analyzes the collected data using the analysis means to identify the hobbies and preferences of the user. In this process, natural language processing (NLP) technology is utilized, enabling a deep understanding of the content of the text data. At the same time, the emotion engine analyzes the emotions of the text and posts in the data. Thereby, emotions such as positive, negative, and neutral are identified.

[0290] Based on the analysis results obtained, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy reflects the user's interests and emotions and can act based on different scenarios in the virtual environment. For example, if the user is interested in movies and has positive emotions, the virtual proxy will actively participate in movie-related forums.

[0291] When a virtual agent performs activities within the virtual environment, the server tracks these activities and records activity logs. Furthermore, the emotion engine analyzes emotions from the virtual agent's interactions and activities, and uses the results in the report generation system. Based on this data, the report generation system creates a detailed report and provides it in a format that can be used by the company.

[0292] For example, if user B has positive feelings about a "new music album" and frequently mentions it, virtual avatar B will become more active in the music community and exchange opinions with other avatars. Through this activity, subtle changes in user B's musical preferences and emotions can be analyzed, and the company can use this information to develop targeted marketing strategies.

[0293] Thus, the present invention enables more sophisticated data analysis that takes user emotions into account, and can support strategic decision-making by companies.

[0294] The following describes the processing flow.

[0295] Step 1:

[0296] The server automatically collects users' publicly available information from online platforms (such as social networking services and blogs). This information includes text, images, and videos, and is collected using public APIs and web scraping techniques.

[0297] Step 2:

[0298] The server feeds the collected information into the analysis engine. The analysis engine uses natural language processing technology to analyze the text data and identify the user's hobbies and preferences. The identified information is stored in a database. At the same time, the emotion engine analyzes the emotions in the text and records that information as well.

[0299] Step 3:

[0300] The server generates a virtual proxy based on the analysis results. Using the proxy generation mechanism, it constructs a virtual proxy that reflects the user's hobbies and emotions. This virtual proxy is a program that mimics the user's behavior and acts according to the set scenario.

[0301] Step 4:

[0302] A virtual proxy (operating via a server) begins its activities within a virtual environment. Various communities exist within this virtual environment, and the proxy participates in forums and chat groups related to the user's hobbies. The virtual proxy interacts with other proxies and acquires new data through these interactions.

[0303] Step 5:

[0304] The server monitors the virtual proxy's activities in real time and stores activity logs. The server meticulously records what content the proxy views and what kind of communication it engages in.

[0305] Step 6:

[0306] The server re-analyzes the accumulated activity logs. Using an emotion engine, it analyzes new emotional information obtained from the virtual proxy's activities to detect changes in the user's behavior patterns and interests. The results of this analysis are provided to the company as a report.

[0307] Through this process, companies can gain deep insights into users' emotions and interests, which they can then use to develop strategies for improving the customer experience.

[0308] (Example 2)

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

[0310] In the conventional information collection and analysis system, there is a problem that only the hobbies and preferences of users are identified, and data analysis based on the emotions and emotional changes of users and the optimization of marketing strategies are not sufficiently carried out. There is also a problem that effective data collection through proxy activities in a virtual environment and the provision of detailed reports based on the data are insufficient.

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

[0312] In this invention, the server includes an information collection means for collecting public information of users, an analysis means for analyzing the collected information using natural language processing technology and analyzing emotions together with hobbies and preferences, and an agent generation means for generating a virtual agent based on the identified information. As a result, analysis including changes in the emotions and behaviors of users becomes possible, and companies can realize the optimization of marketing strategies.

[0313] The "information collection means" has a function of collecting public data on the Internet and comprehensively obtaining information related to the online activities of users.

[0314] The "analysis means" has a function of identifying the hobbies and preferences of users from the collected data and further analyzing emotions by utilizing natural language processing technology.

[0315] The "agent generation means" has a function of generating a virtual agent that reflects the hobbies, preferences, and emotions of users based on the analysis results.

[0316] "Means of activity" refers to a system in which a virtual agent operates within a virtual environment and has the function of acquiring meaningful data while exchanging information with other virtual agents.

[0317] The "report generation means" is a system that analyzes additional data acquired by the virtual agent and generates a detailed report in a format that can be used by the company.

[0318] This invention realizes a system that provides detailed data reports based on the user's emotions and interests through information gathering, data analysis, virtual proxy generation, and activity tracking. Specific embodiments of this system are described below.

[0319] First, the server uses information gathering tools to collect publicly available information from the internet, particularly from social networking services (SNS), including user text, images, and videos. This process typically involves utilizing APIs to acquire data from the internet; for example, this can be achieved by building analysis software that integrates with the Twitter API using Python.

[0320] Next, the server applies analytical methods to the collected data. Here, natural language processing (NLP) techniques are used to extract the user's hobbies and preferences from text information, and an emotion engine is used to determine emotional states such as positive, negative, and neutral. Specifically, natural language processing libraries such as NLTK and spaCy are used, and a BERT-based model is integrated for emotion analysis to perform complex text analysis.

[0321] Based on the analysis results, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy is designed to faithfully reflect the detected user's hobbies and emotions. The virtual proxy is created to operate within a virtual environment, and its activities are used in strategic planning in the company's relevant fields.

[0322] Furthermore, the activities of virtual agents are tracked in real time within the virtual environment through the activity mechanism and recorded by the server. This allows companies to gain a detailed understanding of changes in users' interests and emotional trends based on the information obtained from the activity logs.

[0323] Ultimately, the server uses a report generation mechanism to create a detailed report summarizing the analysis results, which is then provided to companies in a format that can be used for marketing strategies and product development.

[0324] For example, if a user expresses positive feelings towards a "new music album," this information is reflected in the virtual agent's activities in a virtual environment. The virtual agent actively exchanges opinions in music-related forums and provides consumer behavior data based on new music trends.

[0325] An example of a prompt for a generative AI model is: "Use data collected from social media to identify user preferences and emotions, and show how to utilize this information in marketing strategies through virtual representations."

[0326] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0327] Step 1:

[0328] The server collects publicly available data from the internet using various information gathering methods. Specifically, it uses SNS APIs to retrieve user posts and profile information in text, image, and video formats. User IDs and hashtags are provided as input, and a dataset of the retrieved multimedia content is generated as output.

[0329] Step 2:

[0330] The server processes the collected data using analytical tools. It uses natural language processing (NLP) techniques to analyze user interests from text data. Specifically, it uses the Python library NLTK to extract specific keywords and perform contextual analysis. The input is the text data collected in step 1, and the output is profile data indicating the user's hobbies and preferences.

[0331] Step 3:

[0332] Similarly, the server uses an emotion engine to analyze the sentiment of the text data. The BERT sentiment analysis model is used to determine whether the text is positive, negative, or neutral. The input is the text data from step 1, and the output is an evaluation value based on the sentiment analysis.

[0333] Step 4:

[0334] The server generates a virtual surrogate using a surrogate generation mechanism based on hobby, preference, and emotion data obtained from the analysis mechanism. This virtual surrogate is prepared to operate within the virtual environment with specific settings tailored to the user's profile. The analysis results from steps 2 and 3 are used as input, and the virtual surrogate's configuration data is generated as output.

[0335] Step 5:

[0336] Virtual agents operate within a virtual environment through various means of activity. They exchange information with other agents on specific forums and social media platforms. Input is the agent's configuration data, and output is logs of new data and information exchanges obtained during their activities.

[0337] Step 6:

[0338] The server analyzes the data acquired through the activity tools and generates a detailed report using the report generation tool. This report shows changes in user emotions and the evolution of their interests, which companies can use in their marketing strategies. The input is the activity data obtained in step 5, and the output is a detailed report for companies.

[0339] (Application Example 2)

[0340] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0341] In today's world, there is a demand for advertising personalization based on users' online activities. However, conventional systems are unable to accurately reflect users' emotions and real-time changes in their interests, resulting in ineffective ad delivery. This invention aims to solve this problem and provide a system that enables ad delivery that dynamically reflects users' emotions and interests.

[0342] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0343] In this invention, the server includes information acquisition means for collecting publicly available information of users, data analysis means for analyzing the collected publicly available information and identifying the user's hobbies and preferences, and proxy generation means for generating a virtual proxy for the user based on the identified hobbies, preferences, and emotional state. This makes it possible to generate and deliver advertisements based on the dynamic changes in the user's emotions and hobbies.

