system

Abstract

We provide the system. [Solution] A means of creating fictitious customer information using a generation module, A means for simulating interaction based on the aforementioned fictitious customer information, A means for providing feedback to the user based on the analysis results of the aforementioned interaction, 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 the training of new employees, there is a problem that it is difficult to effectively and quickly improve customer service skills. In the conventional training methods, it is difficult to accumulate real experiences for each situation, and the opportunity to systematically learn the response ability to a specific persona is limited. Therefore, it takes time for new employees to become immediately available. In order to solve this problem, it is necessary to develop a training system that can effectively and efficiently acquire customer service skills.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides a system that creates fictional customer information using a generation module and simulates interactions based on that information. Furthermore, by analyzing this interaction in real time and providing specific feedback to the user based on the results, it becomes possible to quickly and efficiently improve the user's customer service skills. As a result, new employees can acquire the skills to immediately respond to diverse customer personas in a short period of time.

[0006] A "generating module" is a component that has the function of automatically creating fictitious customer information using specific algorithms and data.

[0007] "Fictional customer information" refers to profile data of a hypothetical customer with specific backgrounds and needs, generated for the purpose of conducting simulations.

[0008] "Simulating interaction" refers to the process of simulating and recreating a virtual conversation that takes place between a user and a fictional customer that has been created.

[0009] "Analysis results" refer to analytical data generated to evaluate user responses in real time during interactions and to determine their appropriateness and areas for improvement.

[0010] "Providing feedback" refers to the process of returning information to the user, such as evaluations and areas for improvement based on the analysis of their interactions. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled 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.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. This system is built via a server that has a built-in generation module. The server first generates fictional customer information. This information includes a detailed profile, such as age, gender, hobbies, specific needs, and problems.

[0033] The server then sends the generated customer information to the terminal. The terminal is a device operated by the user, and it starts an interaction simulation based on the received information. During this simulation, the user can interact with a fictional customer through the terminal, asking appropriate questions and making suggestions. All of the user's responses are recorded.

[0034] The server then analyzes the user's responses in real time. This analysis includes natural language processing techniques to evaluate how appropriate the user's responses are. Based on this evaluation, the server sends feedback to the terminal. This feedback specifically highlights the user's successes and areas for improvement.

[0035] As a concrete example, consider a simulation where a server generates a persona of an "elderly person who doesn't know how to operate something," and a user responds by explaining the operating procedure in simple language. The server evaluates whether the user's explanation was easy to understand and sends feedback to the terminal. This feedback becomes valuable information for the user to improve in subsequent simulations. Through this process, the user can efficiently improve their customer service skills.

[0036] The following describes the processing flow.

[0037] Step 1:

[0038] The server uses a generation module to generate fictional customer information. This customer information includes age, gender, hobbies, and specific needs or challenges, creating a detailed profile based on a scenario.

[0039] Step 2:

[0040] The server sends the generated customer information to the terminal. The terminal receives this information and presents it to the user through an interface.

[0041] Step 3:

[0042] The user operates the terminal and starts a simulation based on the fictional customer information presented. The user asks questions and makes suggestions for products and services.

[0043] Step 4:

[0044] The terminal records user responses and suggestions and sends them to the server in real time. The server receives this data.

[0045] Step 5:

[0046] The server analyzes the user's response data it receives. Using natural language processing techniques, it evaluates the user's response and determines its appropriateness and specificity.

[0047] Step 6:

[0048] The server generates feedback based on the analysis results. This feedback includes the user's strengths, areas for improvement, and specific advice.

[0049] Step 7:

[0050] The server sends the generated feedback to the terminal and presents it to the user. Through this feedback, the user gains clues to improve their skills for the next simulation.

[0051] (Example 1)

[0052] 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."

[0053] To effectively improve customer service skills, an interaction simulation system is needed that analyzes responses in real time and provides specific feedback. However, existing systems do not adequately perform real-time analysis or offer concrete improvement suggestions, limiting the improvement of users' skills. Therefore, there is a need for effective technology to solve this problem and cultivate more advanced customer service capabilities.

[0054] 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.

[0055] In this invention, the server includes means for creating virtual entity information using a generative model, means for simulating a dialogue based on the virtual entity information, and means for providing an evaluation result to the operator based on the dialogue analysis results. This allows the operator to have their responses analyzed in real time and receive specific, quantifiable feedback, thereby effectively improving their customer service skills.

[0056] A "generative model" is an algorithm or program for automatically creating information about virtual entities.

[0057] "Virtual entity information" refers to data sets about people and objects that do not actually exist but are generated by computers for the purpose of simulation and analysis.

[0058] A "means of simulating dialogue" is a mechanism that provides an environment in which an operator can communicate with a virtual entity by imitating actual interactions.

[0059] A "means of real-time analysis" refers to a technology that has the ability to rapidly analyze the content of an operator's response as soon as it is received and to immediately generate evaluation results.

[0060] "Means of providing evaluation results" refers to a system that, based on analyzed data, provides an evaluation of the operator's actions and decisions, and offers advice and guidance for improvement.

[0061] This invention is primarily implemented by a server, a terminal, and a user. First, the server is responsible for generating virtual entity information. The server has a generative model, which it uses to generate virtual entity information. The generative model employs machine learning algorithms and automatically generates information based on specific conditions by inputting various prompt statements. In terms of hardware, a data processing server with a high-performance processor and sufficient memory is required, and the software typically uses platforms such as Python or Tensorflow®.

[0062] The generated virtual entity information is sent from the server to the terminal. The terminal provides an interface for the user to interact with the virtual entity. The terminal uses the received information to launch dedicated simulation software. During interaction, the terminal provides the user with feedback from the virtual entity. This feedback is generated by the server based on the analysis of the response and is intended to help improve the operator's skills.

[0063] Users can participate in interactions using their devices and engage in dialogue with virtual entities. For example, a user might explain the setup procedure in simple terms to an elderly virtual customer who complains that they "don't know how to set up their new smartphone." This information is recorded by the device and sent to the server.

[0064] The server is equipped with natural language processing technology to analyze recorded user responses. This allows the server to quantify the responses and evaluate how effectively the operator supported the virtual entities. The evaluation results are returned to the terminal as numerical data and specific feedback.

[0065] As a concrete example, by entering the prompt statement "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone," entity information based on this condition can be generated. The information generated using this prompt statement enables a more realistic simulation.

[0066] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0067] Step 1:

[0068] The server creates virtual entity information using a generative model.

[0069] The server receives input such as "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone" as a prompt message.

[0070] The generative AI model uses this prompt to generate a detailed profile of a virtual entity. For example, it outputs data for a person that includes information such as age, gender, and specific problems they are facing.

[0071] Step 2:

[0072] The server sends the virtual entity information it generates to the terminal.

