system

Abstract

We provide the system. [Solution] A means of generating a virtual person profile using a generative AI model based on user information collected from data sources, A means for designing and providing multiple simulation situations based on a generated virtual character profile, A method for analyzing the results of the simulation and extracting evaluation and improvement points for each virtual character, 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, and includes 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional training programs, it is difficult for participants to fully experience the diversity in the actual work environment and interactions with customers. As a result, there is a problem that when participants face unpredictable situations, they cannot respond appropriately. Furthermore, the lack of sufficient resources and realistic information for simulating personas is also a problem. It is necessary to solve these problems.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that includes means for generating a virtual person profile using a generation AI model based on user information collected from a data source, means for designing and providing multiple simulation situations based on the generated virtual person profile, and means for analyzing the results of the simulation situations and extracting evaluation and improvement points for each virtual person profile. As a result, training participants can experience diverse and realistic work environments through simulation and enhance their practical skills. Furthermore, by presenting individualized improvement suggestions suitable for the generated virtual person profile, it is possible to improve their ability to respond more concretely.

[0006] A "data source" is an external information source that provides data necessary for generating a virtual profile, such as user information and statistical data.

[0007] "User information" refers to data that characterizes an individual, such as demographic data and behavioral history, and is used to generate a virtual profile of that person.

[0008] A "generative AI model" is an artificial intelligence program that uses algorithms to create a virtual human profile based on collected data.

[0009] A "virtual character profile" is a person profile generated by a generative AI model, possessing fictional characteristics and behavioral patterns.

[0010] A "simulation scenario" is a reproduction of a specific work environment or customer interaction scene, designed based on a hypothetical persona.

[0011] "Analysis" is the process of thoroughly analyzing the results of a simulation to identify areas for improvement and evaluation of the hypothetical character.

[0012] "Evaluation" is the act of measuring the effectiveness and quality of responses in a simulated situation and showing them using numerical values ​​or indicators.

[0013] "Areas for improvement" refer to the parts that need to be modified based on the analysis of the simulation results, in order to improve efficiency and responsiveness.

[0014] A "personalized improvement plan" is a specific proposal for behavioral improvements tailored to each individual's hypothetical profile. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

[0019] In the following embodiments, 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.

[0020] 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, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

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

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

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

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0036] As an embodiment for carrying out the present invention, the system is configured according to the following procedure.

[0037] First, the server collects user information from data sources. This information includes age group, occupation, region, hobbies, and behavioral patterns, and is used as input data to generate a virtual profile of the person. The server preprocesses this data, removing outliers and imputing missing values, to prepare it for input into the model.

[0038] Subsequently, the server runs the generation AI model and generates a virtual profile based on the pre-processed user information. For example, it outputs a virtual person with various characteristics, such as a virtual person with purchasing behavior and information gathering tendencies specific to a particular age group, or a virtual person whose occupation is an engineer and whose hobby is the outdoors.

[0039] Next, the server designs simulation scenarios based on the generated virtual character profile. These include situations such as customer service at a tourist information center or handling customer complaints at a retail store. Each scenario reflects the specific behavioral patterns and requests of that virtual character profile.

[0040] On the other hand, the terminal presents the user with a list of available virtual character profiles and simulation situations through its user interface. The user can view this list and make selections that suit their training and learning objectives.

[0041] When the user makes a selection, the device retrieves the corresponding simulation data from the server and runs the simulation. The user can experience this situation in real time on the device. As the simulation progresses, the user takes actions according to the scenario and can check the results immediately.

[0042] Finally, user feedback is sent to the server via the terminal. The server aggregates this feedback and uses an evaluation model that analyzes the simulation results to quantify and evaluate the effectiveness of the responses for each virtual character. Subsequently, improvement suggestions tailored to each individual virtual character are automatically generated and presented to the user. In this way, users can continuously improve their skills and acquire the ability to respond in situations similar to actual work.

[0043] In the above configuration, the present invention can provide practical training tailored to diverse work environments and customer needs.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server begins collecting user information from data sources. The collected data includes detailed information such as age, gender, region, hobbies, occupation, and purchase history. This data is used as the basis for generating a virtual profile.

[0047] Step 2:

[0048] The server performs data preprocessing on the collected user information. Specifically, it cleanses the data by imputing missing values ​​and filtering outliers, and converts the data into a format suitable for the AI ​​model.

[0049] Step 3:

[0050] The server runs a generative AI model, using pre-processed data as input to generate virtual character profiles with various characteristics. These generated character profiles reflect specific behavioral patterns and preferences.

[0051] Step 4:

[0052] Based on the generated virtual character profile, the server begins designing various simulation scenarios. These include typical customer interaction scenarios and problem-solving situations, with customized content tailored to the characteristics of the virtual character profile.

[0053] Step 5:

[0054] The terminal generates a user interface, displaying to the user a list of options for each virtual character and their corresponding simulation situation. This interface is designed to be intuitive and easy to use.

[0055] Step 6:

[0056] The user selects a virtual character and simulation scenario of interest through their device. Based on this selection, the system is prepared to run the simulation.

[0057] Step 7:

[0058] The terminal receives selected simulation data from the server and executes the simulation. The user experiences the scenario on the terminal and responds to the displayed challenges.

[0059] Step 8:

[0060] After the simulation is complete, the device will display a screen for user feedback, allowing users to provide feedback based on their experience.

[0061] Step 9:

[0062] The server evaluates the results of the simulation based on feedback received from the user. Using an evaluation model, it analyzes the quality of responses to each virtual character and identifies areas for improvement.

[0063] Step 10:

[0064] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to obtain concrete guidelines for continuously improving their response capabilities.

[0065] (Example 1)

[0066] 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."

[0067] In today's diverse work environments, efficiently providing practical training and supporting the skill development of users is a crucial challenge. However, traditional training methods struggle to create hypothetical situations tailored to individual users and to present specific improvement measures appropriate to those situations. As a result, users are unable to effectively acquire individualized problem-solving skills.

[0068] 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.

[0069] In this invention, the server includes means for preprocessing user information obtained from a data source by removing outliers and imputing missing values; means for generating a virtual person profile using a generative AI model based on the preprocessed user information; and means for designing specific behavioral patterns and requests as simulation situations based on the generated virtual person profile. This enables the provision of practical training tailored to individual learning objectives, allowing users to improve their skills more effectively.

[0070] A "data source" is a fundamental location or system for collecting information, from which user information is obtained.

[0071] "User information" refers to data such as age group, occupation, region, hobbies, and behavioral patterns, and is basic information used to generate a virtual profile.

[0072] An "outlier" refers to a value in the data that falls outside the normal range and is removed because it may impair the accuracy of the data.

[0073] "Missing values" refer to values ​​that are missing from a dataset, and data integrity is maintained by imputing these missing values.

[0074] "Preprocessing" refers to a series of preparatory processes to prepare data so that it can be used appropriately by AI models.

[0075] A "generative AI model" is an algorithm or system designed to generate a virtual human profile using machine learning techniques.

[0076] A "virtual character profile" is a fictional character profile with specific characteristics and behavioral patterns, generated by an AI model based on collected user information.

[0077] A "simulation situation" is a specific scenario or environment designed based on a virtual character, and is a virtual situation for the user to experience.

[0078] An "evaluation model" is an algorithm or system used to analyze the results of a simulation and quantify and evaluate the effectiveness of the corresponding actions for each virtual character.

[0079] An "improvement plan" refers to modifications or improvements proposed based on the results of a simulation to make a particular response more effective.

[0080] This invention relates to a system for generating a virtual character and providing a simulation based on that character. The following elements are important for carrying out this invention.

[0081] First, the server collects user information from the data source. At this stage, it connects to the database using an API and collects user information such as age group, occupation, region, hobbies, and behavioral patterns. The acquired data is preprocessed using the Pandas library by removing outliers and imputing missing values ​​with the median. This preprocessing process facilitates data input into the generative AI model.

[0082] Subsequently, the server runs a pre-trained generative AI model using machine learning libraries such as TENSORFLOW® to generate a virtual profile based on pre-processed user information. This model can generate diverse virtual profiles with specific characteristics. For example, if a virtual profile is generated of a "male engineer in his 30s with an outdoor hobby," it can analyze his purchasing tendencies and preferences.

[0083] The server then designs a simulation that reflects specific behavioral patterns and requests based on the generated virtual character profile. This simulation situation is constructed, for example, as a customer service or complaint handling scenario, facilitating a practical user experience.

[0084] Next, the terminal uses a web browser to present the user with a list of virtual character profiles and simulation scenarios. The user can then select a simulation that suits their purpose. Once the selection is complete, the terminal retrieves the corresponding simulation data from the server and executes the simulation in real time. For example, in customer service training, the user can interact with a virtual customer in a conversational format and immediately see the results.

[0085] Ultimately, user feedback is sent from the terminal to the server. The server aggregates this feedback and analyzes the simulation results using an evaluation model. Based on these results, improvement suggestions tailored to a specific hypothetical persona are generated and provided to the user. This allows users to continuously improve themselves and acquire skills relevant to their work.

[0086] As a concrete example, a prompt such as, "What products would you recommend for a male engineer in his 30s whose hobby is camping?" will prompt the system to suggest products that match the user's purchasing tendencies and interests based on that profile. In this way, the invention provides users with practical and personalized learning and training opportunities.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The server collects user information from the data source. In this step, it uses an API to connect to the database and retrieve information such as age group, occupation, region, hobbies, and behavioral patterns. The input is raw data from the database, and the output is structured user information.

[0090] Step 2:

[0091] The server preprocesses the acquired data. Specifically, it uses the Pandas library to remove outliers and impute missing values. The input is the output data from step 1, and the quality is improved through data cleansing, resulting in preprocessed data as output.

[0092] Step 3:

[0093] The server generates a virtual human profile using a generative AI model. Preprocessed data is input into the model using the TensorFlow library. The data calculations performed here involve extracting and combining data features. The output is a virtual human profile with diverse characteristics.

[0094] Step 4:

[0095] The server designs the simulation situation based on the generated virtual character profile. Specific scenarios are created reflecting the characteristics obtained from the generated AI model. The input is the output from step 3, and the output is simulation environment data that constitutes a specific behavioral pattern.

[0096] Step 5:

[0097] The terminal presents the user with a list of virtual character profiles and simulation situations via a web browser. The user then selects a scenario that suits their learning objectives. The input is the output data from step 4, and the selectable interfaces are output.

[0098] Step 6:

[0099] When the user selects a scenario, the terminal retrieves the corresponding simulation data from the server and executes the simulation. For example, in a customer service simulation, the user interacts with a virtual customer in real time. The input is the scenario selected by the user in step 5, and the output is a real-time simulation exercise.

[0100] Step 7:

[0101] The system collects user feedback and sends it from the terminal to the server. The server uses the feedback to run an evaluation model and analyzes the simulation results. The input is the user's actions during the simulation and their feedback, and the output is quantified evaluation data as a result of the analysis.

[0102] Step 8:

[0103] The server generates improvement suggestions based on the analyzed data and presents them to the user. Using a generation AI model, it automatically derives specific improvement measures for a particular virtual character. The input is the evaluation data from step 7, and the output is customized advice presented to the user.

[0104] (Application Example 1)

[0105] 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."

[0106] Conventional customer service training systems have drawbacks, such as difficulty in providing practical training that closely matches actual work situations and difficulty in obtaining efficient feedback to improve individual customer service skills. This invention aims to effectively improve customer service skills in actual stores through individualized simulations using a virtual persona.

[0107] 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.

[0108] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation scenarios tailored to customer service content in a physical store based on the generated virtual person profile; and means for analyzing the results of the simulation scenarios and extracting evaluation and improvement points for each virtual person profile. This enables users to receive training in an environment close to actual work while obtaining specific feedback based on their individual responses.

[0109] A "data source" is a source of information used to collect information about a user, and this includes online data and user profile information.

[0110] A "generative AI model" is an artificial intelligence model that generates a virtual human profile from input data, thereby constructing the human profile used in virtual simulations.

[0111] A "virtual character profile" is a model of a non-existent person generated based on user information, possessing characteristics such as age group, hobbies, and behavioral patterns.

[0112] A "simulation scenario" is a scenario that mimics a situation corresponding to a hypothetical person, and is intended to reproduce real-world situations in customer service training.

[0113] A "real-time customer service training scenario" is a scenario that allows users to simulate and practice customer service procedures on the spot under conditions similar to those in an actual store.

[0114] A "smart device" is a portable electronic device used to support simulations and virtual reality, and examples include smart glasses and mobile devices.

[0115] A "user interface" refers to the screens and functions that allow users to interact with a system, and is used for selecting and experiencing simulations.

[0116] "Personalized improvement suggestions" refer to specific improvement methods and advice provided to users based on a hypothetical person profile and the results of simulations based on that profile.

[0117] The system implementing this invention consists of a server and a terminal with a user interface. The server continuously collects user information from data sources, preprocesses the collected data to remove outliers, and imputes missing values. The hardware includes a computer server used to efficiently perform data processing. The software includes programs using Python or TensorFlow to support this process.

[0118] Pre-processed user information is input into a generating AI model. This model uses machine learning algorithms to generate a virtual profile of a person. Specific examples include hypothetical customer profiles with different age groups and hobbies, which serve as the basis for diverse customer service simulations.

[0119] Based on the generated virtual character profile, the server designs a simulation that mimics customer service situations in a real store. The simulation content is structured around specific scenarios to allow store employees to receive customer service training. For example, it includes scenarios such as "introducing new products" and "handling customer complaints."