[0344] "User" refers to an individual or group that uses a system or device.

[0345] "Public information" refers to information such as text, images, and videos that are made publicly available on social media and the web.

[0346] "Means of information acquisition" refers to the mechanisms and processes for collecting publicly available information.

[0347] "Data analysis methods" refer to technologies and methods that analyze collected publicly available information to identify users' hobbies and preferences.

[0348] A "proxy generation method" refers to a process or system for generating a virtual proxy that reflects the user's interests and emotions.

[0349] A "virtual proxy" is a virtual entity that mimics the characteristics of a user and operates within an electronic environment.

[0350] "Electronic environment" refers to a virtually constructed information space, such as the internet or digital platforms.

[0351] "Means of activity" refers to the mechanism by which virtual agents generate and deliver advertisements within the electronic environment.

[0352] "Display method" refers to a method of displaying generated advertisements on a user's device and obtaining their response.

[0353] "Result generation means" refers to the technology and methods used to analyze data obtained based on user responses and create a final report.

[0354] "Response" refers to the actions or feedback that users give in response to the advertisements they see.

[0355] This invention is a system for realizing personalized advertising based on users' online activities. This system is configured as follows:

[0356] The server first collects publicly available information from users' social media and web presence using information acquisition tools. This information collection is performed using APIs and can handle various data formats such as text, images, and videos. The data analysis tool uses natural language processing (NLP) libraries (e.g., NLTK and SpaCy) to deeply analyze the collected data and identify the user's hobbies and preferences. Furthermore, sentiment analysis tools (e.g., IBM Watson and Google Cloud Natural Language) are used to identify emotions such as positive, negative, and neutral.

[0357] Next, the proxy generation means generates a virtual proxy based on identified preferences and emotional states. This virtual proxy operates within the electronic environment, dynamically generating and delivering personalized advertisements that respond to the user's emotional state. The advertisements are displayed on the user's device through the display means, and user responses are collected in real time. This creates a feedback loop for understanding the effectiveness of the advertisements.

[0358] The results generation method analyzes user response data further and generates detailed reports that companies can use. For example, if a user makes a positive post such as, "I want to go to the mountains on my next vacation! I want to relax in nature," this information is analyzed by the system, and advertisements for outdoor equipment and eco-tours are provided. The following prompt is used as input to the AI ​​model: "User's latest post: 'I want to go to the mountains on my next vacation! I want to relax in nature.' Please generate appropriate advertisements based on this post."

[0359] Thus, by implementing the present invention, it becomes possible to conduct advertising campaigns based on users' dynamic emotions and changing preferences, thereby maximizing advertising effectiveness.

[0360] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0361] Step 1:

[0362] The server collects publicly available information from users' social media and web presence using a valid API. Input is the user's public profile information, and output is text, image, and video data. The server stores this data in a temporary database.

[0363] Step 2:

[0364] The server uses a natural language processing (NLP) library to analyze the collected text data. The input is the text information obtained in step 1, and the output is the identification of the user's hobbies and preferences. Through NLP processing, the server extracts the user's interests from the context of each text and the frequency patterns of words.

[0365] Step 3:

[0366] The server uses sentiment analysis tools to identify emotions from the text in the collected data. The input is the text messages obtained in step 1, and the output is an emotion label such as positive, negative, or neutral. The server analyzes the emotions based on the tone and keywords of the text.

[0367] Step 4:

[0368] The server generates a virtual surrogate based on the user's interests and emotional state. The input is the analysis results from steps 2 and 3, and the output is the virtual surrogate's profile. The server utilizes a generative AI model to design a surrogate that reflects the user's characteristics.

[0369] Step 5:

[0370] The virtual agent operates within the electronic environment, generating and delivering appropriate advertisements. The input consists of the virtual agent's profile and the user's past behavioral history, while the output is personalized advertisements. The virtual agent uses a generative AI model to construct contextually relevant ad content.

[0371] Step 6:

[0372] The device displays advertisements generated by a virtual agent to the user and collects the user's responses. The input is the advertisement generated in step 5, and the output is the user's clicks and interaction information. The device aggregates the information through the user interface.

[0373] Step 7:

[0374] The server analyzes user response data to generate a detailed report. The input is the response information obtained in step 6, and the output is a performance report of the advertising campaign. The server performs data analysis and compiles insights that companies can use for their strategies.

[0375] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0376] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0377] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0378] [Third Embodiment]

[0379] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0380] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0381] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0382] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0383] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0384] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0385] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0386] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0387] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0388] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0389] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0390] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0391] The present invention is implemented as a series of programs and related processes in a system built on a cloud environment. Its specific form is described below.

[0392] First, the server automatically collects users' publicly available information via the internet. This information includes text posted by users on social media, public profile data, and public follower lists. The collected information is securely stored in the server's data storage.

[0393] Next, the server feeds the collected information into an analysis engine, which uses natural language processing technology to analyze the text data. This analysis allows the server to identify the user's hobbies and preferences. For example, if a user frequently posts words like "travel" or "cooking," these are classified as the user's interests.

[0394] Based on the analysis results, the server programmatically generates a virtual proxy that resembles the user. This virtual proxy is designed to replicate the user's hobbies and preferences, and for example, it operates within the virtual environment as a "travel-loving agent."

[0395] The generated virtual agent begins its activities in a virtual environment on the server. These activities include participating in forums aligned with the user's interests and communicating with other virtual agents. Over time, the virtual agent absorbs information within the virtual environment and can discover new interests.

[0396] The additional data obtained as a result of the virtual proxy's activities is analyzed again by the server and incorporated into the user's dataset as detailed behavioral patterns. This process makes it possible to continuously track how the user's interests are changing and what new interests they are developing.

[0397] As described above, this system allows companies to use data obtained from users' publicly available information to gain deeper insights through virtual agents. For example, if user A posts about a new movie, virtual agent A can participate in a virtual movie community and learn about movie reviews from other virtual agents. This activity allows companies to gain a deeper understanding of user A's movie interests.

[0398] The following describes the processing flow.

[0399] Step 1:

[0400] The server initiates a process to collect publicly available user information via the internet. This involves using SNS APIs and web scraping to gather profile information, posts, and public follower information. This data is then stored in the server's database.

[0401] Step 2:

[0402] The server sends the collected data to the analysis engine. The analysis engine uses natural language processing technology to extract the user's hobbies and preferences from the text. It analyzes frequently occurring topics and keywords to identify the user's areas of interest.

[0403] Step 3:

[0404] Based on the analysis results, the server generates a virtual proxy that mimics the user. This virtual proxy reflects the user's hobbies and preferences, and this data is recorded as agent characteristics.

[0405] Step 4:

[0406] A virtual agent (a virtual entity on a server) begins its activities in a virtual environment. Other virtual agents also exist in this environment and participate in virtual communities and forums. According to their configured preferences, virtual agents take an interest in relevant topics and interact with other agents.

[0407] Step 5:

[0408] The server continuously monitors and logs the activity of virtual agents, tracking which communities they participate in and what new data they collect. This provides additional insights into user interests.

[0409] Step 6:

[0410] The server re-analyzes the recorded activity logs, identifies new interests and behavioral changes, and updates the user's data profile accordingly. This information is generated as a report and imported into the company's data analytics tools.

[0411] (Example 1)

[0412] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0413] In modern society, where people's interests and preferences are diversifying, it is crucial to provide information and services tailored to individual users. However, conventional technologies have struggled to track changes in users' hobbies and preferences in real time, limiting the provision of personalized services. Furthermore, they have been unable to accurately capture users' dynamic interests, resulting in insufficient responses in situations where a high level of personalization is required.

[0414] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0415] In this invention, the server includes data collection means for collecting publicly available user information via a communication network, data analysis means for analyzing the collected data using natural language processing technology to extract the user's interests and preferences, and entity generation means for creating a pseudo-entity that mimics the user based on the extracted interests and preferences. This enables tracking of the user's diverse interests and preferences in real time and provides highly accurate personalized services.

[0416] "Data collection means" refers to a function that automatically acquires users' publicly available information via a communication network.