[0073] The input is the virtual entity information generated in Step 1.

[0074] The server uses a secure communication protocol to send this information to the terminal. As a result, the entity information reaches and is received by the terminal.

[0075] Step 3:

[0076] The terminal starts an interaction simulation based on virtual entity information.

[0077] The terminal uses entity information received from the server as input.

[0078] The simulation software starts up and is ready to provide the user with the opportunity to interact with virtual entities. The output is an environment where the user can interact with virtual entities on the screen.

[0079] Step 4:

[0080] Users interact with virtual entities through their devices.

[0081] Users use the terminal interface to ask questions to virtual entities and offer suggestions for problems they encounter.

[0082] The input consists of problems or questions presented by a virtual entity, to which the user provides responses. The output is a record of the user's responses, which are later analyzed.

[0083] Step 5:

[0084] The server analyzes user responses in real time.

[0085] The server receives user response data from the terminal as input.

[0086] The system uses natural language processing tools to analyze the content of responses and scores how effective the dialogue was. The output generates points and specific comments as a result of the evaluation.

[0087] Step 6:

[0088] The server generates feedback based on the analysis results and sends it to the terminal.

[0089] The input is the evaluation result obtained in step 5.

[0090] The server generates specific feedback based on the analysis and sends it to the terminal. The user can receive this feedback and use it to improve their next interaction. The output is the feedback information that the user can view.

[0091] (Application Example 1)

[0092] 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."

[0093] Traditional customer service training systems typically rely on hypothetical scenarios, lacking efficient means of providing real-time evaluation and feedback. This makes it difficult for users to immediately understand where they need to improve their responses. Furthermore, the systems struggle to provide realistic customer service experiences, hindering practical skill development.

[0094] 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.

[0095] In this invention, the server includes means for creating fictitious customer information using a generation module, means for simulating interactions based on the fictitious customer information, and means for providing real-time feedback using a display device to improve the user's customer service capabilities. This allows the user to receive real-time evaluations of their responses and make quick and concrete improvements.

[0096] A "generation module" is a device or software used to create fictitious customer information and has the function of providing data to simulate interactions based on that information.

[0097] "Fictional customer information" refers to a dataset that models a hypothetical customer and includes information such as their profile, specific needs, and problems.

[0098] "Interaction" is the process of simulating the dialogue and response behavior that takes place between a user and a virtual customer.

[0099] "Analysis results" refer to the output of evaluation and analysis obtained based on data collected to assess user responses and behavior.

[0100] "Feedback" refers to information provided to users that specifically indicates the appropriateness of their responses and areas for improvement.

[0101] A "display device" is an electronic device used to provide information to a user visually, and includes, for example, smart glasses and head-mounted displays.

[0102] "Real-time" refers to the timing of processing and evaluation that allows for immediate response to user actions and reactions.

[0103] "Customer service ability" refers to the skills and knowledge required to accurately and quickly understand and respond to customer needs, thereby increasing customer satisfaction.

[0104] The system based on this invention provides training to improve customer service capabilities using a user-accessible display device. Multiple processes take place between the server, terminal, and user.

[0105] The server utilizes a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems, allowing users to simulate realistic customer interactions. This generated customer information is sent to the terminal for the user to visually review.

[0106] The terminal uses a display device such as smart glasses or a head-mounted display to initiate an interaction simulation for the user. In this simulation, the user can interact with a fictional customer based on generated customer information, asking appropriate questions and making suggestions.

[0107] All user responses are recorded, and the server analyzes these responses in real time using natural language processing technology (e.g., NLTK). The analysis results are displayed as feedback on a display device, specifically indicating the appropriateness and areas for improvement of the user's responses. This allows the user to immediately improve their responses.

[0108] As a concrete example, a user wearing smart glasses can practice responding to a hypothetical customer asking for directions to a new television. Based on the prompt, "Let's practice guiding a customer looking for the television section. The customer is elderly and wants to know more about the features of the latest model," the user provides a product description using polite language. If the response is accurate and prompt, feedback such as "Your explanation is accurate" will be displayed. This allows for the realistic simulation of effective customer service, which is expected to improve the user's skills.

[0109] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0110] Step 1:

[0111] The server uses a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems. As input, the server provides data parameters for creating the customer information based on prompt messages. As output, the generated customer information is sent to the terminal.

[0112] Step 2:

[0113] The terminal presents an interaction simulation to the user via a display device, based on the received fictitious customer information. The input is customer information data from the server, which is processed into a format that can be visually presented on the display. The output is a display of customer information visible to the user.

[0114] Step 3:

[0115] The user initiates the simulation through a terminal and interacts with a fictional customer. User input is provided via voice or other input devices, and the content is recorded on the terminal. As output, the recorded data is sent to a server for later analysis.

[0116] Step 4:

[0117] The server processes input data using natural language processing techniques to analyze user responses. The input consists of recorded user responses, which are processed using semantic analysis and evaluation algorithms. As a result of the analysis, the server ranks the appropriateness and areas for improvement of the user's responses.

[0118] Step 5:

[0119] The server generates feedback and provides it to the user in real time via the terminal. The feedback is generated based on the analysis results; the input is the analysis result data, and the output is displayed on the terminal as a specific feedback message. The user can use this feedback to improve future interactions.

[0120] 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.

[0121] This invention is a training system consisting of three elements: a server, a terminal, and a user, which works by combining an emotion engine. The server generates fictional customer information via a generation module and starts a simulation based on that information.

[0122] The terminal presents the user with fictitious customer information received from the server, and the user interacts with it. The emotion engine recognizes the user's emotions during the interaction and analyzes the changing emotions in real time. This emotion analysis allows the system to capture what emotions the user is experiencing as they engage in the conversation.

[0123] The analysis results are sent to a server, which generates feedback that takes emotional information into account. This feedback includes not only an evaluation of the previous response, but also suggestions for improving the response based on changes in emotions. Users receive this feedback through their device and can learn how to incorporate emotions into their next interaction.

[0124] As a concrete example, consider a scenario where a user interacts with a persona of a "young person seeking the latest devices." During a conversation with this highly inquisitive young person, if the user exhibits excited emotions, the server recognizes these emotions and provides feedback on how to suggest appropriate products in that excited state. In this way, the emotion engine plays a role in comprehensively improving the user's interaction skills.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server uses a generation module to create fictional customer information. This customer information includes detailed profiles such as age, hobbies, and needs.

[0128] Step 2:

[0129] The server sends the created fictitious customer information to the terminal. The terminal receives this information and displays it on the screen in a format viewable by the user.

[0130] Step 3:

[0131] The user starts the simulation on their device. Based on customer information, the user interacts with a fictional customer, asking appropriate questions and suggesting products and services.