[0120] The terminal uses smart devices (e.g., smart glasses) to present these simulation scenarios to the user. Through these, the user can conduct customer service training in an environment that closely resembles a real store. The user interface on the terminal uses a real-time simulation application based on Unity.

[0121] After the simulation, user feedback is sent back to the server. The server analyzes the simulation results based on this feedback and extracts evaluations and areas for improvement for each virtual character. This information is provided to the user and displayed as personalized improvement suggestions.

[0122] An example of a prompt is: "Generate a customer service scenario that increases the interest of a 25-year-old woman living in area A, whose hobby is fashion shopping, in a new product." Using prompts like this, simulations tailored to each hypothetical character can be efficiently generated.

[0123] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0124] Step 1:

[0125] The server collects user information from data sources. This includes data such as age, occupation, region, hobbies, and behavioral patterns. Based on the collected information, outliers are removed and missing values ​​are imputed to prepare the input data for the generative AI model. Preprocessing is performed using Python and the NumPy library to create a clean dataset. The input to this process is raw user data, and the output is preprocessed user information.

[0126] Step 2:

[0127] The server inputs pre-processed user information into a generation AI model to generate a virtual profile. TensorFlow is used for this generation. Pre-formatted user information is provided as input, and a characterized virtual profile is obtained as output. For example, it can generate profiles with purchasing tendencies and information gathering tendencies.

[0128] Step 3:

[0129] The server designs simulation scenarios for use in physical stores based on the generated virtual character profiles. Prompt statements are used in the scenario design, constructing scenarios that include dialogue and behavioral patterns aligned with the generated character profiles. The inputs are the virtual character profiles and prompt statements, and the output is the completed scenario. This process involves programming the scenario logic using a scripting language.

[0130] Step 4:

[0131] The terminal presents scenarios to the user via a smart device and conducts customer service training. The user experiences virtual scenarios in real time through smart glasses or similar devices and learns how to respond. The input is scenario data, and the output is user behavior data and feedback. In this process, the Unity engine is used to render the simulation environment in real time.

[0132] Step 5:

[0133] User feedback is sent to the server, where the results are analyzed to extract evaluations and areas for improvement. This uses a machine learning model to quantify user interaction skills. The input is user feedback, and the output is the analysis results and areas for improvement. Based on the collected data, the analysis model is run using Scikit-learn.

[0134] Step 6:

[0135] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to confirm specific directions for skill improvement. The input is the analysis results, and the output is the improvement suggestion report. A text formatting program is used to improve the readability of the report.

[0136] 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.

[0137] As an embodiment for carrying out the present invention, a system incorporating an emotion engine is configured as follows:

[0138] First, the server collects user information from data sources and generates a virtual profile using a generative AI model. The collected data includes detailed information such as age, gender, region, hobbies, and occupation. Based on this information, the server designs a simulation scenario that corresponds to the virtual profile. This process includes customer service simulations and customer interaction simulations.

[0139] Furthermore, this invention uses an emotion engine to recognize the user's emotions in real time. Through cameras and sensors installed in the terminal, it detects emotions from the user's facial expressions, tone of voice, heart rate, etc. For example, if the user feels stressed during a simulation, the emotion engine recognizes that emotion and sends a signal to the server.

[0140] The server automatically adjusts the content and difficulty of the simulation situation based on the transmitted emotion data. For example, if it determines that the user is relaxed, it can speed up the scenario or present more complex challenges. On the other hand, if the user is confused, it provides guidance and additional support information to help them learn.

[0141] Users experience these simulations on their devices, and the emotion engine monitors the feedback generated during the process, allowing them to understand their own reactions and areas for improvement in real time. Once the simulation is complete, the server analyzes the user's emotional history and simulation results, and presents personalized improvement suggestions. These suggestions may include not only future response methods but also techniques for emotional control.

[0142] In the above configuration, the present invention can provide a flexible simulation environment that responds to the user's emotions, thereby enabling more effective improvement of practical skills.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The server collects user information from data sources. This data includes many attributes such as age, gender, occupation, region, and past purchase history. This data is used as a basis for generating highly accurate virtual profiles of individuals.

[0146] Step 2:

[0147] The server preprocesses the collected data and uses a generative AI model to generate diverse virtual personas. These include personas with specific behavioral patterns and preferences. For example, personas such as a travel enthusiast in their 30s living in a city or a forty-something engineer raising children are generated.

[0148] Step 3:

[0149] The server designs various simulation scenarios based on the generated virtual character profile. For example, these include situations such as customer service in retail or handling complaints at a customer support center, with content tailored to the characteristics of the virtual character.

[0150] Step 4:

[0151] The terminal presents the user with a selection of virtual character profiles and simulation scenarios via a user interface. The user selects a scenario suitable for their skill development and initiates the simulation.

[0152] Step 5:

[0153] The emotion engine built into the device monitors the user's facial expressions, voice tone, and biometric information through the camera and microphone to detect the user's emotional state in real time.

[0154] Step 6:

[0155] The emotion engine sends the user's emotional state to the server in real time, and the server adaptively adjusts the simulation's situation and difficulty based on that data. For example, when the user is frustrated, the server increases the amount of information provided or strengthens the assistance.

[0156] Step 7:

[0157] The user progresses through the simulation on the device and performs tasks requested during the session. The emotion engine monitors the user's emotions and continuously sends data to the server.

[0158] Step 8:

[0159] Once the simulation is complete, the terminal presents the user with feedback and an evaluation of the entire session. Based on the sentiment data, the server generates personalized improvement suggestions tailored to the user and provides them to the user through the terminal.

[0160] Step 9:

[0161] Based on this feedback and suggestions for improvement, users can revise their future learning plans and approaches, helping them to improve their skills.

[0162] (Example 2)

[0163] 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".

[0164] In modern society, there is a demand for flexible and effective simulation environments tailored to the characteristics of users. However, conventional simulation systems have the challenge of being unable to dynamically adjust to users' real-time emotions, making it difficult to support deep experiences and skill improvement.

[0165] 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.

[0166] In this invention, the server includes means for collecting user information and generating a virtual person profile using a generative model; means for designing multiple virtual situations based on the virtual person profile; and means for recognizing the user's emotions in real time through a detection device installed in the terminal and processing that information. This enables dynamic adjustment of the simulation situation based on the user's emotions.

[0167] "User information" refers to detailed attribute data of an individual, such as age, gender, region, hobbies, and occupation.

[0168] A "generative model" refers to an artificial intelligence algorithm or program used to create a virtual persona based on given data.

[0169] A "virtual person profile" refers to a fictional human profile generated based on collected user information.

[0170] A "virtual situation" refers to various simulation environments designed based on a fictional character profile, which users then experience.

[0171] A "terminal" refers to a device equipped with devices such as cameras and sensors, which functions as an interface with the user.

[0172] A "detection device" refers to a device that collects data such as the user's facial expressions, voice tone, and heart rate, enabling emotional analysis.

[0173] "Real-time" refers to near-instantaneous data processing and response capabilities, enabling emotion recognition and simulation adjustments without delay.

[0174] "Evaluation" refers to the process of determining a user's performance and skills based on the results of a simulation.

[0175] "Improvement proposals" refer to specific methods and steps presented based on the evaluation results to improve skills and overcome challenges in the future.

[0176] This invention consists of a system that provides a virtual experience using user information. The server plays a central role in the system, with the terminal acting as the interface. The server collects user information from data sources and generates a virtual profile using a generative AI model. This generative AI model is based on machine learning algorithms and uses information such as the user's age, gender, region, hobbies, and occupation as input data.

[0177] The server designs multiple simulation scenarios based on a virtual persona. This includes the process of generating virtual environments and defining tasks. Furthermore, the terminal is equipped with cameras and sensors to detect the user's facial expressions, voice tone, heart rate, etc., in real time. Based on this data, the terminal recognizes the user's emotions in real time and transmits them to the server.

[0178] Based on the emotional information transmitted, the server dynamically adjusts the simulation situation to provide the user with the optimal learning experience. For example, if the server detects that the user is relaxed, it can present a more challenging task. A concrete example is a customer service simulation in a cafe. In this case, a generative AI model can be used to input prompts such as "30-year-old female, lives in an urban area, hobbies are reading and traveling," and then design a simulation that matches those conditions.

[0179] This invention provides specific means for constructing a system that can improve practical skills by generating individual evaluations and improvement suggestions and providing feedback to users.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. The server stores this information as input data in a database, preparing the basic data necessary for subsequent processing.

[0183] Step 2:

[0184] The server uses a generative AI model to generate a virtual person profile from collected user information. Specifically, stored user data is fed to the AI ​​model, and a virtual person profile is output based on the algorithm the model has learned. This output is used in the next simulation design step.

[0185] Step 3:

[0186] The server designs multiple simulation scenarios based on the generated virtual person profile. Specifically, it generates customer service training and customer interaction scenarios tailored to the user's profile and characteristics. During this design process, the scenarios and difficulty levels of the virtual situations are set, and the necessary materials and configuration data for each simulation are output.

[0187] Step 4:

[0188] The device utilizes cameras and sensors to detect the user's facial expressions, voice tone, and heart rate in real time. This data is used as input for an emotion recognition algorithm to analyze the user's emotional state. The analyzed results are then transmitted from the device to a server.

[0189] Step 5:

[0190] The server receives emotional data transmitted from the terminal as input and dynamically adjusts the simulation situation based on it. Specifically, the server analyzes the emotional data and changes the pace and content of the scenario as needed. This process provides the user with the optimal simulation experience.

[0191] Step 6:

[0192] Once the simulation is complete, the server analyzes the user's emotional history and the simulation results. This analysis generates an evaluation and specific improvement suggestions for each user. These include advice for the next simulation and techniques for skill improvement, which are then fed back to the user.

[0193] (Application Example 2)

[0194] 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."

[0195] In modern customer service, staff are required to accurately understand customers' emotions and respond appropriately in an instant. However, achieving this requires high skill and experience, and they may not be able to respond flexibly to the ever-changing needs and emotions of customers. Therefore, there is a need for a means to support staff skill improvement by providing effective emotion recognition and feedback in real time.

[0196] 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.

[0197] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation situations based on the generated virtual person profile; and means for detecting the user's emotions in real time and adjusting the content and difficulty level of the simulation situations. This allows the user to experience the simulation while receiving real-time feedback based on their emotions, thereby improving their customer service skills and customer interaction techniques.

[0198] A "data source" is a source of information used to collect information about a user.

[0199] "User information" refers to detailed information about individual users, such as age, gender, region, hobbies, and occupation.

[0200] A "generative AI model" is an artificial intelligence technology used to generate a virtual profile of a person based on collected user information.

[0201] A "virtual character" is a digital representation of a person created by an AI model based on collected user information, for use in simulations.

[0202] A "simulation environment" is a training environment designed based on a virtual character profile, which users then experience.

[0203] The "emotion engine" is a technology that analyzes and detects emotions in real time from the user's facial expressions, tone of voice, heart rate, and other factors.

[0204] "Real-time feedback" refers to evaluation information that is immediately provided to users while they are experiencing a simulation, including results and areas for improvement.

[0205] "Advice" refers to practical guidance provided based on the user's behavior and emotional data.

[0206] "Improvement suggestions" are proposals provided to individual users based on the analyzed simulation results, aimed at improving their skills and abilities.

[0207] The system for realizing this application consists of a server, terminal, and user working together. Specifically, the server first collects user information from data sources and uses this information to generate a virtual person profile using a generative AI model. Based on this generated person profile, the server designs multiple simulation scenarios and provides them to the terminal.

[0208] The device is equipped with a camera and sensors that detect the user's facial expressions, voice tone, heart rate, and other data in real time. This allows the emotion engine to analyze the user's emotions and send the emotion data to a server. Based on this emotion data, the server can dynamically adjust the content and difficulty level of the simulation.

[0209] For example, if a user is feeling anxious, the server will take steps to alleviate their anxiety by providing more concise explanations and guidance. Conversely, if a user is relaxed, the server will present more challenging tasks to help them improve their skills. Throughout this process, users receive feedback via real-time sentiment analysis, allowing them to identify areas for improvement based on their responses.

[0210] Furthermore, as a concrete example, when a user is conducting a customer service simulation in a store, the system generates a prompt such as, "Please tell me the necessary customer service methods to alleviate the customer's anxiety," and then provides advice in real time that reflects the results of the sentiment analysis. In this way, users can instantly learn and practice appropriate responses.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. Based on this data, an AI model generates a virtual profile of the user. The input is user information, and the output is a virtual profile.

[0214] Step 2:

[0215] The server designs multiple simulation scenarios based on the generated virtual character profile and provides them to the terminal. The input is the virtual character profile, and the output is the simulation scenario. The server utilizes the generated AI model in this process to create appropriate scenarios.

[0216] Step 3:

[0217] While the simulation is running, the device uses its camera and sensors to input the user's facial expressions, voice tone, and heart rate into the emotion engine in real time. The input is the user's biometric data, and the output is the result of the emotion analysis.

[0218] Step 4:

[0219] The emotion engine detects the user's emotions and sends them to the server. Based on this data, the server dynamically adjusts the content and difficulty of the simulation. The input is the emotion data, and the output is the adjusted simulation state.

[0220] Step 5:

[0221] Based on the adjustments made to the simulation received by the user, real-time feedback is provided through the terminal. The input is the adjusted simulation situation, and the output is the feedback to the user. Specifically, if the user is stressed, the server will provide clearer guidance, and if the server determines that the user is relaxed, it will present a more complex challenge.

[0222] Step 6:

[0223] Based on the simulation results, the server generates personalized improvement suggestions and presents them to the user. The input is the final simulation results and sentiment history, and the output is the improvement suggestions. In this process, a generative AI model generates prompt sentences appropriate for each user.