[0417] "Data analysis means" refers to a function that analyzes collected information using natural language processing technology to extract users' interests and preferences.

[0418] "Entity generation means" refers to a function that creates a pseudo-entity that mimics the user based on the user's interests and preferences obtained through analysis.

[0419] "Activity control means" refers to a function that controls how pseudo-entities act in a virtual space and acquire additional information.

[0420] "Information update means" refers to a function that re-analyzes acquired additional information and updates user behavior information.

[0421] A "pseudo-entity" refers to a virtual proxy that reflects the user's interests and preferences, and acts on behalf of the user within the virtual space.

[0422] This invention is a system designed to collect and analyze user-generated public information using data processing technology. In implementing the invention, the server includes a set of software and hardware environments necessary to collect and analyze data via a communication network and to generate pseudo-entities that can operate in a virtual environment.

[0423] First, the server uses API requests over the internet to collect publicly available user information from platforms such as social networking services (SNS). This includes text, profiles, and follow lists. The data is stored in a database on the server in JSON format.

[0424] The server analyzes the collected information using Python's natural language processing libraries (e.g., NLTK and SpaCy). This extracts user interests and preferences from the text and structures the data accordingly.

[0425] Based on the analysis results, the server generates pseudo-entities using Python scripts. These entities are designed as virtual proxies to simulate activities within a virtual space while reflecting the user's interests. A 3D simulation tool (e.g., Unity) is used for the virtual space.

[0426] For example, when a user frequently posts about travel, the server uses that data to generate a "travel-loving agent," who then participates in a virtual travel forum. Through such simulations, companies can gain deep insights into users' interests.

[0427] An example of a prompt message would be, "Please describe a system that generates a virtual proxy based on a user's SNS activity and simulates their activity in the community." This invention forms the foundation for providing personalized information services by gaining a deeper understanding of users' interests.

[0428] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0429] Step 1:

[0430] The server collects users' publicly available information via the communication network. Specifically, the server uses the SNS API to retrieve users' posted text, profile information, and follower lists. It receives the SNS's public ID as input and stores the data based on this ID in the database as collected data.

[0431] Step 2:

[0432] The server feeds the collected public information into a natural language processing engine. It analyzes the input text data using a natural language processing library (e.g., NLTK or SpaCy). By tokenizing the text data and performing keyword extraction and sentiment analysis, it understands the user's interests and preferences. As output, it generates a list of analyzed interest keywords.

[0433] Step 3:

[0434] The server generates virtual agents based on the analysis results. This uses an agent generation algorithm that sets attributes that reflect the user's interests and preferences. Based on the input interest keywords, it sets a profile for the pseudo-entity and outputs a virtual agent that is ready to operate in the virtual space.

[0435] Step 4:

[0436] The generated virtual agent begins its activities within a virtual environment. This virtual environment is built using a simulation platform (e.g., Unity). The server schedules the agent's participation in forums related to its interests and its communication with other virtual agents. It receives the virtual agent's profile and activity schedule as input and consequently records an activity log within the virtual environment.

[0437] Step 5:

[0438] The server re-analyzes the data obtained as a result of the virtual agent's activities. Specifically, it aggregates the acquired activity logs using data analysis tools (e.g., Pandas, NumPy) and organizes behavioral patterns. It evaluates the new insights gained by the virtual agent and updates the user's data profile. This allows for continuous tracking of changes in the user's interests and provides feedback to the database as needed.

[0439] (Application Example 1)

[0440] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0441] In today's information society, accurately understanding users' hobbies and preferences from vast amounts of data and providing them with relevant advertisements based on that information is difficult. Traditional methods struggle to track changes in user interests in real time and instantly present personalized advertisements, which contributes to a decline in marketing effectiveness.

[0442] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0443] In this invention, the server includes data collection means, data analysis means, and agent generation means. This makes it possible to generate a virtual agent based on the user's publicly available information, track the user's interests in real time, and dynamically generate and present personalized advertisements.

[0444] "Data collection means" refers to a device or program that has the function of automatically collecting publicly available information of users from the internet.

[0445] A "data analysis tool" is a program that uses natural language processing technology to analyze collected information and identify the user's hobbies and preferences.

[0446] "Agent generation means" refers to a device or program that has the function of generating a virtual agent based on the hobbies and preferences of a specified user.

[0447] "Process execution means" refers to a device or program that has the function of allowing a virtual agent to operate within a virtual environment and collect and update information.

[0448] "Output generation means" refers to a device or program that has the function of analyzing additional data acquired based on the activities of a virtual agent and outputting the results in a report or other format.

[0449] "Advertising generation and display means" refers to a device or program that has the function of generating appropriate advertisements based on the user's interests and preferences and displaying them on the user's device.

[0450] The system implementing this invention centers around a server built on a cloud environment. The server automatically collects users' publicly available information via the internet using data collection means. Specifically, it uses SNS APIs to store users' posts and public profile information in the server's data storage. Cloud services (e.g., AWS, Google Cloud) are used for the hardware.

[0451] Next, the server processes the collected information using data analysis tools. This analysis utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract hobbies and preferences from the text data. This identifies areas of interest based on keywords frequently mentioned by the user.

[0452] Based on extracted hobbies and preferences, the server uses an agent generation mechanism to create a virtual proxy for the user. The virtual proxy is programmed to replicate the user's characteristics and begins activities within the virtual environment. During these activities, the process execution mechanism absorbs information from relevant forums, leading to the discovery of new interests.

[0453] The results of the virtual agent's activities are re-analyzed by the output generation mechanism, and detailed behavioral patterns are generated as a report. Based on this, the server utilizes the ad generation and display mechanism to display personalized advertisements on the user's device. For example, if the user shows interest in a "new smartphone," advertisements for related new products will be displayed on the smartphone.

[0454] To effectively manage this process, a generative AI model can be used, and the following prompt message is entered into the generative AI model: "Design a process that analyzes user interests based on data obtained from social media, generates virtual agents, and then generates and displays the most suitable advertisements to users through those agents." This enables real-time ad optimization.

[0455] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0456] Step 1:

[0457] The server collects users' social media and other publicly available information via the internet using data collection methods. The collected data, including user posts and public profile information, is stored in data storage. The specific input is text data obtained via API, and the output is data stored in the database.

[0458] Step 2:

[0459] The server analyzes the collected information using data analysis tools. This process utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract keywords related to hobbies and preferences from the text data. The input is the text data collected in step 1, and the analysis results output data that identifies the user's interests. Specifically, the frequent occurrence of the word "travel" suggests an interest in travel.

[0460] Step 3:

[0461] The server uses an agent generation mechanism based on the analysis results to generate a virtual proxy for the user. This proxy is designed to reflect the user's interests and operate in a virtual environment. The input is the interest data extracted in step 2, and the output is the generation of a virtual proxy with the configured characteristics.

[0462] Step 4:

[0463] The device displays personalized advertisements to the user using ad generation and display mechanisms. The content of the advertisements is determined based on the activities of the virtual agent. The input is the recommendations obtained from the activities of the virtual agent, and the output is the advertisement displayed on the user's device. As a concrete example, advertisements for gadgets that the user has shown interest in are displayed.

[0464] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0465] This invention is implemented as a system that not only identifies hobbies and preferences from users' publicly available information, but also recognizes emotions using an emotion engine and reflects them in the activities of a virtual surrogate, thereby enabling more detailed data collection and analysis. This system consists of multiple modules managed on the cloud.

[0466] The server first collects information from users' social media and publicly available online sources through various data collection methods. This information includes text, images, and videos. This prepares the server to understand the overall picture of the user's online activities.

[0467] Next, the server analyzes the collected data using analytical tools to identify the user's hobbies and preferences. Natural language processing (NLP) technology is used for this purpose, enabling a deep understanding of the text data's content. Simultaneously, an emotion engine analyzes the sentiment of the text and posts within the data. This identifies emotions such as positive, negative, and neutral.

[0468] Based on the analysis results obtained, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy reflects the user's interests and emotions and can act based on different scenarios in the virtual environment. For example, if the user is interested in movies and has positive emotions, the virtual proxy will actively participate in movie-related forums.