[0132] Step 4:

[0133] The emotion engine detects and analyzes the user's emotions in real time based on their facial expressions, tone of voice, and content during interactions. The emotion data is then sent to a server for analysis.

[0134] Step 5:

[0135] The server analyzes the user's responses in combination with sentiment data to determine the appropriateness of the user's responses and the influence of emotions.

[0136] Step 6:

[0137] Based on the analysis results, the server sends emotion-sensitive feedback to the terminal. This feedback includes how the user's actions influenced their emotions and suggests specific ways to improve.

[0138] Step 7:

[0139] Users receive feedback through their devices and learn skills for the next simulation. By utilizing this feedback, users can engage in more effective, emotion-conscious dialogue.

[0140] (Example 2)

[0141] 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".

[0142] Conventional dialogue systems have the challenge of not adequately considering user emotions in their feedback during interactions, making it difficult to effectively improve users' dialogue skills. Furthermore, there is a lack of systems capable of analyzing customer emotions in real time during simulations and responding accordingly to those emotional changes.

[0143] 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.

[0144] In this invention, the server includes means for generating fictitious customer data using a generation device, means for simulating a conversation based on the fictitious customer data, and means equipped with an emotion analysis device for analyzing the user's emotions in real time. This makes it possible to provide feedback in response to changes in the user's emotions, thereby effectively improving the user's conversation skills.

[0145] A "generation device" is a device used to generate fictional customer data, and it is responsible for producing various types of data using generation modules and algorithms.

[0146] "Fictional customer data" refers to information about non-existent customers, including their profile such as age, occupation, and interests.

[0147] "Methods for simulating dialogue" refer to methods and systems that conduct virtual interactions with users based on fictional customer data.

[0148] An "emotion analysis device" is a device that analyzes a user's emotions in real time and has the function of evaluating their emotional state using voice and facial expression data.

[0149] "Feedback" refers to information provided to users, including evaluations and suggestions for improvement, based on the results of interactions and sentiment analysis.

[0150] This system consists of three elements: server, terminal, and user, and provides a training environment that effectively utilizes sentiment analysis.

[0151] The server uses a generation device to generate fictional customer data. Here, a natural language processing model, for example, is used as the generation AI model to create diverse customer profiles including age, occupation, and interests. This generation allows users to be trained through various scenarios.

[0152] The terminal presents the user with fictitious customer data sent from the server. The user interacts with the terminal based on the presented customer data. During this interaction, input from the terminal is received via a microphone, keyboard, etc., and the user's speech and text are processed by a dialogue module.

[0153] During user interaction, the emotion analysis device analyzes the user's emotions in real time. Emotion analysis utilizes technologies such as speech recognition and facial recognition, with services like IBM Watson® Tone Analyzer being used as examples. This allows the user's emotional state to be constantly monitored, and analysis to be performed as needed.

[0154] The server generates feedback based on the results of the user's sentiment analysis. This feedback includes suggestions and areas for improvement based on changes in emotion, designed to help the user apply them to their next interaction. The generated feedback is provided to the user via the device to support their learning.

[0155] A concrete example would be a dialogue scenario with a "young person seeking the latest devices." In this scenario, when the user makes a product suggestion to a fictional young customer, if the customer's emotion is detected as "excitement," the server provides feedback such as "emphasize visual demonstrations when explaining to excited customers."

[0156] An example of a prompt is: "When talking to a hypothetical young customer about the benefits of a new smartphone, how can you engage their interest?"

[0157] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0158] Step 1:

[0159] The server generates fictional customer data using a generative AI model. A prompt is given as input, and the AI ​​model processes the data based on that prompt. The output is a fictional customer profile that includes the customer's age, occupation, interests, etc. Specifically, the server starts the generation module and sends the prompt "Create a customer profile for a young person interested in new smartphones" to the AI ​​model.

[0160] Step 2:

[0161] The terminal receives fictitious customer data sent from the server and presents it to the user. The input is customer profile data from the server, which the terminal displays on the screen. The output is a display of customer information in a format that the user can review. Specifically, the terminal displays the received data in a list and prompts the user to prepare for the interaction.

[0162] Step 3:

[0163] The user interacts with the system based on customer data presented via the device. Input is customer information displayed on the device, and output is the conversation entered by the user. User speech and text input are also recorded as data. For example, the user might input a message into the device such as, "The features of this smartphone are..."

[0164] Step 4:

[0165] The emotion analysis device analyzes the user's emotions in real time from their speech and facial expressions. The input is the user's voice data and facial expression data, and the device evaluates changes in emotion through analysis. The output is a detailed analysis result of the emotional state. Specifically, the emotion analysis device uses the user's voice tone and facial expressions to identify emotions such as "excitement" and "satisfaction."

[0166] Step 5:

[0167] The analyzed emotion data is sent to the server to generate feedback. The input is the result of the emotion analysis and the interaction history, and the server creates feedback based on this data. The output is feedback that includes specific countermeasures and improvements based on the change in emotion. For example, if the server determines that the emotion is "excited," it will generate feedback such as "A product demonstration is effective for excited customers."

[0168] Step 6:

[0169] The user receives feedback from the server via the device and uses it to improve future interactions. The input is feedback information from the server, which the device presents to the user. The output is the user's confirmation and understanding of the feedback. Specifically, the device displays the generated feedback as text, and the user learns from it to improve future interactions.

[0170] (Application Example 2)

[0171] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0172] In modern brick-and-mortar stores, customer service requires quick and accurate interaction. However, understanding customers' emotions and attitudes in real time and responding appropriately is difficult for less experienced service staff. As a result, problems arise such as inconsistent service quality and decreased customer satisfaction. There is a need to develop a system that solves these problems and allows any staff member to consistently provide high-quality customer service.

[0173] 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.

[0174] In this invention, the server includes means for creating fictitious user information using a generation module, means for simulating interactions based on the fictitious user information, means for providing insights to the operator based on the analysis results of the interactions, means for analyzing the operator's emotional state in real time using an emotion analysis engine, and means for generating appropriate action suggestions for the operator based on the emotion analysis results. This enables customer service staff to provide appropriate responses in real time that are in line with the customer's emotions.

[0175] A "generation module" is a component that has the function of creating fictitious user information.

[0176] "User information" refers to various data related to fictional or actual operators, and is the basic information used in simulations.

[0177] "Simulating interaction" means reproducing the actual interaction between the operator and the user in a virtual environment.

[0178] An "emotion analysis engine" is a software or hardware system for recognizing and analyzing the emotional state of an operator in real time.

[0179] "Discussion" refers to information provided to the operator, including evaluations and advice based on the results of the interaction.

[0180] "Action suggestions" are pieces of information that indicate the appropriate next action the operator should take, based on emotion analysis and interaction results.

[0181] In implementing this invention, the server operates as follows: First, it creates fictitious user information using a generation module. This prepares a scenario for staff to train in customer service. The terminal simulates interaction based on this user information and presents the interaction to the operator.