[0224] Step 7:

[0225] Users can improve their skills based on the suggestions and feedback provided. In this final step, a new learning plan is developed based on the input feedback information, and guidelines are provided to help users achieve better results. The output is the user's improved ability.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] As an embodiment for carrying out the present invention, the system is configured according to the following procedure.

[0243] First, the server collects user information from data sources. This information includes age group, occupation, region, hobbies, and behavioral patterns, and is used as input data to generate a virtual profile of the person. The server preprocesses this data, removing outliers and imputing missing values, to prepare it for input into the model.

[0244] Subsequently, the server runs the generation AI model and generates a virtual profile based on the pre-processed user information. For example, it outputs a virtual person with various characteristics, such as a virtual person with purchasing behavior and information gathering tendencies specific to a particular age group, or a virtual person whose occupation is an engineer and whose hobby is the outdoors.

[0245] Next, the server designs simulation scenarios based on the generated virtual character profile. These include situations such as customer service at a tourist information center or handling customer complaints at a retail store. Each scenario reflects the specific behavioral patterns and requests of that virtual character profile.

[0246] On the other hand, the terminal presents the user with a list of available virtual character profiles and simulation situations through its user interface. The user can view this list and make selections that suit their training and learning objectives.

[0247] When the user makes a selection, the device retrieves the corresponding simulation data from the server and runs the simulation. The user can experience this situation in real time on the device. As the simulation progresses, the user takes actions according to the scenario and can check the results immediately.

[0248] Finally, user feedback is sent to the server via the terminal. The server aggregates this feedback and uses an evaluation model that analyzes the simulation results to quantify and evaluate the effectiveness of the responses for each virtual character. Subsequently, improvement suggestions tailored to each individual virtual character are automatically generated and presented to the user. In this way, users can continuously improve their skills and acquire the ability to respond in situations similar to actual work.

[0249] In the above configuration, the present invention can provide practical training tailored to diverse work environments and customer needs.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The server begins collecting user information from data sources. The collected data includes detailed information such as age, gender, region, hobbies, occupation, and purchase history. This data is used as the basis for generating a virtual profile.

[0253] Step 2:

[0254] The server performs data preprocessing on the collected user information. Specifically, it cleanses the data by imputing missing values ​​and filtering outliers, and converts the data into a format suitable for the AI ​​model.

[0255] Step 3:

[0256] The server runs a generative AI model, using pre-processed data as input to generate virtual character profiles with various characteristics. These generated character profiles reflect specific behavioral patterns and preferences.

[0257] Step 4:

[0258] Based on the generated virtual character profile, the server begins designing various simulation scenarios. These include typical customer interaction scenarios and problem-solving situations, with customized content tailored to the characteristics of the virtual character profile.

[0259] Step 5:

[0260] The terminal generates a user interface, displaying to the user a list of options for each virtual character and their corresponding simulation situation. This interface is designed to be intuitive and easy to use.

[0261] Step 6:

[0262] The user selects a virtual character and simulation scenario of interest through their device. Based on this selection, the system is prepared to run the simulation.

[0263] Step 7:

[0264] The terminal receives selected simulation data from the server and executes the simulation. The user experiences the scenario on the terminal and responds to the displayed challenges.

[0265] Step 8:

[0266] After the simulation is complete, the device will display a screen for user feedback, allowing users to provide feedback based on their experience.

[0267] Step 9:

[0268] The server evaluates the results of the simulation based on feedback received from the user. Using an evaluation model, it analyzes the quality of responses to each virtual character and identifies areas for improvement.

[0269] Step 10:

[0270] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to obtain concrete guidelines for continuously improving their response capabilities.

[0271] (Example 1)

[0272] 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."

[0273] In today's diverse work environments, efficiently providing practical training and supporting the skill development of users is a crucial challenge. However, traditional training methods struggle to create hypothetical situations tailored to individual users and to present specific improvement measures appropriate to those situations. As a result, users are unable to effectively acquire individualized problem-solving skills.

[0274] 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.

[0275] In this invention, the server includes means for preprocessing user information obtained from a data source by removing outliers and imputing missing values; means for generating a virtual person profile using a generative AI model based on the preprocessed user information; and means for designing specific behavioral patterns and requests as simulation situations based on the generated virtual person profile. This enables the provision of practical training tailored to individual learning objectives, allowing users to improve their skills more effectively.

[0276] A "data source" is a fundamental location or system for collecting information, from which user information is obtained.

[0277] "User information" refers to data such as age group, occupation, region, hobbies, and behavioral patterns, and is basic information used to generate a virtual profile.

[0278] An "outlier" refers to a value in the data that falls outside the normal range and is removed because it may impair the accuracy of the data.

[0279] "Missing values" refer to values ​​that are missing from a dataset, and data integrity is maintained by imputing these missing values.

[0280] "Preprocessing" refers to a series of preparatory processes to prepare data so that it can be used appropriately by AI models.

[0281] A "generative AI model" is an algorithm or system designed to generate virtual portraits of people using machine learning techniques.

[0282] A "virtual portrait" is a fictional portrait with specific characteristics and behavior patterns generated by an AI model based on the collected user information.

[0283] A "simulation situation" is a specific scenario or environment designed based on a virtual portrait, which is a virtual situation for users to experience.

[0284] An "evaluation model" is an algorithm or system for analyzing the results of a simulation and quantifying and evaluating the corresponding effects for each virtual portrait.

[0285] An "improvement plan" refers to modifications and ideas proposed to make specific responses more effective based on the results of a simulation.

[0286] The present invention relates to a system for generating a virtual portrait of a person and providing a simulation based on that portrait. To implement this invention, the following elements are important.

[0287] First, the server collects user information from a data source. At this stage, it connects to the database using an API and collects user information such as age group, occupation, region, hobbies, and behavior patterns. The acquired data is preprocessed by removing outliers and filling in missing values with the median using the Pandas library. This preprocessing process smooths the data input to the generative AI model.

[0288] Subsequently, the server runs a pre-trained generative AI model using machine learning libraries such as TensorFlow to generate a virtual profile based on pre-processed user information. This model can generate a variety of virtual profiles with specific characteristics. For example, if a virtual profile is generated of a "male engineer in his 30s with an outdoor hobby," it can analyze his purchasing tendencies and preferences.

[0289] The server then designs a simulation that reflects specific behavioral patterns and requests based on the generated virtual character profile. This simulation situation is constructed, for example, as a customer service or complaint handling scenario, facilitating a practical user experience.

[0290] Next, the terminal uses a web browser to present the user with a list of virtual character profiles and simulation scenarios. The user can then select a simulation that suits their purpose. Once the selection is complete, the terminal retrieves the corresponding simulation data from the server and executes the simulation in real time. For example, in customer service training, the user can interact with a virtual customer in a conversational format and immediately see the results.

[0291] Ultimately, user feedback is sent from the terminal to the server. The server aggregates this feedback and analyzes the simulation results using an evaluation model. Based on these results, improvement suggestions tailored to a specific hypothetical persona are generated and provided to the user. This allows users to continuously improve themselves and acquire skills relevant to their work.

[0292] As a concrete example, a prompt such as, "What products would you recommend for a male engineer in his 30s whose hobby is camping?" will prompt the system to suggest products that match the user's purchasing tendencies and interests based on that profile. In this way, the invention provides users with practical and personalized learning and training opportunities.

[0293] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0294] Step 1:

[0295] The server collects user information from the data source. In this step, it uses an API to connect to the database and retrieve information such as age group, occupation, region, hobbies, and behavioral patterns. The input is raw data from the database, and the output is structured user information.

[0296] Step 2:

[0297] The server preprocesses the acquired data. Specifically, it uses the Pandas library to remove outliers and impute missing values. The input is the output data from step 1, and the quality is improved through data cleansing, resulting in preprocessed data as output.

[0298] Step 3:

[0299] The server generates a virtual human profile using a generative AI model. Preprocessed data is input into the model using the TensorFlow library. The data calculations performed here involve extracting and combining data features. The output is a virtual human profile with diverse characteristics.

[0300] Step 4:

[0301] The server designs the simulation situation based on the generated virtual character profile. Specific scenarios are created reflecting the characteristics obtained from the generated AI model. The input is the output from step 3, and the output is simulation environment data that constitutes a specific behavioral pattern.

[0302] Step 5:

[0303] The terminal presents virtual character images and simulation scenarios to the user as a list through a web browser. The user selects a scenario that suits their learning purpose based on this. The input is the output data from Step 4, and a selectable interface is output.

[0304] Step 6:

[0305] When the user selects a scenario, the terminal retrieves the corresponding simulation data from the server and executes the simulation. For example, in a customer service simulation, the user conducts real-time interaction with a virtual customer. The input is the scenario selected by the user in Step 5, and the output is a real-time simulation exercise.

[0306] Step 7:

[0307] Collect the user's feedback and send it from the terminal to the server. The server operates an evaluation model using the feedback and analyzes the results of the simulation. The input is the user's actions and their feedback during the simulation, and the output is numerical evaluation data as the analysis result.

[0308] Step 8:

[0309] The server generates improvement suggestions based on the analyzed data and presents them to the user. Using a generation AI model, specific improvement measures for a particular virtual character image are automatically derived. The input is the evaluation data from Step 7, and the output is customized advice presented to the user.

[0310] (Application Example 1)

[0311] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] Conventional customer service training systems have drawbacks, such as difficulty in providing practical training that closely matches actual work situations and difficulty in obtaining efficient feedback to improve individual customer service skills. This invention aims to effectively improve customer service skills in actual stores through individualized simulations using a virtual persona.

[0313] 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.

[0314] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation scenarios tailored to customer service content in a physical store based on the generated virtual person profile; and means for analyzing the results of the simulation scenarios and extracting evaluation and improvement points for each virtual person profile. This enables users to receive training in an environment close to actual work while obtaining specific feedback based on their individual responses.

[0315] A "data source" is a source of information used to collect information about a user, and this includes online data and user profile information.

[0316] A "generative AI model" is an artificial intelligence model that generates a virtual human profile from input data, thereby constructing the human profile used in virtual simulations.

[0317] A "virtual character profile" is a model of a non-existent person generated based on user information, possessing characteristics such as age group, hobbies, and behavioral patterns.

[0318] A "simulation scenario" is a scenario that mimics a situation corresponding to a hypothetical person, and is intended to reproduce real-world situations in customer service training.

[0319] A "real-time customer service training scenario" is a scenario that allows users to simulate and practice customer service procedures on the spot under conditions similar to those in an actual store.

[0320] A "smart device" is a portable electronic device used to support simulations and virtual reality, and examples include smart glasses and mobile devices.

[0321] A "user interface" refers to the screens and functions that allow users to interact with a system, and is used for selecting and experiencing simulations.

[0322] "Personalized improvement suggestions" refer to specific improvement methods and advice provided to users based on a hypothetical person profile and the results of simulations based on that profile.

[0323] The system implementing this invention consists of a server and a terminal with a user interface. The server continuously collects user information from data sources, preprocesses the collected data to remove outliers, and imputes missing values. The hardware includes a computer server used to efficiently perform data processing. The software includes programs using Python or TensorFlow to support this process.

[0324] Pre-processed user information is input into a generating AI model. This model uses machine learning algorithms to generate a virtual profile of a person. Specific examples include hypothetical customer profiles with different age groups and hobbies, which serve as the basis for diverse customer service simulations.

[0325] Based on the generated virtual character profile, the server designs a simulation that mimics customer service situations in a real store. The simulation content is structured around specific scenarios to allow store employees to receive customer service training. For example, it includes scenarios such as "introducing new products" and "handling customer complaints."

[0326] The terminal uses smart devices (e.g., smart glasses) to present these simulation scenarios to the user. Through these, the user can conduct customer service training in an environment that closely resembles a real store. The user interface on the terminal uses a real-time simulation application based on Unity.

[0327] After the simulation, user feedback is sent back to the server. The server analyzes the simulation results based on this feedback and extracts evaluations and areas for improvement for each virtual character. This information is provided to the user and displayed as personalized improvement suggestions.

[0328] An example of a prompt is: "Generate a customer service scenario that increases the interest of a 25-year-old woman living in area A, whose hobby is fashion shopping, in a new product." Using prompts like this, simulations tailored to each hypothetical character can be efficiently generated.

[0329] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0330] Step 1:

[0331] The server collects user information from data sources. This includes data such as age, occupation, region, hobbies, and behavioral patterns. Based on the collected information, outliers are removed and missing values ​​are imputed to prepare the input data for the generative AI model. Preprocessing is performed using Python and the NumPy library to create a clean dataset. The input to this process is raw user data, and the output is preprocessed user information.

[0332] Step 2:

[0333] The server inputs pre-processed user information into a generation AI model to generate a virtual profile. TensorFlow is used for this generation. Pre-formatted user information is provided as input, and a characterized virtual profile is obtained as output. For example, it can generate profiles with purchasing tendencies and information gathering tendencies.

[0334] Step 3:

[0335] The server designs simulation scenarios for use in physical stores based on the generated virtual character profiles. Prompt statements are used in the scenario design, constructing scenarios that include dialogue and behavioral patterns aligned with the generated character profiles. The inputs are the virtual character profiles and prompt statements, and the output is the completed scenario. This process involves programming the scenario logic using a scripting language.

[0336] Step 4:

[0337] The terminal presents scenarios to the user via a smart device and conducts customer service training. The user experiences virtual scenarios in real time through smart glasses or similar devices and learns how to respond. The input is scenario data, and the output is user behavior data and feedback. In this process, the Unity engine is used to render the simulation environment in real time.