[0469] When a virtual agent performs activities within the virtual environment, the server tracks these activities and records activity logs. Furthermore, the emotion engine analyzes emotions from the virtual agent's interactions and activities, and uses the results in the report generation system. Based on this data, the report generation system creates a detailed report and provides it in a format that can be used by the company.

[0470] For example, if user B has positive feelings about a "new music album" and frequently mentions it, virtual avatar B will become more active in the music community and exchange opinions with other avatars. Through this activity, subtle changes in user B's musical preferences and emotions can be analyzed, and the company can use this information to develop targeted marketing strategies.

[0471] Thus, the present invention enables more sophisticated data analysis that takes user emotions into account, and can support strategic decision-making by companies.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] The server automatically collects users' publicly available information from online platforms (such as social networking services and blogs). This information includes text, images, and videos, and is collected using public APIs and web scraping techniques.

[0475] Step 2:

[0476] The server feeds the collected information into the analysis engine. The analysis engine uses natural language processing technology to analyze the text data and identify the user's hobbies and preferences. The identified information is stored in a database. At the same time, the emotion engine analyzes the emotions in the text and records that information as well.

[0477] Step 3:

[0478] The server generates a virtual proxy based on the analysis results. Using the proxy generation mechanism, it constructs a virtual proxy that reflects the user's hobbies and emotions. This virtual proxy is a program that mimics the user's behavior and acts according to the set scenario.

[0479] Step 4:

[0480] A virtual proxy (operating via a server) begins its activities within a virtual environment. Various communities exist within this virtual environment, and the proxy participates in forums and chat groups related to the user's hobbies. The virtual proxy interacts with other proxies and acquires new data through these interactions.

[0481] Step 5:

[0482] The server monitors the virtual proxy's activities in real time and stores activity logs. The server meticulously records what content the proxy views and what kind of communication it engages in.

[0483] Step 6:

[0484] The server re-analyzes the accumulated activity logs. Using an emotion engine, it analyzes new emotional information obtained from the virtual proxy's activities to detect changes in the user's behavior patterns and interests. The results of this analysis are provided to the company as a report.

[0485] Through this process, companies can gain deep insights into users' emotions and interests, which they can then use to develop strategies for improving the customer experience.

[0486] (Example 2)

[0487] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0488] Conventional information gathering and analysis systems have the drawback of only identifying users' hobbies and preferences, without adequately performing data analysis and optimizing marketing strategies based on users' emotions and emotional changes. Furthermore, there has been a lack of effective data collection through virtual environment proxy activities and the provision of detailed reports based on that data.

[0489] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0490] In this invention, the server includes information gathering means for collecting publicly available information of users, analysis means for analyzing the collected information using natural language processing technology and analyzing emotions along with hobbies and preferences, and proxy generation means for generating virtual proxies based on the identified information. This enables analysis that includes changes in users' emotions and behavior, allowing companies to optimize their marketing strategies.

[0491] "Information gathering means" refers to a system that collects publicly available data on the internet and has the function of comprehensively obtaining information about users' online activities.

[0492] The "analysis method" is a system that utilizes natural language processing technology to identify users' hobbies and preferences from collected data, and further analyzes their emotions.

[0493] A "proxy generation means" is a device that has the function of generating a virtual proxy that reflects the user's hobbies, preferences, and emotions based on the analysis results.

[0494] "Means of activity" refers to a system in which a virtual agent operates within a virtual environment and has the function of acquiring meaningful data while exchanging information with other virtual agents.

[0495] The "report generation means" is a system that analyzes additional data acquired by the virtual agent and generates a detailed report in a format that can be used by the company.

[0496] This invention realizes a system that provides detailed data reports based on the user's emotions and interests through information gathering, data analysis, virtual proxy generation, and activity tracking. Specific embodiments of this system are described below.

[0497] First, the server uses information gathering tools to collect publicly available information from the internet, particularly from social networking services (SNS), including user text, images, and videos. This process typically involves utilizing APIs to acquire data from the internet; for example, this can be achieved by building analysis software that integrates with the Twitter API using Python.

[0498] Next, the server applies analytical methods to the collected data. Here, natural language processing (NLP) techniques are used to extract the user's hobbies and preferences from text information, and an emotion engine is used to determine emotional states such as positive, negative, and neutral. Specifically, natural language processing libraries such as NLTK and spaCy are used, and a BERT-based model is integrated for emotion analysis to perform complex text analysis.

[0499] Based on the analysis results, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy is designed to faithfully reflect the detected user's hobbies and emotions. The virtual proxy is created to operate within a virtual environment, and its activities are used in strategic planning in the company's relevant fields.

[0500] Furthermore, the activities of virtual agents are tracked in real time within the virtual environment through the activity mechanism and recorded by the server. This allows companies to gain a detailed understanding of changes in users' interests and emotional trends based on the information obtained from the activity logs.

[0501] Ultimately, the server uses a report generation mechanism to create a detailed report summarizing the analysis results, which is then provided to companies in a format that can be used for marketing strategies and product development.

[0502] For example, if a user expresses positive feelings towards a "new music album," this information is reflected in the virtual agent's activities in a virtual environment. The virtual agent actively exchanges opinions in music-related forums and provides consumer behavior data based on new music trends.

[0503] An example of a prompt for a generative AI model is: "Use data collected from social media to identify user preferences and emotions, and show how to utilize this information in marketing strategies through virtual representations."

[0504] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0505] Step 1:

[0506] The server collects publicly available data from the internet using various information gathering methods. Specifically, it uses SNS APIs to retrieve user posts and profile information in text, image, and video formats. User IDs and hashtags are provided as input, and a dataset of the retrieved multimedia content is generated as output.

[0507] Step 2:

[0508] The server processes the collected data using analytical tools. It uses natural language processing (NLP) techniques to analyze user interests from text data. Specifically, it uses the Python library NLTK to extract specific keywords and perform contextual analysis. The input is the text data collected in step 1, and the output is profile data indicating the user's hobbies and preferences.

[0509] Step 3:

[0510] Similarly, the server uses an emotion engine to analyze the sentiment of the text data. The BERT sentiment analysis model is used to determine whether the text is positive, negative, or neutral. The input is the text data from step 1, and the output is an evaluation value based on the sentiment analysis.

[0511] Step 4:

[0512] The server generates a virtual surrogate using a surrogate generation mechanism based on hobby, preference, and emotion data obtained from the analysis mechanism. This virtual surrogate is prepared to operate within the virtual environment with specific settings tailored to the user's profile. The analysis results from steps 2 and 3 are used as input, and the virtual surrogate's configuration data is generated as output.

[0513] Step 5:

[0514] Virtual agents operate within a virtual environment through various means of activity. They exchange information with other agents on specific forums and social media platforms. Input is the agent's configuration data, and output is logs of new data and information exchanges obtained during their activities.

[0515] Step 6:

[0516] The server analyzes the data acquired through the activity tools and generates a detailed report using the report generation tool. This report shows changes in user emotions and the evolution of their interests, which companies can use in their marketing strategies. The input is the activity data obtained in step 5, and the output is a detailed report for companies.

[0517] (Application Example 2)

[0518] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0519] In today's world, there is a demand for advertising personalization based on users' online activities. However, conventional systems are unable to accurately reflect users' emotions and real-time changes in their interests, resulting in ineffective ad delivery. This invention aims to solve this problem and provide a system that enables ad delivery that dynamically reflects users' emotions and interests.

[0520] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0521] In this invention, the server includes information acquisition means for collecting publicly available information of users, data analysis means for analyzing the collected publicly available information and identifying the user's hobbies and preferences, and proxy generation means for generating a virtual proxy for the user based on the identified hobbies, preferences, and emotional state. This makes it possible to generate and deliver advertisements based on the dynamic changes in the user's emotions and hobbies.

[0522] "User" refers to an individual or group that uses a system or device.

[0523] "Public information" refers to information such as text, images, and videos that are made publicly available on social media and the web.

[0524] "Means of information acquisition" refers to the mechanisms and processes for collecting publicly available information.

[0525] "Data analysis methods" refer to technologies and methods that analyze collected publicly available information to identify users' hobbies and preferences.

[0526] A "proxy generation method" refers to a process or system for generating a virtual proxy that reflects the user's interests and emotions.

[0527] A "virtual proxy" is a virtual entity that mimics the characteristics of a user and operates within an electronic environment.