[0182] During the user's interaction via the device, an emotion analysis engine analyzes the user's emotional state in real time. For example, sensors in smart glasses capture the user's facial expressions and tone of voice, and the emotional state is determined based on this data. Based on these results, the server generates action suggestions and provides feedback to the user through the device. This feedback is based on the user's responses and emotional state and includes advice that can lead to improved behavior.

[0183] For example, if smart glasses detect a customer's excitement level while they are receiving a new product explanation in a physical store, the server analyzes this information and provides feedback to the operator suggesting actions such as "providing detailed product information and feature descriptions." This allows the operator to respond smoothly in a way that aligns with the customer's emotions.

[0184] An example of a prompt would be, "Create a program that performs sentiment analysis and generates appropriate suggestion feedback in real time for customer service training using smart glasses for a new product." This prompt facilitates the generation of specific training scenarios.

[0185] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0186] Step 1:

[0187] The server generates fictional user information through a generation module. User profile information (e.g., age, interests, desired information) is provided as input. Based on this input, a generation AI model is used to generate fictional user information for various scenarios in a database. The output is the fictional user information used by the operator for training.

[0188] Step 2:

[0189] The terminal receives fictitious user information sent from the server and presents it to the user. The input is fictitious user information from the server. Based on this information, the terminal simulates an interaction and presents it to the operator through the display and audio output. The output is expressed as a simulated interaction experienced by the operator.

[0190] Step 3:

[0191] The user interacts with the presented hypothetical user information. The input here is the simulated information and scenarios the user receives. The user's responses are input into the sentiment analysis engine in real time, and the user's emotional state data is generated as output.

[0192] Step 4:

[0193] The server uses an emotion analysis engine to analyze emotional state data received from the user. The input consists of the user's responses and emotional state data. This allows the server to capture changes in the user's emotions and perform data calculations to determine appropriate action suggestions. The output is the emotion-based analysis result.

[0194] Step 5:

[0195] The server generates feedback for the user based on the analysis results. The input is the analysis results based on emotions. Based on the analysis results, prompt messages are created that indicate areas for improvement and specific action suggestions to the user. This output is presented to the user as feedback information through the terminal.

[0196] Step 6:

[0197] The user receives feedback sent from the server via their device and uses it to improve their next interaction. The input is the feedback information from the server. Based on this feedback, the user learns specific areas for improvement to enhance their customer service skills. The output is the user's improved customer service skills.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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".

[0214] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. This system is built via a server that has a built-in generation module. The server first generates fictional customer information. This information includes a detailed profile, such as age, gender, hobbies, specific needs, and problems.

[0215] The server then sends the generated customer information to the terminal. The terminal is a device operated by the user, and it starts an interaction simulation based on the received information. During this simulation, the user can interact with a fictional customer through the terminal, asking appropriate questions and making suggestions. All of the user's responses are recorded.

[0216] The server then analyzes the user's responses in real time. This analysis includes natural language processing techniques to evaluate how appropriate the user's responses are. Based on this evaluation, the server sends feedback to the terminal. This feedback specifically highlights the user's successes and areas for improvement.

[0217] As a concrete example, consider a simulation where a server generates a persona of an "elderly person who doesn't know how to operate something," and a user responds by explaining the operating procedure in simple language. The server evaluates whether the user's explanation was easy to understand and sends feedback to the terminal. This feedback becomes valuable information for the user to improve in subsequent simulations. Through this process, the user can efficiently improve their customer service skills.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The server uses a generation module to generate fictional customer information. This customer information includes age, gender, hobbies, and specific needs or challenges, creating a detailed profile based on a scenario.

[0221] Step 2:

[0222] The server sends the generated customer information to the terminal. The terminal receives this information and presents it to the user through an interface.

[0223] Step 3:

[0224] The user operates the terminal and starts a simulation based on the fictional customer information presented. The user asks questions and makes suggestions for products and services.

[0225] Step 4:

[0226] The terminal records user responses and suggestions and sends them to the server in real time. The server receives this data.

[0227] Step 5:

[0228] The server analyzes the user's response data it receives. Using natural language processing techniques, it evaluates the user's response and determines its appropriateness and specificity.

[0229] Step 6:

[0230] The server generates feedback based on the analysis results. This feedback includes the user's strengths, areas for improvement, and specific advice.

[0231] Step 7:

[0232] The server sends the generated feedback to the terminal and presents it to the user. Through this feedback, the user gains clues to improve their skills for the next simulation.

[0233] (Example 1)

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

[0235] To effectively improve customer service skills, an interaction simulation system is needed that analyzes responses in real time and provides specific feedback. However, existing systems do not adequately perform real-time analysis or offer concrete improvement suggestions, limiting the improvement of users' skills. Therefore, there is a need for effective technology to solve this problem and cultivate more advanced customer service capabilities.

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

[0237] In this invention, the server includes means for creating virtual entity information using a generative model, means for simulating a dialogue based on the virtual entity information, and means for providing an evaluation result to the operator based on the dialogue analysis results. This allows the operator to have their responses analyzed in real time and receive specific, quantifiable feedback, thereby effectively improving their customer service skills.

[0238] A "generative model" is an algorithm or program for automatically creating information about virtual entities.

[0239] "Virtual entity information" refers to data sets about people and objects that do not actually exist but are generated by computers for the purpose of simulation and analysis.

[0240] A "means of simulating dialogue" is a mechanism that provides an environment in which an operator can communicate with a virtual entity by imitating actual interactions.

[0241] A "means of real-time analysis" refers to a technology that has the ability to rapidly analyze the content of an operator's response as soon as it is received and to immediately generate evaluation results.

[0242] "Means of providing evaluation results" refers to a system that, based on analyzed data, provides an evaluation of the operator's actions and decisions, and offers advice and guidance for improvement.

[0243] This invention is primarily implemented by a server, a terminal, and a user. First, the server is responsible for generating virtual entity information. The server has a generative model, which it uses to generate virtual entity information. The generative model employs machine learning algorithms and automatically generates information based on specific conditions by inputting various prompt statements. In terms of hardware, a data processing server with a high-performance processor and sufficient memory is required, and the software typically uses platforms such as Python or TensorFlow.

[0244] The generated virtual entity information is sent from the server to the terminal. The terminal provides an interface for the user to interact with the virtual entity. The terminal uses the received information to launch dedicated simulation software. During interaction, the terminal provides the user with feedback from the virtual entity. This feedback is generated by the server based on the analysis of the response and is intended to help improve the operator's skills.

[0245] Users can participate in interactions using their devices and engage in dialogue with virtual entities. For example, a user might explain the setup procedure in simple terms to an elderly virtual customer who complains that they "don't know how to set up their new smartphone." This information is recorded by the device and sent to the server.