[0338] Step 5:

[0339] User feedback is sent to the server, where the results are analyzed to extract evaluations and areas for improvement. This uses a machine learning model to quantify user interaction skills. The input is user feedback, and the output is the analysis results and areas for improvement. Based on the collected data, the analysis model is run using Scikit-learn.

[0340] Step 6:

[0341] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to confirm specific directions for skill improvement. The input is the analysis results, and the output is the improvement suggestion report. A text formatting program is used to improve the readability of the report.

[0342] 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.

[0343] As an embodiment for carrying out the present invention, a system incorporating an emotion engine is configured as follows:

[0344] First, the server collects user information from data sources and generates a virtual profile using a generative AI model. The collected data includes detailed information such as age, gender, region, hobbies, and occupation. Based on this information, the server designs a simulation scenario that corresponds to the virtual profile. This process includes customer service simulations and customer interaction simulations.

[0345] Furthermore, this invention uses an emotion engine to recognize the user's emotions in real time. Through cameras and sensors installed in the terminal, it detects emotions from the user's facial expressions, tone of voice, heart rate, etc. For example, if the user feels stressed during a simulation, the emotion engine recognizes that emotion and sends a signal to the server.

[0346] The server automatically adjusts the content and difficulty of the simulation situation based on the transmitted emotion data. For example, if it determines that the user is relaxed, it can speed up the scenario or present more complex challenges. On the other hand, if the user is confused, it provides guidance and additional support information to help them learn.

[0347] Users experience these simulations on their devices, and the emotion engine monitors the feedback generated during the process, allowing them to understand their own reactions and areas for improvement in real time. Once the simulation is complete, the server analyzes the user's emotional history and simulation results, and presents personalized improvement suggestions. These suggestions may include not only future response methods but also techniques for emotional control.

[0348] In the above configuration, the present invention can provide a flexible simulation environment that responds to the user's emotions, thereby enabling more effective improvement of practical skills.

[0349] The following describes the processing flow.

[0350] Step 1:

[0351] The server collects user information from data sources. This data includes many attributes such as age, gender, occupation, region, and past purchase history. This data is used as a basis for generating highly accurate virtual profiles of individuals.

[0352] Step 2:

[0353] The server preprocesses the collected data and uses a generative AI model to generate diverse virtual personas. These include personas with specific behavioral patterns and preferences. For example, personas such as a travel enthusiast in their 30s living in a city or a forty-something engineer raising children are generated.

[0354] Step 3:

[0355] The server designs various simulation scenarios based on the generated virtual character profile. For example, these include situations such as customer service in retail or handling complaints at a customer support center, with content tailored to the characteristics of the virtual character.

[0356] Step 4:

[0357] The terminal presents the user with a selection of virtual character profiles and simulation scenarios via a user interface. The user selects a scenario suitable for their skill development and initiates the simulation.

[0358] Step 5:

[0359] The emotion engine built into the device monitors the user's facial expressions, voice tone, and biometric information through the camera and microphone to detect the user's emotional state in real time.

[0360] Step 6:

[0361] The emotion engine sends the user's emotional state to the server in real time, and the server adaptively adjusts the simulation's situation and difficulty based on that data. For example, when the user is frustrated, the server increases the amount of information provided or strengthens the assistance.

[0362] Step 7:

[0363] The user progresses through the simulation on the device and performs tasks requested during the session. The emotion engine monitors the user's emotions and continuously sends data to the server.

[0364] Step 8:

[0365] Once the simulation is complete, the terminal presents the user with feedback and an evaluation of the entire session. Based on the sentiment data, the server generates personalized improvement suggestions tailored to the user and provides them to the user through the terminal.

[0366] Step 9:

[0367] Based on this feedback and suggestions for improvement, users can revise their future learning plans and approaches, helping them to improve their skills.

[0368] (Example 2)

[0369] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0370] In modern society, there is a demand for flexible and effective simulation environments tailored to the characteristics of users. However, conventional simulation systems have the challenge of being unable to dynamically adjust to users' real-time emotions, making it difficult to support deep experiences and skill improvement.

[0371] 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.

[0372] In this invention, the server includes means for collecting user information and generating a virtual person profile using a generative model; means for designing multiple virtual situations based on the virtual person profile; and means for recognizing the user's emotions in real time through a detection device installed in the terminal and processing that information. This enables dynamic adjustment of the simulation situation based on the user's emotions.

[0373] "User information" refers to detailed attribute data of an individual, such as age, gender, region, hobbies, and occupation.

[0374] A "generative model" refers to an artificial intelligence algorithm or program used to create a virtual persona based on given data.

[0375] A "virtual person profile" refers to a fictional human profile generated based on collected user information.

[0376] A "virtual situation" refers to various simulation environments designed based on a fictional character profile, which users then experience.

[0377] A "terminal" refers to a device equipped with devices such as cameras and sensors, which functions as an interface with the user.

[0378] A "detection device" refers to a device that collects data such as the user's facial expressions, voice tone, and heart rate, enabling emotional analysis.

[0379] "Real-time" refers to near-instantaneous data processing and response capabilities, enabling emotion recognition and simulation adjustments without delay.

[0380] "Evaluation" refers to the process of determining a user's performance and skills based on the results of a simulation.

[0381] "Improvement proposals" refer to specific methods and steps presented based on the evaluation results to improve skills and overcome challenges in the future.

[0382] This invention consists of a system that provides a virtual experience using user information. The server plays a central role in the system, with the terminal acting as the interface. The server collects user information from data sources and generates a virtual profile using a generative AI model. This generative AI model is based on machine learning algorithms and uses information such as the user's age, gender, region, hobbies, and occupation as input data.

[0383] The server designs multiple simulation scenarios based on a virtual persona. This includes the process of generating virtual environments and defining tasks. Furthermore, the terminal is equipped with cameras and sensors to detect the user's facial expressions, voice tone, heart rate, etc., in real time. Based on this data, the terminal recognizes the user's emotions in real time and transmits them to the server.

[0384] Based on the emotional information transmitted, the server dynamically adjusts the simulation situation to provide the user with the optimal learning experience. For example, if the server detects that the user is relaxed, it can present a more challenging task. A concrete example is a customer service simulation in a cafe. In this case, a generative AI model can be used to input prompts such as "30-year-old female, lives in an urban area, hobbies are reading and traveling," and then design a simulation that matches those conditions.

[0385] This invention provides specific means for constructing a system that can improve practical skills by generating individual evaluations and improvement suggestions and providing feedback to users.

[0386] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0387] Step 1:

[0388] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. The server stores this information as input data in a database, preparing the basic data necessary for subsequent processing.

[0389] Step 2:

[0390] The server uses a generative AI model to generate a virtual person profile from collected user information. Specifically, stored user data is fed to the AI ​​model, and a virtual person profile is output based on the algorithm the model has learned. This output is used in the next simulation design step.

[0391] Step 3:

[0392] The server designs multiple simulation scenarios based on the generated virtual person profile. Specifically, it generates customer service training and customer interaction scenarios tailored to the user's profile and characteristics. During this design process, the scenarios and difficulty levels of the virtual situations are set, and the necessary materials and configuration data for each simulation are output.

[0393] Step 4:

[0394] The device utilizes cameras and sensors to detect the user's facial expressions, voice tone, and heart rate in real time. This data is used as input for an emotion recognition algorithm to analyze the user's emotional state. The analyzed results are then transmitted from the device to a server.

[0395] Step 5:

[0396] The server receives emotional data transmitted from the terminal as input and dynamically adjusts the simulation situation based on it. Specifically, the server analyzes the emotional data and changes the pace and content of the scenario as needed. This process provides the user with the optimal simulation experience.

[0397] Step 6:

[0398] Once the simulation is complete, the server analyzes the user's emotional history and the simulation results. This analysis generates an evaluation and specific improvement suggestions for each user. These include advice for the next simulation and techniques for skill improvement, which are then fed back to the user.

[0399] (Application Example 2)

[0400] 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".

[0401] In modern customer service, staff are required to accurately understand customers' emotions and respond appropriately in an instant. However, achieving this requires high skill and experience, and they may not be able to respond flexibly to the ever-changing needs and emotions of customers. Therefore, there is a need for a means to support staff skill improvement by providing effective emotion recognition and feedback in real time.

[0402] 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.

[0403] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation situations based on the generated virtual person profile; and means for detecting the user's emotions in real time and adjusting the content and difficulty level of the simulation situations. This allows the user to experience the simulation while receiving real-time feedback based on their emotions, thereby improving their customer service skills and customer interaction techniques.

[0404] A "data source" is a source of information used to collect information about a user.

[0405] "User information" refers to detailed information about individual users, such as age, gender, region, hobbies, and occupation.

[0406] A "generative AI model" is an artificial intelligence technology used to generate a virtual profile of a person based on collected user information.

[0407] A "virtual character" is a digital representation of a person created by an AI model based on collected user information, for use in simulations.

[0408] A "simulation environment" is a training environment designed based on a virtual character profile, which users then experience.

[0409] The "emotion engine" is a technology that analyzes and detects emotions in real time from the user's facial expressions, tone of voice, heart rate, and other factors.

[0410] "Real-time feedback" refers to evaluation information that is immediately provided to users while they are experiencing a simulation, including results and areas for improvement.

[0411] "Advice" refers to practical guidance provided based on the user's behavior and emotional data.

[0412] "Improvement suggestions" are proposals provided to individual users based on the analyzed simulation results, aimed at improving their skills and abilities.

[0413] The system for realizing this application consists of a server, terminal, and user working together. Specifically, the server first collects user information from data sources and uses this information to generate a virtual person profile using a generative AI model. Based on this generated person profile, the server designs multiple simulation scenarios and provides them to the terminal.

[0414] The device is equipped with a camera and sensors that detect the user's facial expressions, voice tone, heart rate, and other data in real time. This allows the emotion engine to analyze the user's emotions and send the emotion data to a server. Based on this emotion data, the server can dynamically adjust the content and difficulty level of the simulation.

[0415] For example, if a user is feeling anxious, the server will take steps to alleviate their anxiety by providing more concise explanations and guidance. Conversely, if a user is relaxed, the server will present more challenging tasks to help them improve their skills. Throughout this process, users receive feedback via real-time sentiment analysis, allowing them to identify areas for improvement based on their responses.

[0416] Furthermore, as a concrete example, when a user is conducting a customer service simulation in a store, the system generates a prompt such as, "Please tell me the necessary customer service methods to alleviate the customer's anxiety," and then provides advice in real time that reflects the results of the sentiment analysis. In this way, users can instantly learn and practice appropriate responses.

[0417] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0418] Step 1:

[0419] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. Based on this data, an AI model generates a virtual profile of the user. The input is user information, and the output is a virtual profile.

[0420] Step 2:

[0421] The server designs multiple simulation scenarios based on the generated virtual character profile and provides them to the terminal. The input is the virtual character profile, and the output is the simulation scenario. The server utilizes the generated AI model in this process to create appropriate scenarios.

[0422] Step 3:

[0423] While the simulation is running, the device uses its camera and sensors to input the user's facial expressions, voice tone, and heart rate into the emotion engine in real time. The input is the user's biometric data, and the output is the result of the emotion analysis.

[0424] Step 4:

[0425] The emotion engine detects the user's emotions and sends them to the server. Based on this data, the server dynamically adjusts the content and difficulty of the simulation. The input is the emotion data, and the output is the adjusted simulation state.

[0426] Step 5:

[0427] Based on the adjustments made to the simulation received by the user, real-time feedback is provided through the terminal. The input is the adjusted simulation situation, and the output is the feedback to the user. Specifically, if the user is stressed, the server will provide clearer guidance, and if the server determines that the user is relaxed, it will present a more complex challenge.

[0428] Step 6:

[0429] Based on the simulation results, the server generates personalized improvement suggestions and presents them to the user. The input is the final simulation results and sentiment history, and the output is the improvement suggestions. In this process, a generative AI model generates prompt sentences appropriate for each user.

[0430] Step 7:

[0431] Users can improve their skills based on the suggestions and feedback provided. In this final step, a new learning plan is developed based on the input feedback information, and guidelines are provided to help users achieve better results. The output is the user's improved ability.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Third Embodiment]

[0436] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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".

[0448] As an embodiment for carrying out the present invention, the system is configured according to the following procedure.

[0449] First, the server collects user information from data sources. This information includes age group, occupation, region, hobbies, and behavioral patterns, and is used as input data to generate a virtual profile of the person. The server preprocesses this data, removing outliers and imputing missing values, to prepare it for input into the model.

[0450] Subsequently, the server runs the generation AI model and generates a virtual profile based on the pre-processed user information. For example, it outputs a virtual person with various characteristics, such as a virtual person with purchasing behavior and information gathering tendencies specific to a particular age group, or a virtual person whose occupation is an engineer and whose hobby is the outdoors.

[0451] Next, the server designs simulation scenarios based on the generated virtual character profile. These include situations such as customer service at a tourist information center or handling customer complaints at a retail store. Each scenario reflects the specific behavioral patterns and requests of that virtual character profile.

[0452] On the other hand, the terminal presents the user with a list of available virtual character profiles and simulation situations through its user interface. The user can view this list and make selections that suit their training and learning objectives.

[0453] When the user makes a selection, the device retrieves the corresponding simulation data from the server and runs the simulation. The user can experience this situation in real time on the device. As the simulation progresses, the user takes actions according to the scenario and can check the results immediately.