[0528] "Electronic environment" refers to a virtually constructed information space, such as the internet or digital platforms.

[0529] "Means of activity" refers to the mechanism by which virtual agents generate and deliver advertisements within the electronic environment.

[0530] "Display method" refers to a method of displaying generated advertisements on a user's device and obtaining their response.

[0531] "Result generation means" refers to the technology and methods used to analyze data obtained based on user responses and create a final report.

[0532] "Response" refers to the actions or feedback that users give in response to the advertisements they see.

[0533] This invention is a system for realizing personalized advertising based on users' online activities. This system is configured as follows:

[0534] The server first collects publicly available information from users' social media and web presence using information acquisition tools. This information collection is performed using APIs and can handle various data formats such as text, images, and videos. The data analysis tool uses natural language processing (NLP) libraries (e.g., NLTK and SpaCy) to deeply analyze the collected data and identify the user's hobbies and preferences. Furthermore, sentiment analysis tools (e.g., IBM Watson and Google Cloud Natural Language) are used to identify emotions such as positive, negative, and neutral.

[0535] Next, the proxy generation means generates a virtual proxy based on identified preferences and emotional states. This virtual proxy operates within the electronic environment, dynamically generating and delivering personalized advertisements that respond to the user's emotional state. The advertisements are displayed on the user's device through the display means, and user responses are collected in real time. This creates a feedback loop for understanding the effectiveness of the advertisements.

[0536] The results generation method analyzes user response data further and generates detailed reports that companies can use. For example, if a user makes a positive post such as, "I want to go to the mountains on my next vacation! I want to relax in nature," this information is analyzed by the system, and advertisements for outdoor equipment and eco-tours are provided. The following prompt is used as input to the AI ​​model: "User's latest post: 'I want to go to the mountains on my next vacation! I want to relax in nature.' Please generate appropriate advertisements based on this post."

[0537] Thus, by implementing the present invention, it becomes possible to conduct advertising campaigns based on users' dynamic emotions and changing preferences, thereby maximizing advertising effectiveness.

[0538] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0539] Step 1:

[0540] The server collects publicly available information from users' social media and web presence using a valid API. Input is the user's public profile information, and output is text, image, and video data. The server stores this data in a temporary database.

[0541] Step 2:

[0542] The server uses a natural language processing (NLP) library to analyze the collected text data. The input is the text information obtained in step 1, and the output is the identification of the user's hobbies and preferences. Through NLP processing, the server extracts the user's interests from the context of each text and the frequency patterns of words.

[0543] Step 3:

[0544] The server uses sentiment analysis tools to identify emotions from the text in the collected data. The input is the text messages obtained in step 1, and the output is an emotion label such as positive, negative, or neutral. The server analyzes the emotions based on the tone and keywords of the text.

[0545] Step 4:

[0546] The server generates a virtual surrogate based on the user's interests and emotional state. The input is the analysis results from steps 2 and 3, and the output is the virtual surrogate's profile. The server utilizes a generative AI model to design a surrogate that reflects the user's characteristics.

[0547] Step 5:

[0548] The virtual agent operates within the electronic environment, generating and delivering appropriate advertisements. The input consists of the virtual agent's profile and the user's past behavioral history, while the output is personalized advertisements. The virtual agent uses a generative AI model to construct contextually relevant ad content.

[0549] Step 6:

[0550] The device displays advertisements generated by a virtual agent to the user and collects the user's responses. The input is the advertisement generated in step 5, and the output is the user's clicks and interaction information. The device aggregates the information through the user interface.

[0551] Step 7:

[0552] The server analyzes user response data to generate a detailed report. The input is the response information obtained in step 6, and the output is a performance report of the advertising campaign. The server performs data analysis and compiles insights that companies can use for their strategies.

[0553] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0554] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0555] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0556] [Fourth Embodiment]

[0557] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0558] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0559] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0560] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0561] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0562] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0563] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0564] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0565] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0566] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0567] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0568] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0569] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0570] The present invention is implemented as a series of programs and related processes in a system built on a cloud environment. Its specific form is described below.

[0571] First, the server automatically collects users' publicly available information via the internet. This information includes text posted by users on social media, public profile data, and public follower lists. The collected information is securely stored in the server's data storage.

[0572] Next, the server feeds the collected information into an analysis engine, which uses natural language processing technology to analyze the text data. This analysis allows the server to identify the user's hobbies and preferences. For example, if a user frequently posts words like "travel" or "cooking," these are classified as the user's interests.

[0573] Based on the analysis results, the server programmatically generates a virtual proxy that resembles the user. This virtual proxy is designed to replicate the user's hobbies and preferences, and for example, it operates within the virtual environment as a "travel-loving agent."

[0574] The generated virtual agent begins its activities in a virtual environment on the server. These activities include participating in forums aligned with the user's interests and communicating with other virtual agents. Over time, the virtual agent absorbs information within the virtual environment and can discover new interests.

[0575] The additional data obtained as a result of the virtual proxy's activities is analyzed again by the server and incorporated into the user's dataset as detailed behavioral patterns. This process makes it possible to continuously track how the user's interests are changing and what new interests they are developing.

[0576] As described above, this system allows companies to use data obtained from users' publicly available information to gain deeper insights through virtual agents. For example, if user A posts about a new movie, virtual agent A can participate in a virtual movie community and learn about movie reviews from other virtual agents. This activity allows companies to gain a deeper understanding of user A's movie interests.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] The server initiates a process to collect publicly available user information via the internet. This involves using SNS APIs and web scraping to gather profile information, posts, and public follower information. This data is then stored in the server's database.

[0580] Step 2:

[0581] The server sends the collected data to the analysis engine. The analysis engine uses natural language processing technology to extract the user's hobbies and preferences from the text. It analyzes frequently occurring topics and keywords to identify the user's areas of interest.

[0582] Step 3:

[0583] Based on the analysis results, the server generates a virtual proxy that mimics the user. This virtual proxy reflects the user's hobbies and preferences, and this data is recorded as agent characteristics.

[0584] Step 4:

[0585] A virtual agent (a virtual entity on a server) begins its activities in a virtual environment. Other virtual agents also exist in this environment and participate in virtual communities and forums. According to their configured preferences, virtual agents take an interest in relevant topics and interact with other agents.

[0586] Step 5:

[0587] The server continuously monitors and logs the activity of virtual agents, tracking which communities they participate in and what new data they collect. This provides additional insights into user interests.

[0588] Step 6:

[0589] The server re-analyzes the recorded activity logs, identifies new interests and behavioral changes, and updates the user's data profile accordingly. This information is generated as a report and imported into the company's data analytics tools.

[0590] (Example 1)

[0591] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0592] In modern society, where people's interests and preferences are diversifying, it is crucial to provide information and services tailored to individual users. However, conventional technologies have struggled to track changes in users' hobbies and preferences in real time, limiting the provision of personalized services. Furthermore, they have been unable to accurately capture users' dynamic interests, resulting in insufficient responses in situations where a high level of personalization is required.

[0593] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0594] In this invention, the server includes data collection means for collecting publicly available user information via a communication network, data analysis means for analyzing the collected data using natural language processing technology to extract the user's interests and preferences, and entity generation means for creating a pseudo-entity that mimics the user based on the extracted interests and preferences. This enables tracking of the user's diverse interests and preferences in real time and provides highly accurate personalized services.

[0595] "Data collection means" refers to a function that automatically acquires users' publicly available information via a communication network.

[0596] "Data analysis means" refers to a function that analyzes collected information using natural language processing technology to extract users' interests and preferences.

[0597] "Entity generation means" refers to a function that creates a pseudo-entity that mimics the user based on the user's interests and preferences obtained through analysis.

[0598] "Activity control means" refers to a function that controls how pseudo-entities act in a virtual space and acquire additional information.

[0599] "Information update means" refers to a function that re-analyzes acquired additional information and updates user behavior information.

[0600] A "pseudo-entity" refers to a virtual proxy that reflects the user's interests and preferences, and acts on behalf of the user within the virtual space.

[0601] This invention is a system designed to collect and analyze user-generated public information using data processing technology. In implementing the invention, the server includes a set of software and hardware environments necessary to collect and analyze data via a communication network and to generate pseudo-entities that can operate in a virtual environment.