[0246] The server is equipped with natural language processing technology to analyze recorded user responses. This allows the server to quantify the responses and evaluate how effectively the operator supported the virtual entities. The evaluation results are returned to the terminal as numerical data and specific feedback.

[0247] As a concrete example, by entering the prompt statement "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone," entity information based on this condition can be generated. The information generated using this prompt statement enables a more realistic simulation.

[0248] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0249] Step 1:

[0250] The server creates virtual entity information using a generative model.

[0251] The server receives input such as "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone" as a prompt message.

[0252] The generative AI model uses this prompt to generate a detailed profile of a virtual entity. For example, it outputs data for a person that includes information such as age, gender, and specific problems they are facing.

[0253] Step 2:

[0254] The server sends the virtual entity information it generates to the terminal.

[0255] The input is the virtual entity information generated in Step 1.

[0256] The server uses a secure communication protocol to send this information to the terminal. As a result, the entity information reaches and is received by the terminal.

[0257] Step 3:

[0258] The terminal starts an interaction simulation based on virtual entity information.

[0259] The terminal uses entity information received from the server as input.

[0260] The simulation software starts up and is ready to provide the user with the opportunity to interact with virtual entities. The output is an environment where the user can interact with virtual entities on the screen.

[0261] Step 4:

[0262] Users interact with virtual entities through their devices.

[0263] Users use the terminal interface to ask questions to virtual entities and offer suggestions for problems they encounter.

[0264] The input consists of problems or questions presented by a virtual entity, to which the user provides responses. The output is a record of the user's responses, which are later analyzed.

[0265] Step 5:

[0266] The server analyzes user responses in real time.

[0267] The server receives user response data from the terminal as input.

[0268] The system uses natural language processing tools to analyze the content of responses and scores how effective the dialogue was. The output generates points and specific comments as a result of the evaluation.

[0269] Step 6:

[0270] The server generates feedback based on the analysis results and sends it to the terminal.

[0271] The input is the evaluation result obtained in step 5.

[0272] The server generates specific feedback based on the analysis and sends it to the terminal. The user can receive this feedback and use it to improve their next interaction. The output is the feedback information that the user can view.

[0273] (Application Example 1)

[0274] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] Traditional customer service training systems typically rely on hypothetical scenarios, lacking efficient means of providing real-time evaluation and feedback. This makes it difficult for users to immediately understand where they need to improve their responses. Furthermore, the systems struggle to provide realistic customer service experiences, hindering practical skill development.

[0276] 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.

[0277] In this invention, the server includes means for creating fictitious customer information using a generation module, means for simulating interactions based on the fictitious customer information, and means for providing real-time feedback using a display device to improve the user's customer service capabilities. This allows the user to receive real-time evaluations of their responses and make quick and concrete improvements.

[0278] A "generation module" is a device or software used to create fictitious customer information and has the function of providing data to simulate interactions based on that information.

[0279] "Hypothetical customer information" refers to a dataset that models assumed customers and includes information such as profiles, specific needs, and problems.

[0280] "Interaction" is a process that simulates the dialogue and response actions that occur between a user and a virtual customer.

[0281] "Analysis results" refer to the outputs of evaluation and analysis obtained based on data collected to evaluate the user's responses and actions.

[0282] "Feedback" is information provided to the user that specifically indicates the appropriateness and areas for improvement of the user's response.

[0283] "Display device" is an electronic device for visually providing information to the user, including, for example, smart glasses and head-mounted displays.

[0284] "Real-time" refers to the timing of processing and evaluation that can immediately respond to the user's operations and responses.

[0285] "Customer response ability" refers to the skills and knowledge for accurately and quickly understanding and responding to customer needs and enhancing satisfaction.

[0286] The system according to this invention provides training for improving customer response ability using a display device that the user can contact. Multiple processes are performed among the server, the terminal, and the user.

[0287] The server utilizes a generative AI model to generate hypothetical customer information. This information includes the customer's age, gender, hobbies, specific needs, and problems, and is content that allows the user to simulate real customer responses. This generated customer information is transmitted to the terminal and can be visually confirmed by the user.

[0288] The terminal uses a display device such as smart glasses or a head-mounted display to initiate an interaction simulation for the user. In this simulation, the user can interact with a fictional customer based on generated customer information, asking appropriate questions and making suggestions.

[0289] All user responses are recorded, and the server analyzes these responses in real time using natural language processing technology (e.g., NLTK). The analysis results are displayed as feedback on a display device, specifically indicating the appropriateness and areas for improvement of the user's responses. This allows the user to immediately improve their responses.

[0290] As a concrete example, a user wearing smart glasses can practice responding to a hypothetical customer asking for directions to a new television. Based on the prompt, "Let's practice guiding a customer looking for the television section. The customer is elderly and wants to know more about the features of the latest model," the user provides a product description using polite language. If the response is accurate and prompt, feedback such as "Your explanation is accurate" will be displayed. This allows for the realistic simulation of effective customer service, which is expected to improve the user's skills.

[0291] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0292] Step 1:

[0293] The server uses a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems. As input, the server provides data parameters for creating the customer information based on prompt messages. As output, the generated customer information is sent to the terminal.

[0294] Step 2:

[0295] The terminal presents an interaction simulation to the user via a display device, based on the received fictitious customer information. The input is customer information data from the server, which is processed into a format that can be visually presented on the display. The output is a display of customer information visible to the user.

[0296] Step 3:

[0297] The user initiates the simulation through a terminal and interacts with a fictional customer. User input is provided via voice or other input devices, and the content is recorded on the terminal. As output, the recorded data is sent to a server for later analysis.

[0298] Step 4:

[0299] The server processes input data using natural language processing techniques to analyze user responses. The input consists of recorded user responses, which are processed using semantic analysis and evaluation algorithms. As a result of the analysis, the server ranks the appropriateness and areas for improvement of the user's responses.

[0300] Step 5:

[0301] The server generates feedback and provides it to the user in real time via the terminal. The feedback is generated based on the analysis results; the input is the analysis result data, and the output is displayed on the terminal as a specific feedback message. The user can use this feedback to improve future interactions.

[0302] 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.

[0303] The present invention is a training system composed of three elements: a server, a terminal, and a user, which combines an emotion engine to exert its effects. The server generates virtual customer information via a generation module and starts a simulation based on that information.

[0304] The terminal presents the virtual customer information received from the server to the user, and the user interacts with it. The emotion engine recognizes the user's emotions during the interaction and analyzes in real time the emotions that change accordingly. Through this emotion analysis, it is possible to grasp what emotions the user has while proceeding with the conversation.

[0305] The analysis result is sent to the server, and the server generates feedback considering the emotion information. The feedback includes not only an evaluation of the conventional response content but also points for improvement of the response based on the change in emotions. The user receives this feedback through the terminal and can learn how to utilize emotions in the next interaction to proceed with the conversation.