[0454] Finally, user feedback is sent to the server via the terminal. The server aggregates this feedback and uses an evaluation model that analyzes the simulation results to quantify and evaluate the effectiveness of the responses for each virtual character. Subsequently, improvement suggestions tailored to each individual virtual character are automatically generated and presented to the user. In this way, users can continuously improve their skills and acquire the ability to respond in situations similar to actual work.

[0455] In the above configuration, the present invention can provide practical training tailored to diverse work environments and customer needs.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The server begins collecting user information from data sources. The collected data includes detailed information such as age, gender, region, hobbies, occupation, and purchase history. This data is used as the basis for generating a virtual profile.

[0459] Step 2:

[0460] The server performs data preprocessing on the collected user information. Specifically, it cleanses the data by imputing missing values ​​and filtering outliers, and converts the data into a format suitable for the AI ​​model.

[0461] Step 3:

[0462] The server runs a generative AI model, using pre-processed data as input to generate virtual character profiles with various characteristics. These generated character profiles reflect specific behavioral patterns and preferences.

[0463] Step 4:

[0464] Based on the generated virtual character profile, the server begins designing various simulation scenarios. These include typical customer interaction scenarios and problem-solving situations, with customized content tailored to the characteristics of the virtual character profile.

[0465] Step 5:

[0466] The terminal generates a user interface, displaying to the user a list of options for each virtual character and their corresponding simulation situation. This interface is designed to be intuitive and easy to use.

[0467] Step 6:

[0468] The user selects a virtual character and simulation scenario of interest through their device. Based on this selection, the system is prepared to run the simulation.

[0469] Step 7:

[0470] The terminal receives selected simulation data from the server and executes the simulation. The user experiences the scenario on the terminal and responds to the displayed challenges.

[0471] Step 8:

[0472] After the simulation is complete, the device will display a screen for user feedback, allowing users to provide feedback based on their experience.

[0473] Step 9:

[0474] The server evaluates the results of the simulation based on feedback received from the user. Using an evaluation model, it analyzes the quality of responses to each virtual character and identifies areas for improvement.

[0475] Step 10:

[0476] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to obtain concrete guidelines for continuously improving their response capabilities.

[0477] (Example 1)

[0478] 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."

[0479] In today's diverse work environments, efficiently providing practical training and supporting the skill development of users is a crucial challenge. However, traditional training methods struggle to create hypothetical situations tailored to individual users and to present specific improvement measures appropriate to those situations. As a result, users are unable to effectively acquire individualized problem-solving skills.

[0480] 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.

[0481] In this invention, the server includes means for preprocessing user information obtained from a data source by removing outliers and imputing missing values; means for generating a virtual person profile using a generative AI model based on the preprocessed user information; and means for designing specific behavioral patterns and requests as simulation situations based on the generated virtual person profile. This enables the provision of practical training tailored to individual learning objectives, allowing users to improve their skills more effectively.

[0482] A "data source" is a fundamental location or system for collecting information, from which user information is obtained.

[0483] "User information" refers to data such as age group, occupation, region, hobbies, and behavioral patterns, and is basic information used to generate a virtual profile.

[0484] An "outlier" refers to a value in the data that falls outside the normal range and is removed because it may impair the accuracy of the data.

[0485] "Missing values" refer to values ​​that are missing from a dataset, and data integrity is maintained by imputing these missing values.

[0486] "Preprocessing" refers to a series of preparatory processes to prepare data so that it can be used appropriately by AI models.

[0487] A "generative AI model" is an algorithm or system designed to generate a virtual human profile using machine learning techniques.

[0488] A "virtual character profile" is a fictional character profile with specific characteristics and behavioral patterns, generated by an AI model based on collected user information.

[0489] A "simulation situation" is a specific scenario or environment designed based on a virtual character, and is a virtual situation for the user to experience.

[0490] An "evaluation model" is an algorithm or system used to analyze the results of a simulation and quantify and evaluate the effectiveness of the corresponding actions for each virtual character.

[0491] An "improvement plan" refers to modifications or improvements proposed based on the results of a simulation to make a particular response more effective.

[0492] This invention relates to a system for generating a virtual character and providing a simulation based on that character. The following elements are important for carrying out this invention.

[0493] First, the server collects user information from the data source. At this stage, it connects to the database using an API and collects user information such as age group, occupation, region, hobbies, and behavioral patterns. The acquired data is preprocessed using the Pandas library by removing outliers and imputing missing values ​​with the median. This preprocessing process facilitates data input into the generative AI model.

[0494] Subsequently, the server runs a pre-trained generative AI model using machine learning libraries such as TensorFlow to generate a virtual profile based on pre-processed user information. This model can generate a variety of virtual profiles with specific characteristics. For example, if a virtual profile is generated of a "male engineer in his 30s with an outdoor hobby," it can analyze his purchasing tendencies and preferences.

[0495] The server then designs a simulation that reflects specific behavioral patterns and requests based on the generated virtual character profile. This simulation situation is constructed, for example, as a customer service or complaint handling scenario, facilitating a practical user experience.

[0496] Next, the terminal uses a web browser to present the user with a list of virtual character profiles and simulation scenarios. The user can then select a simulation that suits their purpose. Once the selection is complete, the terminal retrieves the corresponding simulation data from the server and executes the simulation in real time. For example, in customer service training, the user can interact with a virtual customer in a conversational format and immediately see the results.

[0497] Ultimately, user feedback is sent from the terminal to the server. The server aggregates this feedback and analyzes the simulation results using an evaluation model. Based on these results, improvement suggestions tailored to a specific hypothetical persona are generated and provided to the user. This allows users to continuously improve themselves and acquire skills relevant to their work.

[0498] As a concrete example, a prompt such as, "What products would you recommend for a male engineer in his 30s whose hobby is camping?" will prompt the system to suggest products that match the user's purchasing tendencies and interests based on that profile. In this way, the invention provides users with practical and personalized learning and training opportunities.

[0499] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0500] Step 1:

[0501] The server collects user information from the data source. In this step, it uses an API to connect to the database and retrieve information such as age group, occupation, region, hobbies, and behavioral patterns. The input is raw data from the database, and the output is structured user information.

[0502] Step 2:

[0503] The server preprocesses the acquired data. Specifically, it uses the Pandas library to remove outliers and impute missing values. The input is the output data from step 1, and the quality is improved through data cleansing, resulting in preprocessed data as output.

[0504] Step 3:

[0505] The server generates a virtual human profile using a generative AI model. Preprocessed data is input into the model using the TensorFlow library. The data calculations performed here involve extracting and combining data features. The output is a virtual human profile with diverse characteristics.

[0506] Step 4:

[0507] The server designs the simulation situation based on the generated virtual character profile. Specific scenarios are created reflecting the characteristics obtained from the generated AI model. The input is the output from step 3, and the output is simulation environment data that constitutes a specific behavioral pattern.

[0508] Step 5:

[0509] The terminal presents the user with a list of virtual character profiles and simulation situations via a web browser. The user then selects a scenario that suits their learning objectives. The input is the output data from step 4, and the selectable interfaces are output.

[0510] Step 6:

[0511] When the user selects a scenario, the terminal retrieves the corresponding simulation data from the server and executes the simulation. For example, in a customer service simulation, the user interacts with a virtual customer in real time. The input is the scenario selected by the user in step 5, and the output is a real-time simulation exercise.

[0512] Step 7:

[0513] The system collects user feedback and sends it from the terminal to the server. The server uses the feedback to run an evaluation model and analyzes the simulation results. The input is the user's actions during the simulation and their feedback, and the output is quantified evaluation data as a result of the analysis.

[0514] Step 8:

[0515] The server generates improvement suggestions based on the analyzed data and presents them to the user. Using a generation AI model, it automatically derives specific improvement measures for a particular virtual character. The input is the evaluation data from step 7, and the output is customized advice presented to the user.

[0516] (Application Example 1)

[0517] 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."

[0518] Conventional customer service training systems have drawbacks, such as difficulty in providing practical training that closely matches actual work situations and difficulty in obtaining efficient feedback to improve individual customer service skills. This invention aims to effectively improve customer service skills in actual stores through individualized simulations using a virtual persona.

[0519] 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.

[0520] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation scenarios tailored to customer service content in a physical store based on the generated virtual person profile; and means for analyzing the results of the simulation scenarios and extracting evaluation and improvement points for each virtual person profile. This enables users to receive training in an environment close to actual work while obtaining specific feedback based on their individual responses.

[0521] A "data source" is a source of information used to collect information about a user, and this includes online data and user profile information.

[0522] A "generative AI model" is an artificial intelligence model that generates a virtual human profile from input data, thereby constructing the human profile used in virtual simulations.

[0523] A "virtual character profile" is a model of a non-existent person generated based on user information, possessing characteristics such as age group, hobbies, and behavioral patterns.

[0524] A "simulation scenario" is a scenario that mimics a situation corresponding to a hypothetical person, and is intended to reproduce real-world situations in customer service training.

[0525] A "real-time customer service training scenario" is a scenario that allows users to simulate and practice customer service procedures on the spot under conditions similar to those in an actual store.

[0526] A "smart device" is a portable electronic device used to support simulations and virtual reality, and examples include smart glasses and mobile devices.

[0527] A "user interface" refers to the screens and functions that allow users to interact with a system, and is used for selecting and experiencing simulations.

[0528] "Personalized improvement suggestions" refer to specific improvement methods and advice provided to users based on a hypothetical person profile and the results of simulations based on that profile.

[0529] The system implementing this invention consists of a server and a terminal with a user interface. The server continuously collects user information from data sources, preprocesses the collected data to remove outliers, and imputes missing values. The hardware includes a computer server used to efficiently perform data processing. The software includes programs using Python or TensorFlow to support this process.

[0530] Pre-processed user information is input into a generating AI model. This model uses machine learning algorithms to generate a virtual profile of a person. Specific examples include hypothetical customer profiles with different age groups and hobbies, which serve as the basis for diverse customer service simulations.

[0531] Based on the generated virtual character profile, the server designs a simulation that mimics customer service situations in a real store. The simulation content is structured around specific scenarios to allow store employees to receive customer service training. For example, it includes scenarios such as "introducing new products" and "handling customer complaints."

[0532] The terminal uses smart devices (e.g., smart glasses) to present these simulation scenarios to the user. Through these, the user can conduct customer service training in an environment that closely resembles a real store. The user interface on the terminal uses a real-time simulation application based on Unity.

[0533] After the simulation, user feedback is sent back to the server. The server analyzes the simulation results based on this feedback and extracts evaluations and areas for improvement for each virtual character. This information is provided to the user and displayed as personalized improvement suggestions.

[0534] An example of a prompt is: "Generate a customer service scenario that increases the interest of a 25-year-old woman living in area A, whose hobby is fashion shopping, in a new product." Using prompts like this, simulations tailored to each hypothetical character can be efficiently generated.

[0535] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0536] Step 1:

[0537] The server collects user information from data sources. This includes data such as age, occupation, region, hobbies, and behavioral patterns. Based on the collected information, outliers are removed and missing values ​​are imputed to prepare the input data for the generative AI model. Preprocessing is performed using Python and the NumPy library to create a clean dataset. The input to this process is raw user data, and the output is preprocessed user information.

[0538] Step 2:

[0539] The server inputs pre-processed user information into a generation AI model to generate a virtual profile. TensorFlow is used for this generation. Pre-formatted user information is provided as input, and a characterized virtual profile is obtained as output. For example, it can generate profiles with purchasing tendencies and information gathering tendencies.

[0540] Step 3:

[0541] The server designs simulation scenarios for use in physical stores based on the generated virtual character profiles. Prompt statements are used in the scenario design, constructing scenarios that include dialogue and behavioral patterns aligned with the generated character profiles. The inputs are the virtual character profiles and prompt statements, and the output is the completed scenario. This process involves programming the scenario logic using a scripting language.

[0542] Step 4:

[0543] The terminal presents scenarios to the user via a smart device and conducts customer service training. The user experiences virtual scenarios in real time through smart glasses or similar devices and learns how to respond. The input is scenario data, and the output is user behavior data and feedback. In this process, the Unity engine is used to render the simulation environment in real time.

[0544] Step 5:

[0545] User feedback is sent to the server, where the results are analyzed to extract evaluations and areas for improvement. This uses a machine learning model to quantify user interaction skills. The input is user feedback, and the output is the analysis results and areas for improvement. Based on the collected data, the analysis model is run using Scikit-learn.

[0546] Step 6:

[0547] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to confirm specific directions for skill improvement. The input is the analysis results, and the output is the improvement suggestion report. A text formatting program is used to improve the readability of the report.

[0548] 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.

[0549] As an embodiment for carrying out the present invention, a system incorporating an emotion engine is configured as follows:

[0550] First, the server collects user information from data sources and generates a virtual profile using a generative AI model. The collected data includes detailed information such as age, gender, region, hobbies, and occupation. Based on this information, the server designs a simulation scenario that corresponds to the virtual profile. This process includes customer service simulations and customer interaction simulations.

[0551] Furthermore, this invention uses an emotion engine to recognize the user's emotions in real time. Through cameras and sensors installed in the terminal, it detects emotions from the user's facial expressions, tone of voice, heart rate, etc. For example, if the user feels stressed during a simulation, the emotion engine recognizes that emotion and sends a signal to the server.

[0552] The server automatically adjusts the content and difficulty of the simulation situation based on the transmitted emotion data. For example, if it determines that the user is relaxed, it can speed up the scenario or present more complex challenges. On the other hand, if the user is confused, it provides guidance and additional support information to help them learn.

[0553] Users experience these simulations on their devices, and the emotion engine monitors the feedback generated during the process, allowing them to understand their own reactions and areas for improvement in real time. Once the simulation is complete, the server analyzes the user's emotional history and simulation results, and presents personalized improvement suggestions. These suggestions may include not only future response methods but also techniques for emotional control.