[0602] First, the server uses API requests over the internet to collect publicly available user information from platforms such as social networking services (SNS). This includes text, profiles, and follow lists. The data is stored in a database on the server in JSON format.

[0603] The server analyzes the collected information using Python's natural language processing libraries (e.g., NLTK and SpaCy). This extracts user interests and preferences from the text and structures the data accordingly.

[0604] Based on the analysis results, the server generates pseudo-entities using Python scripts. These entities are designed as virtual proxies to simulate activities within a virtual space while reflecting the user's interests. A 3D simulation tool (e.g., Unity) is used for the virtual space.

[0605] For example, when a user frequently posts about travel, the server uses that data to generate a "travel-loving agent," who then participates in a virtual travel forum. Through such simulations, companies can gain deep insights into users' interests.

[0606] An example of a prompt message would be, "Please describe a system that generates a virtual proxy based on a user's SNS activity and simulates their activity in the community." This invention forms the foundation for providing personalized information services by gaining a deeper understanding of users' interests.

[0607] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0608] Step 1:

[0609] The server collects users' publicly available information via the communication network. Specifically, the server uses the SNS API to retrieve users' posted text, profile information, and follower lists. It receives the SNS's public ID as input and stores the data based on this ID in the database as collected data.

[0610] Step 2:

[0611] The server feeds the collected public information into a natural language processing engine. It analyzes the input text data using a natural language processing library (e.g., NLTK or SpaCy). By tokenizing the text data and performing keyword extraction and sentiment analysis, it understands the user's interests and preferences. As output, it generates a list of analyzed interest keywords.

[0612] Step 3:

[0613] The server generates virtual agents based on the analysis results. This uses an agent generation algorithm that sets attributes that reflect the user's interests and preferences. Based on the input interest keywords, it sets a profile for the pseudo-entity and outputs a virtual agent that is ready to operate in the virtual space.

[0614] Step 4:

[0615] The generated virtual agent begins its activities within a virtual environment. This virtual environment is built using a simulation platform (e.g., Unity). The server schedules the agent's participation in forums related to its interests and its communication with other virtual agents. It receives the virtual agent's profile and activity schedule as input and consequently records an activity log within the virtual environment.

[0616] Step 5:

[0617] The server re-analyzes the data obtained as a result of the virtual agent's activities. Specifically, it aggregates the acquired activity logs using data analysis tools (e.g., Pandas, NumPy) and organizes behavioral patterns. It evaluates the new insights gained by the virtual agent and updates the user's data profile. This allows for continuous tracking of changes in the user's interests and provides feedback to the database as needed.

[0618] (Application Example 1)

[0619] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0620] In today's information society, accurately understanding users' hobbies and preferences from vast amounts of data and providing them with relevant advertisements based on that information is difficult. Traditional methods struggle to track changes in user interests in real time and instantly present personalized advertisements, which contributes to a decline in marketing effectiveness.

[0621] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0622] In this invention, the server includes data collection means, data analysis means, and agent generation means. This makes it possible to generate a virtual agent based on the user's publicly available information, track the user's interests in real time, and dynamically generate and present personalized advertisements.

[0623] "Data collection means" refers to a device or program that has the function of automatically collecting publicly available information of users from the internet.

[0624] A "data analysis tool" is a program that uses natural language processing technology to analyze collected information and identify the user's hobbies and preferences.

[0625] "Agent generation means" refers to a device or program that has the function of generating a virtual agent based on the hobbies and preferences of a specified user.

[0626] "Process execution means" refers to a device or program that has the function of allowing a virtual agent to operate within a virtual environment and collect and update information.

[0627] "Output generation means" refers to a device or program that has the function of analyzing additional data acquired based on the activities of a virtual agent and outputting the results in a report or other format.

[0628] "Advertising generation and display means" refers to a device or program that has the function of generating appropriate advertisements based on the user's interests and preferences and displaying them on the user's device.

[0629] The system implementing this invention centers around a server built on a cloud environment. The server automatically collects users' publicly available information via the internet using data collection means. Specifically, it uses SNS APIs to store users' posts and public profile information in the server's data storage. Cloud services (e.g., AWS, Google Cloud) are used for the hardware.

[0630] Next, the server processes the collected information using data analysis tools. This analysis utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract hobbies and preferences from the text data. This identifies areas of interest based on keywords frequently mentioned by the user.

[0631] Based on extracted hobbies and preferences, the server uses an agent generation mechanism to create a virtual proxy for the user. The virtual proxy is programmed to replicate the user's characteristics and begins activities within the virtual environment. During these activities, the process execution mechanism absorbs information from relevant forums, leading to the discovery of new interests.

[0632] The results of the virtual agent's activities are re-analyzed by the output generation mechanism, and detailed behavioral patterns are generated as a report. Based on this, the server utilizes the ad generation and display mechanism to display personalized advertisements on the user's device. For example, if the user shows interest in a "new smartphone," advertisements for related new products will be displayed on the smartphone.

[0633] To effectively manage this process, a generative AI model can be used, and the following prompt message is entered into the generative AI model: "Design a process that analyzes user interests based on data obtained from social media, generates virtual agents, and then generates and displays the most suitable advertisements to users through those agents." This enables real-time ad optimization.

[0634] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0635] Step 1:

[0636] The server collects users' social media and other publicly available information via the internet using data collection methods. The collected data, including user posts and public profile information, is stored in data storage. The specific input is text data obtained via API, and the output is data stored in the database.

[0637] Step 2:

[0638] The server analyzes the collected information using data analysis tools. This process utilizes natural language processing techniques (e.g., NLTK, spaCy) to extract keywords related to hobbies and preferences from the text data. The input is the text data collected in step 1, and the analysis results output data that identifies the user's interests. Specifically, the frequent occurrence of the word "travel" suggests an interest in travel.

[0639] Step 3:

[0640] The server uses an agent generation mechanism based on the analysis results to generate a virtual proxy for the user. This proxy is designed to reflect the user's interests and operate in a virtual environment. The input is the interest data extracted in step 2, and the output is the generation of a virtual proxy with the configured characteristics.

[0641] Step 4:

[0642] The device displays personalized advertisements to the user using ad generation and display mechanisms. The content of the advertisements is determined based on the activities of the virtual agent. The input is the recommendations obtained from the activities of the virtual agent, and the output is the advertisement displayed on the user's device. As a concrete example, advertisements for gadgets that the user has shown interest in are displayed.

[0643] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0644] This invention is implemented as a system that not only identifies hobbies and preferences from users' publicly available information, but also recognizes emotions using an emotion engine and reflects them in the activities of a virtual surrogate, thereby enabling more detailed data collection and analysis. This system consists of multiple modules managed on the cloud.

[0645] The server first collects information from users' social media and publicly available online sources through various data collection methods. This information includes text, images, and videos. This prepares the server to understand the overall picture of the user's online activities.

[0646] Next, the server analyzes the collected data using analytical tools to identify the user's hobbies and preferences. Natural language processing (NLP) technology is used for this purpose, enabling a deep understanding of the text data's content. Simultaneously, an emotion engine analyzes the sentiment of the text and posts within the data. This identifies emotions such as positive, negative, and neutral.

[0647] Based on the analysis results obtained, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy reflects the user's interests and emotions and can act based on different scenarios in the virtual environment. For example, if the user is interested in movies and has positive emotions, the virtual proxy will actively participate in movie-related forums.

[0648] When a virtual agent performs activities within the virtual environment, the server tracks these activities and records activity logs. Furthermore, the emotion engine analyzes emotions from the virtual agent's interactions and activities, and uses the results in the report generation system. Based on this data, the report generation system creates a detailed report and provides it in a format that can be used by the company.

[0649] For example, if user B has positive feelings about a "new music album" and frequently mentions it, virtual avatar B will become more active in the music community and exchange opinions with other avatars. Through this activity, subtle changes in user B's musical preferences and emotions can be analyzed, and the company can use this information to develop targeted marketing strategies.

[0650] Thus, the present invention enables more sophisticated data analysis that takes user emotions into account, and can support strategic decision-making by companies.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server automatically collects users' publicly available information from online platforms (such as social networking services and blogs). This information includes text, images, and videos, and is collected using public APIs and web scraping techniques.