[0306] As a specific example, consider a scenario where the user corresponds to the persona of "a young person seeking the latest device". During the conversation with a young person with a high curiosity, if the user shows an excited emotion, the server recognizes that emotion and provides feedback on an appropriate way to propose products in an excited state. In this way, the emotion engine plays a role in comprehensively improving the user's response skills.

[0307] The following describes the processing flow.

[0308] Step 1:

[0309] The server uses the generation module to create virtual customer information. The customer information includes detailed profiles such as age, hobbies, needs, etc.

[0310] Step 2:

[0311] The server sends the created fictitious customer information to the terminal. The terminal receives this information and displays it on the screen in a format viewable by the user.

[0312] Step 3:

[0313] The user starts the simulation on their device. Based on customer information, the user interacts with a fictional customer, asking appropriate questions and suggesting products and services.

[0314] Step 4:

[0315] The emotion engine detects and analyzes the user's emotions in real time based on their facial expressions, tone of voice, and content during interactions. The emotion data is then sent to a server for analysis.

[0316] Step 5:

[0317] The server analyzes the user's responses in combination with sentiment data to determine the appropriateness of the user's responses and the influence of emotions.

[0318] Step 6:

[0319] Based on the analysis results, the server sends emotion-sensitive feedback to the terminal. This feedback includes how the user's actions influenced their emotions and suggests specific ways to improve.

[0320] Step 7:

[0321] Users receive feedback through their devices and learn skills for the next simulation. By utilizing this feedback, users can engage in more effective, emotion-conscious dialogue.

[0322] (Example 2)

[0323] 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".

[0324] Conventional dialogue systems have the challenge of not adequately considering user emotions in their feedback during interactions, making it difficult to effectively improve users' dialogue skills. Furthermore, there is a lack of systems capable of analyzing customer emotions in real time during simulations and responding accordingly to those emotional changes.

[0325] 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.

[0326] In this invention, the server includes means for generating fictitious customer data using a generation device, means for simulating a conversation based on the fictitious customer data, and means equipped with an emotion analysis device for analyzing the user's emotions in real time. This makes it possible to provide feedback in response to changes in the user's emotions, thereby effectively improving the user's conversation skills.

[0327] A "generation device" is a device used to generate fictional customer data, and it is responsible for producing various types of data using generation modules and algorithms.

[0328] "Fictional customer data" refers to information about non-existent customers, including their profile such as age, occupation, and interests.

[0329] "Methods for simulating dialogue" refer to methods and systems that conduct virtual interactions with users based on fictional customer data.

[0330] An "emotion analysis device" is a device that analyzes a user's emotions in real time and has the function of evaluating their emotional state using voice and facial expression data.

[0331] "Feedback" refers to information provided to users, including evaluations and suggestions for improvement, based on the results of interactions and sentiment analysis.

[0332] This system consists of three elements: server, terminal, and user, and provides a training environment that effectively utilizes sentiment analysis.

[0333] The server uses a generation device to generate fictional customer data. Here, a natural language processing model, for example, is used as the generation AI model to create diverse customer profiles including age, occupation, and interests. This generation allows users to be trained through various scenarios.

[0334] The terminal presents the user with fictitious customer data sent from the server. The user interacts with the terminal based on the presented customer data. During this interaction, input from the terminal is received via a microphone, keyboard, etc., and the user's speech and text are processed by a dialogue module.

[0335] During user interaction, an emotion analysis device analyzes the user's emotions in real time. Emotion analysis utilizes technologies such as speech recognition and facial recognition, with services like IBM Watson Tone Analyzer being used as examples. This allows the user's emotional state to be constantly monitored, and analysis to be performed as needed.

[0336] The server generates feedback based on the results of the user's sentiment analysis. This feedback includes suggestions and areas for improvement based on changes in emotion, designed to help the user apply them to their next interaction. The generated feedback is provided to the user via the device to support their learning.

[0337] A concrete example would be a dialogue scenario with a "young person seeking the latest devices." In this scenario, when the user makes a product suggestion to a fictional young customer, if the customer's emotion is detected as "excitement," the server provides feedback such as "emphasize visual demonstrations when explaining to excited customers."

[0338] An example of a prompt is: "When talking to a hypothetical young customer about the benefits of a new smartphone, how can you engage their interest?"

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The server generates fictional customer data using a generative AI model. A prompt is given as input, and the AI ​​model processes the data based on that prompt. The output is a fictional customer profile that includes the customer's age, occupation, interests, etc. Specifically, the server starts the generation module and sends the prompt "Create a customer profile for a young person interested in new smartphones" to the AI ​​model.

[0342] Step 2:

[0343] The terminal receives fictitious customer data sent from the server and presents it to the user. The input is customer profile data from the server, which the terminal displays on the screen. The output is a display of customer information in a format that the user can review. Specifically, the terminal displays the received data in a list and prompts the user to prepare for the interaction.

[0344] Step 3:

[0345] The user interacts with the system based on customer data presented via the device. Input is customer information displayed on the device, and output is the conversation entered by the user. User speech and text input are also recorded as data. For example, the user might input a message into the device such as, "The features of this smartphone are..."

[0346] Step 4:

[0347] The emotion analysis device analyzes the user's emotions in real time from their speech and facial expressions. The input is the user's voice data and facial expression data, and the device evaluates changes in emotion through analysis. The output is a detailed analysis result of the emotional state. Specifically, the emotion analysis device uses the user's voice tone and facial expressions to identify emotions such as "excitement" and "satisfaction."

[0348] Step 5:

[0349] The analyzed emotion data is sent to the server to generate feedback. The input is the result of the emotion analysis and the interaction history, and the server creates feedback based on this data. The output is feedback that includes specific countermeasures and improvements based on the change in emotion. For example, if the server determines that the emotion is "excited," it will generate feedback such as "A product demonstration is effective for excited customers."

[0350] Step 6:

[0351] The user receives feedback from the server via the device and uses it to improve future interactions. The input is feedback information from the server, which the device presents to the user. The output is the user's confirmation and understanding of the feedback. Specifically, the device displays the generated feedback as text, and the user learns from it to improve future interactions.

[0352] (Application Example 2)

[0353] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0354] In modern brick-and-mortar stores, customer service requires quick and accurate interaction. However, understanding customers' emotions and attitudes in real time and responding appropriately is difficult for less experienced service staff. As a result, problems arise such as inconsistent service quality and decreased customer satisfaction. There is a need to develop a system that solves these problems and allows any staff member to consistently provide high-quality customer service.

[0355] 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.