[0554] In the above configuration, the present invention can provide a flexible simulation environment that responds to the user's emotions, thereby enabling more effective improvement of practical skills.

[0555] The following describes the processing flow.

[0556] Step 1:

[0557] The server collects user information from data sources. This data includes many attributes such as age, gender, occupation, region, and past purchase history. This data is used as a basis for generating highly accurate virtual profiles of individuals.

[0558] Step 2:

[0559] The server preprocesses the collected data and uses a generative AI model to generate diverse virtual personas. These include personas with specific behavioral patterns and preferences. For example, personas such as a travel enthusiast in their 30s living in a city or a forty-something engineer raising children are generated.

[0560] Step 3:

[0561] The server designs various simulation scenarios based on the generated virtual character profile. For example, these include situations such as customer service in retail or handling complaints at a customer support center, with content tailored to the characteristics of the virtual character.

[0562] Step 4:

[0563] The terminal presents the user with a selection of virtual character profiles and simulation scenarios via a user interface. The user selects a scenario suitable for their skill development and initiates the simulation.

[0564] Step 5:

[0565] The emotion engine built into the device monitors the user's facial expressions, voice tone, and biometric information through the camera and microphone to detect the user's emotional state in real time.

[0566] Step 6:

[0567] The emotion engine sends the user's emotional state to the server in real time, and the server adaptively adjusts the simulation's situation and difficulty based on that data. For example, when the user is frustrated, the server increases the amount of information provided or strengthens the assistance.

[0568] Step 7:

[0569] The user progresses through the simulation on the device and performs tasks requested during the session. The emotion engine monitors the user's emotions and continuously sends data to the server.

[0570] Step 8:

[0571] Once the simulation is complete, the terminal presents the user with feedback and an evaluation of the entire session. Based on the sentiment data, the server generates personalized improvement suggestions tailored to the user and provides them to the user through the terminal.

[0572] Step 9:

[0573] Based on this feedback and suggestions for improvement, users can revise their future learning plans and approaches, helping them to improve their skills.

[0574] (Example 2)

[0575] 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."

[0576] In modern society, there is a demand for flexible and effective simulation environments tailored to the characteristics of users. However, conventional simulation systems have the challenge of being unable to dynamically adjust to users' real-time emotions, making it difficult to support deep experiences and skill improvement.

[0577] 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.

[0578] In this invention, the server includes means for collecting user information and generating a virtual person profile using a generative model; means for designing multiple virtual situations based on the virtual person profile; and means for recognizing the user's emotions in real time through a detection device installed in the terminal and processing that information. This enables dynamic adjustment of the simulation situation based on the user's emotions.

[0579] "User information" refers to detailed attribute data of an individual, such as age, gender, region, hobbies, and occupation.

[0580] A "generative model" refers to an artificial intelligence algorithm or program used to create a virtual persona based on given data.

[0581] A "virtual person profile" refers to a fictional human profile generated based on collected user information.

[0582] A "virtual situation" refers to various simulation environments designed based on a fictional character profile, which users then experience.

[0583] A "terminal" refers to a device equipped with devices such as cameras and sensors, which functions as an interface with the user.

[0584] A "detection device" refers to a device that collects data such as the user's facial expressions, voice tone, and heart rate, enabling emotional analysis.

[0585] "Real-time" refers to near-instantaneous data processing and response capabilities, enabling emotion recognition and simulation adjustments without delay.

[0586] "Evaluation" refers to the process of determining a user's performance and skills based on the results of a simulation.

[0587] "Improvement proposals" refer to specific methods and steps presented based on the evaluation results to improve skills and overcome challenges in the future.

[0588] This invention consists of a system that provides a virtual experience using user information. The server plays a central role in the system, with the terminal acting as the interface. The server collects user information from data sources and generates a virtual profile using a generative AI model. This generative AI model is based on machine learning algorithms and uses information such as the user's age, gender, region, hobbies, and occupation as input data.

[0589] The server designs multiple simulation scenarios based on a virtual persona. This includes the process of generating virtual environments and defining tasks. Furthermore, the terminal is equipped with cameras and sensors to detect the user's facial expressions, voice tone, heart rate, etc., in real time. Based on this data, the terminal recognizes the user's emotions in real time and transmits them to the server.

[0590] Based on the emotional information transmitted, the server dynamically adjusts the simulation situation to provide the user with the optimal learning experience. For example, if the server detects that the user is relaxed, it can present a more challenging task. A concrete example is a customer service simulation in a cafe. In this case, a generative AI model can be used to input prompts such as "30-year-old female, lives in an urban area, hobbies are reading and traveling," and then design a simulation that matches those conditions.

[0591] This invention provides specific means for constructing a system that can improve practical skills by generating individual evaluations and improvement suggestions and providing feedback to users.

[0592] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0593] Step 1:

[0594] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. The server stores this information as input data in a database, preparing the basic data necessary for subsequent processing.

[0595] Step 2:

[0596] The server uses a generative AI model to generate a virtual person profile from collected user information. Specifically, stored user data is fed to the AI ​​model, and a virtual person profile is output based on the algorithm the model has learned. This output is used in the next simulation design step.

[0597] Step 3:

[0598] The server designs multiple simulation scenarios based on the generated virtual person profile. Specifically, it generates customer service training and customer interaction scenarios tailored to the user's profile and characteristics. During this design process, the scenarios and difficulty levels of the virtual situations are set, and the necessary materials and configuration data for each simulation are output.

[0599] Step 4:

[0600] The device utilizes cameras and sensors to detect the user's facial expressions, voice tone, and heart rate in real time. This data is used as input for an emotion recognition algorithm to analyze the user's emotional state. The analyzed results are then transmitted from the device to a server.

[0601] Step 5:

[0602] The server receives emotional data transmitted from the terminal as input and dynamically adjusts the simulation situation based on it. Specifically, the server analyzes the emotional data and changes the pace and content of the scenario as needed. This process provides the user with the optimal simulation experience.

[0603] Step 6:

[0604] Once the simulation is complete, the server analyzes the user's emotional history and the simulation results. This analysis generates an evaluation and specific improvement suggestions for each user. These include advice for the next simulation and techniques for skill improvement, which are then fed back to the user.

[0605] (Application Example 2)

[0606] 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."

[0607] In modern customer service, staff are required to accurately understand customers' emotions and respond appropriately in an instant. However, achieving this requires high skill and experience, and they may not be able to respond flexibly to the ever-changing needs and emotions of customers. Therefore, there is a need for a means to support staff skill improvement by providing effective emotion recognition and feedback in real time.

[0608] 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.

[0609] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation situations based on the generated virtual person profile; and means for detecting the user's emotions in real time and adjusting the content and difficulty level of the simulation situations. This allows the user to experience the simulation while receiving real-time feedback based on their emotions, thereby improving their customer service skills and customer interaction techniques.

[0610] A "data source" is a source of information used to collect information about a user.

[0611] "User information" refers to detailed information about individual users, such as age, gender, region, hobbies, and occupation.

[0612] A "generative AI model" is an artificial intelligence technology used to generate a virtual profile of a person based on collected user information.

[0613] A "virtual character" is a digital representation of a person created by an AI model based on collected user information, for use in simulations.

[0614] A "simulation environment" is a training environment designed based on a virtual character profile, which users then experience.

[0615] The "emotion engine" is a technology that analyzes and detects emotions in real time from the user's facial expressions, tone of voice, heart rate, and other factors.

[0616] "Real-time feedback" refers to evaluation information that is immediately provided to users while they are experiencing a simulation, including results and areas for improvement.

[0617] "Advice" refers to practical guidance provided based on the user's behavior and emotional data.

[0618] "Improvement suggestions" are proposals provided to individual users based on the analyzed simulation results, aimed at improving their skills and abilities.

[0619] The system for realizing this application consists of a server, terminal, and user working together. Specifically, the server first collects user information from data sources and uses this information to generate a virtual person profile using a generative AI model. Based on this generated person profile, the server designs multiple simulation scenarios and provides them to the terminal.

[0620] The device is equipped with a camera and sensors that detect the user's facial expressions, voice tone, heart rate, and other data in real time. This allows the emotion engine to analyze the user's emotions and send the emotion data to a server. Based on this emotion data, the server can dynamically adjust the content and difficulty level of the simulation.

[0621] For example, if a user is feeling anxious, the server will take steps to alleviate their anxiety by providing more concise explanations and guidance. Conversely, if a user is relaxed, the server will present more challenging tasks to help them improve their skills. Throughout this process, users receive feedback via real-time sentiment analysis, allowing them to identify areas for improvement based on their responses.

[0622] Furthermore, as a concrete example, when a user is conducting a customer service simulation in a store, the system generates a prompt such as, "Please tell me the necessary customer service methods to alleviate the customer's anxiety," and then provides advice in real time that reflects the results of the sentiment analysis. In this way, users can instantly learn and practice appropriate responses.

[0623] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0624] Step 1:

[0625] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. Based on this data, an AI model generates a virtual profile of the user. The input is user information, and the output is a virtual profile.

[0626] Step 2:

[0627] The server designs multiple simulation scenarios based on the generated virtual character profile and provides them to the terminal. The input is the virtual character profile, and the output is the simulation scenario. The server utilizes the generated AI model in this process to create appropriate scenarios.

[0628] Step 3:

[0629] While the simulation is running, the device uses its camera and sensors to input the user's facial expressions, voice tone, and heart rate into the emotion engine in real time. The input is the user's biometric data, and the output is the result of the emotion analysis.

[0630] Step 4:

[0631] The emotion engine detects the user's emotions and sends them to the server. Based on this data, the server dynamically adjusts the content and difficulty of the simulation. The input is the emotion data, and the output is the adjusted simulation state.

[0632] Step 5:

[0633] Based on the adjustments made to the simulation received by the user, real-time feedback is provided through the terminal. The input is the adjusted simulation situation, and the output is the feedback to the user. Specifically, if the user is stressed, the server will provide clearer guidance, and if the server determines that the user is relaxed, it will present a more complex challenge.

[0634] Step 6:

[0635] Based on the simulation results, the server generates personalized improvement suggestions and presents them to the user. The input is the final simulation results and sentiment history, and the output is the improvement suggestions. In this process, a generative AI model generates prompt sentences appropriate for each user.

[0636] Step 7:

[0637] Users can improve their skills based on the suggestions and feedback provided. In this final step, a new learning plan is developed based on the input feedback information, and guidelines are provided to help users achieve better results. The output is the user's improved ability.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] [Fourth Embodiment]

[0642] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0643] 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.

[0644] 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).

[0645] 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.

[0646] 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.

[0647] 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).

[0648] 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.

[0649] 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.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] 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.

[0654] 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".

[0655] As an embodiment for carrying out the present invention, the system is configured according to the following procedure.

[0656] First, the server collects user information from data sources. This information includes age group, occupation, region, hobbies, and behavioral patterns, and is used as input data to generate a virtual profile of the person. The server preprocesses this data, removing outliers and imputing missing values, to prepare it for input into the model.

[0657] Subsequently, the server runs the generation AI model and generates a virtual profile based on the pre-processed user information. For example, it outputs a virtual person with various characteristics, such as a virtual person with purchasing behavior and information gathering tendencies specific to a particular age group, or a virtual person whose occupation is an engineer and whose hobby is the outdoors.

[0658] Next, the server designs simulation scenarios based on the generated virtual character profile. These include situations such as customer service at a tourist information center or handling customer complaints at a retail store. Each scenario reflects the specific behavioral patterns and requests of that virtual character profile.

[0659] On the other hand, the terminal presents the user with a list of available virtual character profiles and simulation situations through its user interface. The user can view this list and make selections that suit their training and learning objectives.

[0660] When the user makes a selection, the device retrieves the corresponding simulation data from the server and runs the simulation. The user can experience this situation in real time on the device. As the simulation progresses, the user takes actions according to the scenario and can check the results immediately.

[0661] Finally, user feedback is sent to the server via the terminal. The server aggregates this feedback and uses an evaluation model that analyzes the simulation results to quantify and evaluate the effectiveness of the responses for each virtual character. Subsequently, improvement suggestions tailored to each individual virtual character are automatically generated and presented to the user. In this way, users can continuously improve their skills and acquire the ability to respond in situations similar to actual work.

[0662] In the above configuration, the present invention can provide practical training tailored to diverse work environments and customer needs.

[0663] The following describes the processing flow.

[0664] Step 1:

[0665] The server begins collecting user information from data sources. The collected data includes detailed information such as age, gender, region, hobbies, occupation, and purchase history. This data is used as the basis for generating a virtual profile.

[0666] Step 2:

[0667] The server performs data preprocessing on the collected user information. Specifically, it cleanses the data by imputing missing values ​​and filtering outliers, and converts the data into a format suitable for the AI ​​model.

[0668] Step 3:

[0669] The server runs a generative AI model, using pre-processed data as input to generate virtual character profiles with various characteristics. These generated character profiles reflect specific behavioral patterns and preferences.

[0670] Step 4:

[0671] Based on the generated virtual character profile, the server begins designing various simulation scenarios. These include typical customer interaction scenarios and problem-solving situations, with customized content tailored to the characteristics of the virtual character profile.

[0672] Step 5:

[0673] The terminal generates a user interface, displaying to the user a list of options for each virtual character and their corresponding simulation situation. This interface is designed to be intuitive and easy to use.

[0674] Step 6:

[0675] The user selects a virtual character and simulation scenario of interest through their device. Based on this selection, the system is prepared to run the simulation.