[0654] Step 2:

[0655] The server feeds the collected information into the analysis engine. The analysis engine uses natural language processing technology to analyze the text data and identify the user's hobbies and preferences. The identified information is stored in a database. At the same time, the emotion engine analyzes the emotions in the text and records that information as well.

[0656] Step 3:

[0657] The server generates a virtual proxy based on the analysis results. Using the proxy generation mechanism, it constructs a virtual proxy that reflects the user's hobbies and emotions. This virtual proxy is a program that mimics the user's behavior and acts according to the set scenario.

[0658] Step 4:

[0659] A virtual proxy (operating via a server) begins its activities within a virtual environment. Various communities exist within this virtual environment, and the proxy participates in forums and chat groups related to the user's hobbies. The virtual proxy interacts with other proxies and acquires new data through these interactions.

[0660] Step 5:

[0661] The server monitors the virtual proxy's activities in real time and stores activity logs. The server meticulously records what content the proxy views and what kind of communication it engages in.

[0662] Step 6:

[0663] The server re-analyzes the accumulated activity logs. Using an emotion engine, it analyzes new emotional information obtained from the virtual proxy's activities to detect changes in the user's behavior patterns and interests. The results of this analysis are provided to the company as a report.

[0664] Through this process, companies can gain deep insights into users' emotions and interests, which they can then use to develop strategies for improving the customer experience.

[0665] (Example 2)

[0666] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0667] Conventional information gathering and analysis systems have the drawback of only identifying users' hobbies and preferences, without adequately performing data analysis and optimizing marketing strategies based on users' emotions and emotional changes. Furthermore, there has been a lack of effective data collection through virtual environment proxy activities and the provision of detailed reports based on that data.

[0668] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0669] In this invention, the server includes information gathering means for collecting publicly available information of users, analysis means for analyzing the collected information using natural language processing technology and analyzing emotions along with hobbies and preferences, and proxy generation means for generating virtual proxies based on the identified information. This enables analysis that includes changes in users' emotions and behavior, allowing companies to optimize their marketing strategies.

[0670] "Information gathering means" refers to a system that collects publicly available data on the internet and has the function of comprehensively obtaining information about users' online activities.

[0671] The "analysis method" is a system that utilizes natural language processing technology to identify users' hobbies and preferences from collected data, and further analyzes their emotions.

[0672] A "proxy generation means" is a device that has the function of generating a virtual proxy that reflects the user's hobbies, preferences, and emotions based on the analysis results.

[0673] "Means of activity" refers to a system in which a virtual agent operates within a virtual environment and has the function of acquiring meaningful data while exchanging information with other virtual agents.

[0674] The "report generation means" is a system that analyzes additional data acquired by the virtual agent and generates a detailed report in a format that can be used by the company.

[0675] This invention realizes a system that provides detailed data reports based on the user's emotions and interests through information gathering, data analysis, virtual proxy generation, and activity tracking. Specific embodiments of this system are described below.

[0676] First, the server uses information gathering tools to collect publicly available information from the internet, particularly from social networking services (SNS), including user text, images, and videos. This process typically involves utilizing APIs to acquire data from the internet; for example, this can be achieved by building analysis software that integrates with the Twitter API using Python.

[0677] Next, the server applies analytical methods to the collected data. Here, natural language processing (NLP) techniques are used to extract the user's hobbies and preferences from text information, and an emotion engine is used to determine emotional states such as positive, negative, and neutral. Specifically, natural language processing libraries such as NLTK and spaCy are used, and a BERT-based model is integrated for emotion analysis to perform complex text analysis.

[0678] Based on the analysis results, the server generates a virtual proxy using a proxy generation mechanism. This virtual proxy is designed to faithfully reflect the detected user's hobbies and emotions. The virtual proxy is created to operate within a virtual environment, and its activities are used in strategic planning in the company's relevant fields.

[0679] Furthermore, the activities of virtual agents are tracked in real time within the virtual environment through the activity mechanism and recorded by the server. This allows companies to gain a detailed understanding of changes in users' interests and emotional trends based on the information obtained from the activity logs.

[0680] Ultimately, the server uses a report generation mechanism to create a detailed report summarizing the analysis results, which is then provided to companies in a format that can be used for marketing strategies and product development.

[0681] For example, if a user expresses positive feelings towards a "new music album," this information is reflected in the virtual agent's activities in a virtual environment. The virtual agent actively exchanges opinions in music-related forums and provides consumer behavior data based on new music trends.

[0682] An example of a prompt for a generative AI model is: "Use data collected from social media to identify user preferences and emotions, and show how to utilize this information in marketing strategies through virtual representations."

[0683] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0684] Step 1:

[0685] The server collects publicly available data from the internet using various information gathering methods. Specifically, it uses SNS APIs to retrieve user posts and profile information in text, image, and video formats. User IDs and hashtags are provided as input, and a dataset of the retrieved multimedia content is generated as output.

[0686] Step 2:

[0687] The server processes the collected data using analytical tools. It uses natural language processing (NLP) techniques to analyze user interests from text data. Specifically, it uses the Python library NLTK to extract specific keywords and perform contextual analysis. The input is the text data collected in step 1, and the output is profile data indicating the user's hobbies and preferences.

[0688] Step 3:

[0689] Similarly, the server uses an emotion engine to analyze the sentiment of the text data. The BERT sentiment analysis model is used to determine whether the text is positive, negative, or neutral. The input is the text data from step 1, and the output is an evaluation value based on the sentiment analysis.

[0690] Step 4:

[0691] The server generates a virtual surrogate using a surrogate generation mechanism based on hobby, preference, and emotion data obtained from the analysis mechanism. This virtual surrogate is prepared to operate within the virtual environment with specific settings tailored to the user's profile. The analysis results from steps 2 and 3 are used as input, and the virtual surrogate's configuration data is generated as output.

[0692] Step 5:

[0693] Virtual agents operate within a virtual environment through various means of activity. They exchange information with other agents on specific forums and social media platforms. Input is the agent's configuration data, and output is logs of new data and information exchanges obtained during their activities.

[0694] Step 6:

[0695] The server analyzes the data acquired through the activity tools and generates a detailed report using the report generation tool. This report shows changes in user emotions and the evolution of their interests, which companies can use in their marketing strategies. The input is the activity data obtained in step 5, and the output is a detailed report for companies.

[0696] (Application Example 2)

[0697] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] In today's world, there is a demand for advertising personalization based on users' online activities. However, conventional systems are unable to accurately reflect users' emotions and real-time changes in their interests, resulting in ineffective ad delivery. This invention aims to solve this problem and provide a system that enables ad delivery that dynamically reflects users' emotions and interests.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0700] In this invention, the server includes information acquisition means for collecting publicly available information of users, data analysis means for analyzing the collected publicly available information and identifying the user's hobbies and preferences, and proxy generation means for generating a virtual proxy for the user based on the identified hobbies, preferences, and emotional state. This makes it possible to generate and deliver advertisements based on the dynamic changes in the user's emotions and hobbies.

[0701] "User" refers to an individual or group that uses a system or device.

[0702] "Public information" refers to information such as text, images, and videos that are made publicly available on social media and the web.

[0703] "Means of information acquisition" refers to the mechanisms and processes for collecting publicly available information.

[0704] "Data analysis methods" refer to technologies and methods that analyze collected publicly available information to identify users' hobbies and preferences.

[0705] A "proxy generation method" refers to a process or system for generating a virtual proxy that reflects the user's interests and emotions.

[0706] A "virtual proxy" is a virtual entity that mimics the characteristics of a user and operates within an electronic environment.

[0707] "Electronic environment" refers to a virtually constructed information space, such as the internet or digital platforms.

[0708] "Means of activity" refers to the mechanism by which virtual agents generate and deliver advertisements within the electronic environment.

[0709] "Display method" refers to a method of displaying generated advertisements on a user's device and obtaining their response.

[0710] "Result generation means" refers to the technology and methods used to analyze data obtained based on user responses and create a final report.

[0711] "Response" refers to the actions or feedback that users give in response to the advertisements they see.