[0356] In this invention, the server includes means for creating fictitious user information using a generation module, means for simulating interactions based on the fictitious user information, means for providing insights to the operator based on the analysis results of the interactions, means for analyzing the operator's emotional state in real time using an emotion analysis engine, and means for generating appropriate action suggestions for the operator based on the emotion analysis results. This enables customer service staff to provide appropriate responses in real time that are in line with the customer's emotions.

[0357] A "generation module" is a component that has the function of creating fictitious user information.

[0358] "User information" refers to various data related to fictional or actual operators, and is the basic information used in simulations.

[0359] "Simulating interaction" means reproducing the actual interaction between the operator and the user in a virtual environment.

[0360] An "emotion analysis engine" is a software or hardware system for recognizing and analyzing the emotional state of an operator in real time.

[0361] "Discussion" refers to information provided to the operator, including evaluations and advice based on the results of the interaction.

[0362] "Action suggestions" are pieces of information that indicate the appropriate next action the operator should take, based on emotion analysis and interaction results.

[0363] In implementing this invention, the server operates as follows: First, it creates fictitious user information using a generation module. This prepares a scenario for staff to train in customer service. The terminal simulates interaction based on this user information and presents the interaction to the operator.

[0364] During the user's interaction via the device, an emotion analysis engine analyzes the user's emotional state in real time. For example, sensors in smart glasses capture the user's facial expressions and tone of voice, and the emotional state is determined based on this data. Based on these results, the server generates action suggestions and provides feedback to the user through the device. This feedback is based on the user's responses and emotional state and includes advice that can lead to improved behavior.

[0365] For example, if smart glasses detect a customer's excitement level while they are receiving a new product explanation in a physical store, the server analyzes this information and provides feedback to the operator suggesting actions such as "providing detailed product information and feature descriptions." This allows the operator to respond smoothly in a way that aligns with the customer's emotions.

[0366] An example of a prompt would be, "Create a program that performs sentiment analysis and generates appropriate suggestion feedback in real time for customer service training using smart glasses for a new product." This prompt facilitates the generation of specific training scenarios.

[0367] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0368] Step 1:

[0369] The server generates fictional user information through a generation module. User profile information (e.g., age, interests, desired information) is provided as input. Based on this input, a generation AI model is used to generate fictional user information for various scenarios in a database. The output is the fictional user information used by the operator for training.

[0370] Step 2:

[0371] The terminal receives fictitious user information sent from the server and presents it to the user. The input is fictitious user information from the server. Based on this information, the terminal simulates an interaction and presents it to the operator through the display and audio output. The output is expressed as a simulated interaction experienced by the operator.

[0372] Step 3:

[0373] The user interacts with the presented hypothetical user information. The input here is the simulated information and scenarios the user receives. The user's responses are input into the sentiment analysis engine in real time, and the user's emotional state data is generated as output.

[0374] Step 4:

[0375] The server uses an emotion analysis engine to analyze emotional state data received from the user. The input consists of the user's responses and emotional state data. This allows the server to capture changes in the user's emotions and perform data calculations to determine appropriate action suggestions. The output is the emotion-based analysis result.

[0376] Step 5:

[0377] The server generates feedback for the user based on the analysis results. The input is the analysis results based on emotions. Based on the analysis results, prompt messages are created that indicate areas for improvement and specific action suggestions to the user. This output is presented to the user as feedback information through the terminal.

[0378] Step 6:

[0379] The user receives feedback sent from the server via their device and uses it to improve their next interaction. The input is the feedback information from the server. Based on this feedback, the user learns specific areas for improvement to enhance their customer service skills. The output is the user's improved customer service skills.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] [Third Embodiment]

[0384] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0385] 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.

[0386] 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).

[0387] 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.

[0388] 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.

[0389] 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).

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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".

[0396] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. This system is built via a server that has a built-in generation module. The server first generates fictional customer information. This information includes a detailed profile, such as age, gender, hobbies, specific needs, and problems.

[0397] The server then sends the generated customer information to the terminal. The terminal is a device operated by the user, and it starts an interaction simulation based on the received information. During this simulation, the user can interact with a fictional customer through the terminal, asking appropriate questions and making suggestions. All of the user's responses are recorded.

[0398] The server then analyzes the user's responses in real time. This analysis includes natural language processing techniques to evaluate how appropriate the user's responses are. Based on this evaluation, the server sends feedback to the terminal. This feedback specifically highlights the user's successes and areas for improvement.

[0399] As a concrete example, consider a simulation where a server generates a persona of an "elderly person who doesn't know how to operate something," and a user responds by explaining the operating procedure in simple language. The server evaluates whether the user's explanation was easy to understand and sends feedback to the terminal. This feedback becomes valuable information for the user to improve in subsequent simulations. Through this process, the user can efficiently improve their customer service skills.

[0400] The following describes the processing flow.

[0401] Step 1:

[0402] The server uses a generation module to generate fictional customer information. This customer information includes age, gender, hobbies, and specific needs or challenges, creating a detailed profile based on a scenario.

[0403] Step 2:

[0404] The server sends the generated customer information to the terminal. The terminal receives this information and presents it to the user through an interface.

[0405] Step 3:

[0406] The user operates the terminal and starts a simulation based on the fictional customer information presented. The user asks questions and makes suggestions for products and services.

[0407] Step 4:

[0408] The terminal records user responses and suggestions and sends them to the server in real time. The server receives this data.

[0409] Step 5:

[0410] The server analyzes the user's response data it receives. Using natural language processing techniques, it evaluates the user's response and determines its appropriateness and specificity.

[0411] Step 6:

[0412] The server generates feedback based on the analysis results. This feedback includes the user's strengths, areas for improvement, and specific advice.

[0413] Step 7:

[0414] The server sends the generated feedback to the terminal and presents it to the user. Through this feedback, the user gains clues to improve their skills for the next simulation.

[0415] (Example 1)

[0416] 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."

[0417] To effectively improve customer service skills, an interaction simulation system is needed that analyzes responses in real time and provides specific feedback. However, existing systems do not adequately perform real-time analysis or offer concrete improvement suggestions, limiting the improvement of users' skills. Therefore, there is a need for effective technology to solve this problem and cultivate more advanced customer service capabilities.

[0418] 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.

[0419] In this invention, the server includes means for creating virtual entity information using a generative model, means for simulating a dialogue based on the virtual entity information, and means for providing an evaluation result to the operator based on the dialogue analysis results. This allows the operator to have their responses analyzed in real time and receive specific, quantifiable feedback, thereby effectively improving their customer service skills.

[0420] A "generative model" is an algorithm or program for automatically creating information about virtual entities.

[0421] "Virtual entity information" refers to data sets about people and objects that do not actually exist but are generated by computers for the purpose of simulation and analysis.

[0422] A "means of simulating dialogue" is a mechanism that provides an environment in which an operator can communicate with a virtual entity by imitating actual interactions.