[0676] Step 7:

[0677] The terminal receives selected simulation data from the server and executes the simulation. The user experiences the scenario on the terminal and responds to the displayed challenges.

[0678] Step 8:

[0679] After the simulation is complete, the device will display a screen for user feedback, allowing users to provide feedback based on their experience.

[0680] Step 9:

[0681] The server evaluates the results of the simulation based on feedback received from the user. Using an evaluation model, it analyzes the quality of responses to each virtual character and identifies areas for improvement.

[0682] Step 10:

[0683] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to obtain concrete guidelines for continuously improving their response capabilities.

[0684] (Example 1)

[0685] 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".

[0686] In today's diverse work environments, efficiently providing practical training and supporting the skill development of users is a crucial challenge. However, traditional training methods struggle to create hypothetical situations tailored to individual users and to present specific improvement measures appropriate to those situations. As a result, users are unable to effectively acquire individualized problem-solving skills.

[0687] 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.

[0688] In this invention, the server includes means for preprocessing user information obtained from a data source by removing outliers and imputing missing values; means for generating a virtual person profile using a generative AI model based on the preprocessed user information; and means for designing specific behavioral patterns and requests as simulation situations based on the generated virtual person profile. This enables the provision of practical training tailored to individual learning objectives, allowing users to improve their skills more effectively.

[0689] A "data source" is a fundamental location or system for collecting information, from which user information is obtained.

[0690] "User information" refers to data such as age group, occupation, region, hobbies, and behavioral patterns, and is basic information used to generate a virtual profile.

[0691] An "outlier" refers to a value in the data that falls outside the normal range and is removed because it may impair the accuracy of the data.

[0692] "Missing values" refer to values ​​that are missing from a dataset, and data integrity is maintained by imputing these missing values.

[0693] "Preprocessing" refers to a series of preparatory processes to prepare data so that it can be used appropriately by AI models.

[0694] A "generative AI model" is an algorithm or system designed to generate a virtual human profile using machine learning techniques.

[0695] A "virtual character profile" is a fictional character profile with specific characteristics and behavioral patterns, generated by an AI model based on collected user information.

[0696] A "simulation situation" is a specific scenario or environment designed based on a virtual character, and is a virtual situation for the user to experience.

[0697] An "evaluation model" is an algorithm or system used to analyze the results of a simulation and quantify and evaluate the effectiveness of the corresponding actions for each virtual character.

[0698] An "improvement plan" refers to modifications or improvements proposed based on the results of a simulation to make a particular response more effective.

[0699] This invention relates to a system for generating a virtual character and providing a simulation based on that character. The following elements are important for carrying out this invention.

[0700] First, the server collects user information from the data source. At this stage, it connects to the database using an API and collects user information such as age group, occupation, region, hobbies, and behavioral patterns. The acquired data is preprocessed using the Pandas library by removing outliers and imputing missing values ​​with the median. This preprocessing process facilitates data input into the generative AI model.

[0701] Subsequently, the server runs a pre-trained generative AI model using machine learning libraries such as TensorFlow to generate a virtual profile based on pre-processed user information. This model can generate a variety of virtual profiles with specific characteristics. For example, if a virtual profile is generated of a "male engineer in his 30s with an outdoor hobby," it can analyze his purchasing tendencies and preferences.

[0702] The server then designs a simulation that reflects specific behavioral patterns and requests based on the generated virtual character profile. This simulation situation is constructed, for example, as a customer service or complaint handling scenario, facilitating a practical user experience.

[0703] Next, the terminal uses a web browser to present the user with a list of virtual character profiles and simulation scenarios. The user can then select a simulation that suits their purpose. Once the selection is complete, the terminal retrieves the corresponding simulation data from the server and executes the simulation in real time. For example, in customer service training, the user can interact with a virtual customer in a conversational format and immediately see the results.

[0704] Ultimately, user feedback is sent from the terminal to the server. The server aggregates this feedback and analyzes the simulation results using an evaluation model. Based on these results, improvement suggestions tailored to a specific hypothetical persona are generated and provided to the user. This allows users to continuously improve themselves and acquire skills relevant to their work.

[0705] As a concrete example, a prompt such as, "What products would you recommend for a male engineer in his 30s whose hobby is camping?" will prompt the system to suggest products that match the user's purchasing tendencies and interests based on that profile. In this way, the invention provides users with practical and personalized learning and training opportunities.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] The server collects user information from the data source. In this step, it uses an API to connect to the database and retrieve information such as age group, occupation, region, hobbies, and behavioral patterns. The input is raw data from the database, and the output is structured user information.

[0709] Step 2:

[0710] The server preprocesses the acquired data. Specifically, it uses the Pandas library to remove outliers and impute missing values. The input is the output data from step 1, and the quality is improved through data cleansing, resulting in preprocessed data as output.

[0711] Step 3:

[0712] The server generates a virtual human profile using a generative AI model. Preprocessed data is input into the model using the TensorFlow library. The data calculations performed here involve extracting and combining data features. The output is a virtual human profile with diverse characteristics.

[0713] Step 4:

[0714] The server designs the simulation situation based on the generated virtual character profile. Specific scenarios are created reflecting the characteristics obtained from the generated AI model. The input is the output from step 3, and the output is simulation environment data that constitutes a specific behavioral pattern.

[0715] Step 5:

[0716] The terminal presents the user with a list of virtual character profiles and simulation situations via a web browser. The user then selects a scenario that suits their learning objectives. The input is the output data from step 4, and the selectable interfaces are output.

[0717] Step 6:

[0718] When the user selects a scenario, the terminal retrieves the corresponding simulation data from the server and executes the simulation. For example, in a customer service simulation, the user interacts with a virtual customer in real time. The input is the scenario selected by the user in step 5, and the output is a real-time simulation exercise.

[0719] Step 7:

[0720] The system collects user feedback and sends it from the terminal to the server. The server uses the feedback to run an evaluation model and analyzes the simulation results. The input is the user's actions during the simulation and their feedback, and the output is quantified evaluation data as a result of the analysis.

[0721] Step 8:

[0722] The server generates improvement suggestions based on the analyzed data and presents them to the user. Using a generation AI model, it automatically derives specific improvement measures for a particular virtual character. The input is the evaluation data from step 7, and the output is customized advice presented to the user.

[0723] (Application Example 1)

[0724] 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".

[0725] Conventional customer service training systems have drawbacks, such as difficulty in providing practical training that closely matches actual work situations and difficulty in obtaining efficient feedback to improve individual customer service skills. This invention aims to effectively improve customer service skills in actual stores through individualized simulations using a virtual persona.

[0726] 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.

[0727] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation scenarios tailored to customer service content in a physical store based on the generated virtual person profile; and means for analyzing the results of the simulation scenarios and extracting evaluation and improvement points for each virtual person profile. This enables users to receive training in an environment close to actual work while obtaining specific feedback based on their individual responses.

[0728] A "data source" is a source of information used to collect information about a user, and this includes online data and user profile information.

[0729] A "generative AI model" is an artificial intelligence model that generates a virtual human profile from input data, thereby constructing the human profile used in virtual simulations.

[0730] A "virtual character profile" is a model of a non-existent person generated based on user information, possessing characteristics such as age group, hobbies, and behavioral patterns.

[0731] A "simulation scenario" is a scenario that mimics a situation corresponding to a hypothetical person, and is intended to reproduce real-world situations in customer service training.

[0732] A "real-time customer service training scenario" is a scenario that allows users to simulate and practice customer service procedures on the spot under conditions similar to those in an actual store.

[0733] A "smart device" is a portable electronic device used to support simulations and virtual reality, and examples include smart glasses and mobile devices.

[0734] A "user interface" refers to the screens and functions that allow users to interact with a system, and is used for selecting and experiencing simulations.

[0735] "Personalized improvement suggestions" refer to specific improvement methods and advice provided to users based on a hypothetical person profile and the results of simulations based on that profile.

[0736] The system implementing this invention consists of a server and a terminal with a user interface. The server continuously collects user information from data sources, preprocesses the collected data to remove outliers, and imputes missing values. The hardware includes a computer server used to efficiently perform data processing. The software includes programs using Python or TensorFlow to support this process.

[0737] Pre-processed user information is input into a generating AI model. This model uses machine learning algorithms to generate a virtual profile of a person. Specific examples include hypothetical customer profiles with different age groups and hobbies, which serve as the basis for diverse customer service simulations.

[0738] Based on the generated virtual character profile, the server designs a simulation that mimics customer service situations in a real store. The simulation content is structured around specific scenarios to allow store employees to receive customer service training. For example, it includes scenarios such as "introducing new products" and "handling customer complaints."

[0739] The terminal uses smart devices (e.g., smart glasses) to present these simulation scenarios to the user. Through these, the user can conduct customer service training in an environment that closely resembles a real store. The user interface on the terminal uses a real-time simulation application based on Unity.

[0740] After the simulation, user feedback is sent back to the server. The server analyzes the simulation results based on this feedback and extracts evaluations and areas for improvement for each virtual character. This information is provided to the user and displayed as personalized improvement suggestions.

[0741] An example of a prompt is: "Generate a customer service scenario that increases the interest of a 25-year-old woman living in area A, whose hobby is fashion shopping, in a new product." Using prompts like this, simulations tailored to each hypothetical character can be efficiently generated.

[0742] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0743] Step 1:

[0744] The server collects user information from data sources. This includes data such as age, occupation, region, hobbies, and behavioral patterns. Based on the collected information, outliers are removed and missing values ​​are imputed to prepare the input data for the generative AI model. Preprocessing is performed using Python and the NumPy library to create a clean dataset. The input to this process is raw user data, and the output is preprocessed user information.

[0745] Step 2:

[0746] The server inputs pre-processed user information into a generation AI model to generate a virtual profile. TensorFlow is used for this generation. Pre-formatted user information is provided as input, and a characterized virtual profile is obtained as output. For example, it can generate profiles with purchasing tendencies and information gathering tendencies.

[0747] Step 3:

[0748] The server designs simulation scenarios for use in physical stores based on the generated virtual character profiles. Prompt statements are used in the scenario design, constructing scenarios that include dialogue and behavioral patterns aligned with the generated character profiles. The inputs are the virtual character profiles and prompt statements, and the output is the completed scenario. This process involves programming the scenario logic using a scripting language.

[0749] Step 4:

[0750] The terminal presents scenarios to the user via a smart device and conducts customer service training. The user experiences virtual scenarios in real time through smart glasses or similar devices and learns how to respond. The input is scenario data, and the output is user behavior data and feedback. In this process, the Unity engine is used to render the simulation environment in real time.

[0751] Step 5:

[0752] User feedback is sent to the server, where the results are analyzed to extract evaluations and areas for improvement. This uses a machine learning model to quantify user interaction skills. The input is user feedback, and the output is the analysis results and areas for improvement. Based on the collected data, the analysis model is run using Scikit-learn.

[0753] Step 6:

[0754] The server generates personalized improvement suggestions based on the analysis results and presents them to the user. This allows the user to confirm specific directions for skill improvement. The input is the analysis results, and the output is the improvement suggestion report. A text formatting program is used to improve the readability of the report.

[0755] 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.

[0756] As an embodiment for carrying out the present invention, a system incorporating an emotion engine is configured as follows:

[0757] First, the server collects user information from data sources and generates a virtual profile using a generative AI model. The collected data includes detailed information such as age, gender, region, hobbies, and occupation. Based on this information, the server designs a simulation scenario that corresponds to the virtual profile. This process includes customer service simulations and customer interaction simulations.

[0758] Furthermore, this invention uses an emotion engine to recognize the user's emotions in real time. Through cameras and sensors installed in the terminal, it detects emotions from the user's facial expressions, tone of voice, heart rate, etc. For example, if the user feels stressed during a simulation, the emotion engine recognizes that emotion and sends a signal to the server.

[0759] The server automatically adjusts the content and difficulty of the simulation situation based on the transmitted emotion data. For example, if it determines that the user is relaxed, it can speed up the scenario or present more complex challenges. On the other hand, if the user is confused, it provides guidance and additional support information to help them learn.

[0760] Users experience these simulations on their devices, and the emotion engine monitors the feedback generated during the process, allowing them to understand their own reactions and areas for improvement in real time. Once the simulation is complete, the server analyzes the user's emotional history and simulation results, and presents personalized improvement suggestions. These suggestions may include not only future response methods but also techniques for emotional control.

[0761] In the above configuration, the present invention can provide a flexible simulation environment that responds to the user's emotions, thereby enabling more effective improvement of practical skills.

[0762] The following describes the processing flow.

[0763] Step 1:

[0764] The server collects user information from data sources. This data includes many attributes such as age, gender, occupation, region, and past purchase history. This data is used as a basis for generating highly accurate virtual profiles of individuals.

[0765] Step 2:

[0766] The server preprocesses the collected data and uses a generative AI model to generate diverse virtual personas. These include personas with specific behavioral patterns and preferences. For example, personas such as a travel enthusiast in their 30s living in a city or a forty-something engineer raising children are generated.

[0767] Step 3:

[0768] The server designs various simulation scenarios based on the generated virtual character profile. For example, these include situations such as customer service in retail or handling complaints at a customer support center, with content tailored to the characteristics of the virtual character.

[0769] Step 4:

[0770] The terminal presents the user with a selection of virtual character profiles and simulation scenarios via a user interface. The user selects a scenario suitable for their skill development and initiates the simulation.

[0771] Step 5:

[0772] The emotion engine built into the device monitors the user's facial expressions, voice tone, and biometric information through the camera and microphone to detect the user's emotional state in real time.