[0712] This invention is a system for realizing personalized advertising based on users' online activities. This system is configured as follows:

[0713] The server first collects publicly available information from users' social media and web presence using information acquisition tools. This information collection is performed using APIs and can handle various data formats such as text, images, and videos. The data analysis tool uses natural language processing (NLP) libraries (e.g., NLTK and SpaCy) to deeply analyze the collected data and identify the user's hobbies and preferences. Furthermore, sentiment analysis tools (e.g., IBM Watson and Google Cloud Natural Language) are used to identify emotions such as positive, negative, and neutral.

[0714] Next, the proxy generation means generates a virtual proxy based on identified preferences and emotional states. This virtual proxy operates within the electronic environment, dynamically generating and delivering personalized advertisements that respond to the user's emotional state. The advertisements are displayed on the user's device through the display means, and user responses are collected in real time. This creates a feedback loop for understanding the effectiveness of the advertisements.

[0715] The results generation method analyzes user response data further and generates detailed reports that companies can use. For example, if a user makes a positive post such as, "I want to go to the mountains on my next vacation! I want to relax in nature," this information is analyzed by the system, and advertisements for outdoor equipment and eco-tours are provided. The following prompt is used as input to the AI ​​model: "User's latest post: 'I want to go to the mountains on my next vacation! I want to relax in nature.' Please generate appropriate advertisements based on this post."

[0716] Thus, by implementing the present invention, it becomes possible to conduct advertising campaigns based on users' dynamic emotions and changing preferences, thereby maximizing advertising effectiveness.

[0717] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0718] Step 1:

[0719] The server collects publicly available information from users' social media and web presence using a valid API. Input is the user's public profile information, and output is text, image, and video data. The server stores this data in a temporary database.

[0720] Step 2:

[0721] The server uses a natural language processing (NLP) library to analyze the collected text data. The input is the text information obtained in step 1, and the output is the identification of the user's hobbies and preferences. Through NLP processing, the server extracts the user's interests from the context of each text and the frequency patterns of words.

[0722] Step 3:

[0723] The server uses sentiment analysis tools to identify emotions from the text in the collected data. The input is the text messages obtained in step 1, and the output is an emotion label such as positive, negative, or neutral. The server analyzes the emotions based on the tone and keywords of the text.

[0724] Step 4:

[0725] The server generates a virtual surrogate based on the user's interests and emotional state. The input is the analysis results from steps 2 and 3, and the output is the virtual surrogate's profile. The server utilizes a generative AI model to design a surrogate that reflects the user's characteristics.

[0726] Step 5:

[0727] The virtual agent operates within the electronic environment, generating and delivering appropriate advertisements. The input consists of the virtual agent's profile and the user's past behavioral history, while the output is personalized advertisements. The virtual agent uses a generative AI model to construct contextually relevant ad content.

[0728] Step 6:

[0729] The device displays advertisements generated by a virtual agent to the user and collects the user's responses. The input is the advertisement generated in step 5, and the output is the user's clicks and interaction information. The device aggregates the information through the user interface.

[0730] Step 7:

[0731] The server analyzes user response data to generate a detailed report. The input is the response information obtained in step 6, and the output is a performance report of the advertising campaign. The server performs data analysis and compiles insights that companies can use for their strategies.

[0732] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0733] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0734] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0735] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0736] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0737] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0738] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0739] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0740] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0741] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0742] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0743] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0744] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0745] 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.

[0746] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0747] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0748] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0749] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0750] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0751] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0752] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0753] The following is further disclosed regarding the embodiments described above.

[0754] (Claim 1)

[0755] Information gathering means for collecting publicly available information from users,

[0756] An analytical method that analyzes collected public information to identify users' hobbies and preferences,

[0757] A proxy generation means that generates a virtual proxy for a user based on their identified hobbies and preferences,

[0758] A means by which a virtual agent operates within a virtual environment and acquires additional data,

[0759] A report generation means that analyzes the acquired additional data and generates a report,

[0760] A system that includes this.

[0761] (Claim 2)

[0762] The system according to claim 1, further comprising means for a virtual agent to acquire new information about the user's interests by interacting with other virtual agents.

[0763] (Claim 3)

[0764] The system according to claim 1, further comprising means for detecting changes in user interests by recording activity logs of generated virtual agents and analyzing user behavior patterns.

[0765] "Example 1"

[0766] (Claim 1)

[0767] A data collection method that collects users' publicly available information via a communication network,

[0768] A data analysis method that uses natural language processing technology to analyze collected data and extract users' interests and preferences,

[0769] An entity generation means that creates a pseudo-entity that mimics the user based on extracted interests and preferences,

[0770] An activity control means by which a pseudo-entity behaves in a virtual space and acquires additional information,

[0771] An information update means that re-analyzes the acquired additional information and updates the user's behavior information,

[0772] A system that includes this.

[0773] (Claim 2)

[0774] The system according to claim 1, further comprising means for pseudo-entities to interact with other pseudo-entities and to obtain new information of the user's interests.

[0775] (Claim 3)

[0776] The system according to claim 1, further comprising means for maintaining a record of the actions of the created pseudo-entities, analyzing the user's behavioral characteristics, and identifying changes in the user's interests.

[0777] "Application Example 1"

[0778] (Claim 1)

[0779] A data collection method for collecting publicly available user information,

[0780] A data analysis method that analyzes collected public information to identify users' hobbies and preferences,

[0781] An agent generation means that generates a virtual surrogate for a user based on their identified hobbies and preferences,

[0782] A virtual proxy operates within a virtual environment and is a process execution means for acquiring additional data,

[0783] An output generation means that analyzes the acquired additional data and generates a report,

[0784] An advertising generation and display means that generates and displays advertisements tailored to the user based on the activities of a virtual agent,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, further comprising a method for obtaining new information about a user's interests by having a virtual agent interact with other virtual agents.

[0788] (Claim 3)

[0789] The system according to claim 1, further comprising a method for detecting changes in a user's interests by recording the activities of a generated virtual proxy and analyzing the user's behavioral patterns.

[0790] "Example 2 of combining an emotion engine"

[0791] (Claim 1)

[0792] Information gathering means for collecting publicly available information from users,

[0793] An analytical means that analyzes collected public information and uses natural language processing technology to identify users' hobbies and preferences, as well as analyze their emotions.

[0794] A proxy generation means that generates a virtual proxy for a user based on their identified hobbies, preferences, and emotions,

[0795] A means of operation in which a virtual agent operates within a virtual environment and acquires additional data by exchanging information with other virtual agents,

[0796] A reporting means that analyzes acquired additional data to generate a detailed report that can be used by the company,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, further comprising means for obtaining new information about the user's interests and emotions by having a virtual agent interact with other virtual agents.

[0800] (Claim 3)

[0801] The system according to claim 1, further comprising means for recording activity logs of generated virtual agents and detecting changes in user behavior patterns and emotions through analysis including sentiment analysis.

[0802] "Application example 2 of combining emotional engines"

[0803] (Claim 1)

[0804] Information acquisition means for collecting publicly available information from users,

[0805] A data analysis method that analyzes collected public information to identify users' hobbies and preferences,

[0806] A proxy generation means that generates a virtual proxy for a user based on their identified hobbies, preferences, and emotional state,

[0807] A means of operation in which a virtual agent operates within an electronic environment and dynamically generates advertisements,

[0808] A display means that displays the generated advertisement on the user's device and obtains their response,

[0809] A result generation means that analyzes additional data obtained based on the response and generates a report,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, further comprising means for virtual agents to interact with other virtual agents and share their interests and emotional states in order to acquire new information about the user's interests.

[0813] (Claim 3)

[0814] The system according to claim 1, further comprising means for accumulating activity records of generated virtual agents, analyzing changes in user behavior trends, and identifying the evolution of interests. [Explanation of Symbols]

[0815] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information gathering means for collecting publicly available information from users, An analytical method that analyzes collected public information to identify users' hobbies and preferences, A proxy generation means that generates a virtual proxy for a user based on their identified hobbies and preferences, A means by which a virtual agent operates within a virtual environment and acquires additional data, A report generation means that analyzes the acquired additional data and generates a report, A system that includes this.

2. The system according to claim 1, further comprising means for a virtual agent to acquire new information about the user's interests by interacting with other virtual agents.

3. The system according to claim 1, further comprising means for detecting changes in the user's interests by recording activity logs of the generated virtual proxy and analyzing the user's behavior patterns.

Images