[0773] Step 6:

[0774] The emotion engine sends the user's emotional state to the server in real time, and the server adaptively adjusts the simulation's situation and difficulty based on that data. For example, when the user is frustrated, the server increases the amount of information provided or strengthens the assistance.

[0775] Step 7:

[0776] The user progresses through the simulation on the device and performs tasks requested during the session. The emotion engine monitors the user's emotions and continuously sends data to the server.

[0777] Step 8:

[0778] Once the simulation is complete, the terminal presents the user with feedback and an evaluation of the entire session. Based on the sentiment data, the server generates personalized improvement suggestions tailored to the user and provides them to the user through the terminal.

[0779] Step 9:

[0780] Based on this feedback and suggestions for improvement, users can revise their future learning plans and approaches, helping them to improve their skills.

[0781] (Example 2)

[0782] 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".

[0783] In modern society, there is a demand for flexible and effective simulation environments tailored to the characteristics of users. However, conventional simulation systems have the challenge of being unable to dynamically adjust to users' real-time emotions, making it difficult to support deep experiences and skill improvement.

[0784] 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.

[0785] In this invention, the server includes means for collecting user information and generating a virtual person profile using a generative model; means for designing multiple virtual situations based on the virtual person profile; and means for recognizing the user's emotions in real time through a detection device installed in the terminal and processing that information. This enables dynamic adjustment of the simulation situation based on the user's emotions.

[0786] "User information" refers to detailed attribute data of an individual, such as age, gender, region, hobbies, and occupation.

[0787] A "generative model" refers to an artificial intelligence algorithm or program used to create a virtual persona based on given data.

[0788] A "virtual person profile" refers to a fictional human profile generated based on collected user information.

[0789] A "virtual situation" refers to various simulation environments designed based on a fictional character profile, which users then experience.

[0790] A "terminal" refers to a device equipped with devices such as cameras and sensors, which functions as an interface with the user.

[0791] A "detection device" refers to a device that collects data such as the user's facial expressions, voice tone, and heart rate, enabling emotional analysis.

[0792] "Real-time" refers to near-instantaneous data processing and response capabilities, enabling emotion recognition and simulation adjustments without delay.

[0793] "Evaluation" refers to the process of determining a user's performance and skills based on the results of a simulation.

[0794] "Improvement proposals" refer to specific methods and steps presented based on the evaluation results to improve skills and overcome challenges in the future.

[0795] This invention consists of a system that provides a virtual experience using user information. The server plays a central role in the system, with the terminal acting as the interface. The server collects user information from data sources and generates a virtual profile using a generative AI model. This generative AI model is based on machine learning algorithms and uses information such as the user's age, gender, region, hobbies, and occupation as input data.

[0796] The server designs multiple simulation scenarios based on a virtual persona. This includes the process of generating virtual environments and defining tasks. Furthermore, the terminal is equipped with cameras and sensors to detect the user's facial expressions, voice tone, heart rate, etc., in real time. Based on this data, the terminal recognizes the user's emotions in real time and transmits them to the server.

[0797] Based on the emotional information transmitted, the server dynamically adjusts the simulation situation to provide the user with the optimal learning experience. For example, if the server detects that the user is relaxed, it can present a more challenging task. A concrete example is a customer service simulation in a cafe. In this case, a generative AI model can be used to input prompts such as "30-year-old female, lives in an urban area, hobbies are reading and traveling," and then design a simulation that matches those conditions.

[0798] This invention provides specific means for constructing a system that can improve practical skills by generating individual evaluations and improvement suggestions and providing feedback to users.

[0799] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0800] Step 1:

[0801] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. The server stores this information as input data in a database, preparing the basic data necessary for subsequent processing.

[0802] Step 2:

[0803] The server uses a generative AI model to generate a virtual person profile from collected user information. Specifically, stored user data is fed to the AI ​​model, and a virtual person profile is output based on the algorithm the model has learned. This output is used in the next simulation design step.

[0804] Step 3:

[0805] The server designs multiple simulation scenarios based on the generated virtual person profile. Specifically, it generates customer service training and customer interaction scenarios tailored to the user's profile and characteristics. During this design process, the scenarios and difficulty levels of the virtual situations are set, and the necessary materials and configuration data for each simulation are output.

[0806] Step 4:

[0807] The device utilizes cameras and sensors to detect the user's facial expressions, voice tone, and heart rate in real time. This data is used as input for an emotion recognition algorithm to analyze the user's emotional state. The analyzed results are then transmitted from the device to a server.

[0808] Step 5:

[0809] The server receives emotional data transmitted from the terminal as input and dynamically adjusts the simulation situation based on it. Specifically, the server analyzes the emotional data and changes the pace and content of the scenario as needed. This process provides the user with the optimal simulation experience.

[0810] Step 6:

[0811] Once the simulation is complete, the server analyzes the user's emotional history and the simulation results. This analysis generates an evaluation and specific improvement suggestions for each user. These include advice for the next simulation and techniques for skill improvement, which are then fed back to the user.

[0812] (Application Example 2)

[0813] 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".

[0814] In modern customer service, staff are required to accurately understand customers' emotions and respond appropriately in an instant. However, achieving this requires high skill and experience, and they may not be able to respond flexibly to the ever-changing needs and emotions of customers. Therefore, there is a need for a means to support staff skill improvement by providing effective emotion recognition and feedback in real time.

[0815] 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.

[0816] In this invention, the server includes means for generating a virtual person profile using a generative AI model based on user information collected from a data source; means for designing and providing multiple simulation situations based on the generated virtual person profile; and means for detecting the user's emotions in real time and adjusting the content and difficulty level of the simulation situations. This allows the user to experience the simulation while receiving real-time feedback based on their emotions, thereby improving their customer service skills and customer interaction techniques.

[0817] A "data source" is a source of information used to collect information about a user.

[0818] "User information" refers to detailed information about individual users, such as age, gender, region, hobbies, and occupation.

[0819] A "generative AI model" is an artificial intelligence technology used to generate a virtual profile of a person based on collected user information.

[0820] A "virtual character" is a digital representation of a person created by an AI model based on collected user information, for use in simulations.

[0821] A "simulation environment" is a training environment designed based on a virtual character profile, which users then experience.

[0822] The "emotion engine" is a technology that analyzes and detects emotions in real time from the user's facial expressions, tone of voice, heart rate, and other factors.

[0823] "Real-time feedback" refers to evaluation information that is immediately provided to users while they are experiencing a simulation, including results and areas for improvement.

[0824] "Advice" refers to practical guidance provided based on the user's behavior and emotional data.

[0825] "Improvement suggestions" are proposals provided to individual users based on the analyzed simulation results, aimed at improving their skills and abilities.

[0826] The system for realizing this application consists of a server, terminal, and user working together. Specifically, the server first collects user information from data sources and uses this information to generate a virtual person profile using a generative AI model. Based on this generated person profile, the server designs multiple simulation scenarios and provides them to the terminal.

[0827] The device is equipped with a camera and sensors that detect the user's facial expressions, voice tone, heart rate, and other data in real time. This allows the emotion engine to analyze the user's emotions and send the emotion data to a server. Based on this emotion data, the server can dynamically adjust the content and difficulty level of the simulation.

[0828] For example, if a user is feeling anxious, the server will take steps to alleviate their anxiety by providing more concise explanations and guidance. Conversely, if a user is relaxed, the server will present more challenging tasks to help them improve their skills. Throughout this process, users receive feedback via real-time sentiment analysis, allowing them to identify areas for improvement based on their responses.

[0829] Furthermore, as a concrete example, when a user is conducting a customer service simulation in a store, the system generates a prompt such as, "Please tell me the necessary customer service methods to alleviate the customer's anxiety," and then provides advice in real time that reflects the results of the sentiment analysis. In this way, users can instantly learn and practice appropriate responses.

[0830] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0831] Step 1:

[0832] The server collects user information from data sources. This information includes age, gender, region, hobbies, and occupation. Based on this data, an AI model generates a virtual profile of the user. The input is user information, and the output is a virtual profile.

[0833] Step 2:

[0834] The server designs multiple simulation scenarios based on the generated virtual character profile and provides them to the terminal. The input is the virtual character profile, and the output is the simulation scenario. The server utilizes the generated AI model in this process to create appropriate scenarios.

[0835] Step 3:

[0836] While the simulation is running, the device uses its camera and sensors to input the user's facial expressions, voice tone, and heart rate into the emotion engine in real time. The input is the user's biometric data, and the output is the result of the emotion analysis.

[0837] Step 4:

[0838] The emotion engine detects the user's emotions and sends them to the server. Based on this data, the server dynamically adjusts the content and difficulty of the simulation. The input is the emotion data, and the output is the adjusted simulation state.

[0839] Step 5:

[0840] Based on the adjustments made to the simulation received by the user, real-time feedback is provided through the terminal. The input is the adjusted simulation situation, and the output is the feedback to the user. Specifically, if the user is stressed, the server will provide clearer guidance, and if the server determines that the user is relaxed, it will present a more complex challenge.

[0841] Step 6:

[0842] Based on the simulation results, the server generates personalized improvement suggestions and presents them to the user. The input is the final simulation results and sentiment history, and the output is the improvement suggestions. In this process, a generative AI model generates prompt sentences appropriate for each user.

[0843] Step 7:

[0844] Users can improve their skills based on the suggestions and feedback provided. In this final step, a new learning plan is developed based on the input feedback information, and guidelines are provided to help users achieve better results. The output is the user's improved ability.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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."

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] The following is further disclosed regarding the embodiments described above.

[0867] (Claim 1)

[0868] A means of generating a virtual person profile using a generative AI model based on user information collected from data sources,

[0869] A means for designing and providing multiple simulation situations based on a generated virtual character profile,

[0870] A method for analyzing the results of the simulation and extracting evaluation and improvement points for each virtual character,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, characterized by comprising means for providing an interface for a user to select and experience a virtual character and a simulated situation.

[0874] (Claim 3)

[0875] The system according to claim 1, characterized by comprising means for presenting personalized improvement suggestions suitable for the generated virtual character.

[0876] "Example 1"

[0877] (Claim 1)

[0878] A means for preprocessing user information obtained from a data source by removing outliers and imputing missing values,

[0879] A means for generating a virtual person profile using a generation AI model based on pre-processed user information,

[0880] A means of designing specific behavioral patterns and requirements as a simulated situation based on a generated virtual character profile,

[0881] A means of quantifying and evaluating the effectiveness of responses for each virtual character using an evaluation model that collects user feedback and analyzes the simulation results,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, characterized by comprising means for providing a user interface that allows the user to select a virtual character and a simulation situation.

[0885] (Claim 3)

[0886] The system according to claim 1, characterized by comprising means for automatically generating and presenting personalized improvement proposals using a generation AI model based on the evaluated results.

[0887] "Application Example 1"

[0888] (Claim 1)

[0889] A means of generating a virtual person profile using a generative AI model based on user information collected from data sources,

[0890] A means of designing and providing multiple simulation scenarios specifically tailored to customer service in physical stores, based on a generated virtual character profile.

[0891] A method for analyzing the results of the simulation and extracting evaluation and improvement points for each virtual character,

[0892] Using smart devices, a means of providing customer service training scenarios in real time and enabling users to acquire skills that closely resemble those of actual work,

[0893] A system that includes this.

[0894] (Claim 2)

[0895] The system according to claim 1, characterized by comprising means for providing a user interface for a user to select and experience a virtual character and a simulation situation.

[0896] (Claim 3)

[0897] The system according to claim 1, characterized by providing means to support the improvement of customer service skills in physical stores by presenting personalized improvement suggestions suitable for the generated virtual character.

[0898] "Example 2 of combining an emotion engine"

[0899] (Claim 1)

[0900] A means for collecting user information and generating a virtual person profile using a generative model,

[0901] A means of designing multiple virtual situations based on a virtual character profile,

[0902] A means of recognizing the user's emotions in real time through a detection device installed in the terminal and processing that information,

[0903] A means for dynamically adjusting the virtual situation based on recognized emotional information,

[0904] A means of analyzing the results of a hypothetical situation and presenting evaluations and improvement suggestions for each hypothetical character,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, characterized by comprising means for providing a function for a user to select and experience a virtual character and a virtual situation.

[0908] (Claim 3)

[0909] The system according to claim 1, characterized by having a function to present personalized improvement suggestions suitable for the generated virtual character.

[0910] "Application example 2 of combining emotional engines"

[0911] (Claim 1)

[0912] A means of generating a virtual person profile using a generative AI model based on user information collected from data sources,

[0913] A means for designing and providing multiple simulation situations based on a generated virtual character profile,

[0914] A means to detect the user's emotions in real time and adjust the content and difficulty level of the simulation situation,

[0915] A method for analyzing the results of the simulation and extracting evaluation and improvement points for each virtual character,

[0916] A means of providing advice in real time based on user sentiment data,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, characterized by comprising means for providing an interface for a user to select and experience a virtual character and a simulated situation.

[0920] (Claim 3)

[0921] The system according to claim 1, characterized by providing personalized improvement suggestions suitable for the generated virtual character, and further comprising means for the user to learn response methods based on real-time sentiment analysis. [Explanation of Symbols]

[0922] 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. A means of generating a virtual person profile using a generative AI model based on user information collected from data sources, A means of designing and providing multiple simulation situations based on a generated virtual character profile, A method for analyzing the results of the simulation and extracting evaluation and improvement points for each virtual character, A system that includes this.

2. The system according to claim 1, characterized by comprising means for providing an interface for a user to select and experience a virtual character and a simulation situation.

3. The system according to claim 1, characterized by comprising means for presenting personalized improvement suggestions suitable for the generated virtual character.

Images