[0423] A "means of real-time analysis" refers to a technology that has the ability to rapidly analyze the content of an operator's response as soon as it is received and to immediately generate evaluation results.

[0424] "Means of providing evaluation results" refers to a system that, based on analyzed data, provides an evaluation of the operator's actions and decisions, and offers advice and guidance for improvement.

[0425] This invention is primarily implemented by a server, a terminal, and a user. First, the server is responsible for generating virtual entity information. The server has a generative model, which it uses to generate virtual entity information. The generative model employs machine learning algorithms and automatically generates information based on specific conditions by inputting various prompt statements. In terms of hardware, a data processing server with a high-performance processor and sufficient memory is required, and the software typically uses platforms such as Python or TensorFlow.

[0426] The generated virtual entity information is sent from the server to the terminal. The terminal provides an interface for the user to interact with the virtual entity. The terminal uses the received information to launch dedicated simulation software. During interaction, the terminal provides the user with feedback from the virtual entity. This feedback is generated by the server based on the analysis of the response and is intended to help improve the operator's skills.

[0427] Users can participate in interactions using their devices and engage in dialogue with virtual entities. For example, a user might explain the setup procedure in simple terms to an elderly virtual customer who complains that they "don't know how to set up their new smartphone." This information is recorded by the device and sent to the server.

[0428] The server is equipped with natural language processing technology to analyze recorded user responses. This allows the server to quantify the responses and evaluate how effectively the operator supported the virtual entities. The evaluation results are returned to the terminal as numerical data and specific feedback.

[0429] As a concrete example, by entering the prompt statement "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone," entity information based on this condition can be generated. The information generated using this prompt statement enables a more realistic simulation.

[0430] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0431] Step 1:

[0432] The server creates virtual entity information using a generative model.

[0433] The server receives input such as "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone" as a prompt message.

[0434] The generative AI model uses this prompt to generate a detailed profile of a virtual entity. For example, it outputs data for a person that includes information such as age, gender, and specific problems they are facing.

[0435] Step 2:

[0436] The server sends the virtual entity information it generates to the terminal.

[0437] The input is the virtual entity information generated in Step 1.

[0438] The server uses a secure communication protocol to send this information to the terminal. As a result, the entity information reaches and is received by the terminal.

[0439] Step 3:

[0440] The terminal starts an interaction simulation based on virtual entity information.

[0441] The terminal uses entity information received from the server as input.

[0442] The simulation software starts up and is ready to provide the user with the opportunity to interact with virtual entities. The output is an environment where the user can interact with virtual entities on the screen.

[0443] Step 4:

[0444] Users interact with virtual entities through their devices.

[0445] Users use the terminal interface to ask questions to virtual entities and offer suggestions for problems they encounter.

[0446] The input consists of problems or questions presented by a virtual entity, to which the user provides responses. The output is a record of the user's responses, which are later analyzed.

[0447] Step 5:

[0448] The server analyzes user responses in real time.

[0449] The server receives user response data from the terminal as input.

[0450] The system uses natural language processing tools to analyze the content of responses and scores how effective the dialogue was. The output generates points and specific comments as a result of the evaluation.

[0451] Step 6:

[0452] The server generates feedback based on the analysis results and sends it to the terminal.

[0453] The input is the evaluation result obtained in step 5.

[0454] The server generates specific feedback based on the analysis and sends it to the terminal. The user can receive this feedback and use it to improve their next interaction. The output is the feedback information that the user can view.

[0455] (Application Example 1)

[0456] 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."

[0457] Traditional customer service training systems typically rely on hypothetical scenarios, lacking efficient means of providing real-time evaluation and feedback. This makes it difficult for users to immediately understand where they need to improve their responses. Furthermore, the systems struggle to provide realistic customer service experiences, hindering practical skill development.

[0458] 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.

[0459] In this invention, the server includes means for creating fictitious customer information using a generation module, means for simulating interactions based on the fictitious customer information, and means for providing real-time feedback using a display device to improve the user's customer service capabilities. This allows the user to receive real-time evaluations of their responses and make quick and concrete improvements.

[0460] A "generation module" is a device or software used to create fictitious customer information and has the function of providing data to simulate interactions based on that information.

[0461] "Fictional customer information" refers to a dataset that models a hypothetical customer and includes information such as their profile, specific needs, and problems.

[0462] "Interaction" is the process of simulating the dialogue and response behavior that takes place between a user and a virtual customer.

[0463] "Analysis results" refer to the output of evaluation and analysis obtained based on data collected to assess user responses and behavior.

[0464] "Feedback" refers to information provided to users that specifically indicates the appropriateness of their responses and areas for improvement.

[0465] A "display device" is an electronic device used to provide information to a user visually, and includes, for example, smart glasses and head-mounted displays.

[0466] "Real-time" refers to the timing of processing and evaluation that allows for immediate response to user actions and reactions.

[0467] "Customer service ability" refers to the skills and knowledge required to accurately and quickly understand and respond to customer needs, thereby increasing customer satisfaction.

[0468] The system based on this invention provides training to improve customer service capabilities using a user-accessible display device. Multiple processes take place between the server, terminal, and user.

[0469] The server utilizes a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems, allowing users to simulate realistic customer interactions. This generated customer information is sent to the terminal for the user to visually review.

[0470] The terminal uses a display device such as smart glasses or a head-mounted display to initiate an interaction simulation for the user. In this simulation, the user can interact with a fictional customer based on generated customer information, asking appropriate questions and making suggestions.

[0471] All user responses are recorded, and the server analyzes these responses in real time using natural language processing technology (e.g., NLTK). The analysis results are displayed as feedback on a display device, specifically indicating the appropriateness and areas for improvement of the user's responses. This allows the user to immediately improve their responses.

[0472] As a concrete example, a user wearing smart glasses can practice responding to a hypothetical customer asking for directions to a new television. Based on the prompt, "Let's practice guiding a customer looking for the television section. The customer is elderly and wants to know more about the features of the latest model," the user provides a product description using polite language. If the response is accurate and prompt, feedback such as "Your explanation is accurate" will be displayed. This allows for the realistic simulation of effective customer service, which is expected to improve the user's skills.

[0473] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0474] Step 1:

[0475] The server uses a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems. As input, the server provides data parameters for creating the customer information based on prompt messages. As output, the generated customer information is sent to the terminal.

[0476] Step 2:

[0477] The terminal presents an interaction simulation to the user via a display device, based on the received fictitious customer information. The input is customer information data from the server, which is processed into a format that can be visually presented on the display. The output is a display of customer information visible to the user.

[0478] Step 3:

[0479] The user initiates the simulation through a terminal and interacts with a fictional customer. User input is provided via voice or other input devices, and the content is recorded on the terminal. As output, the recorded data is sent to a server for later analysis.

[0480] Step 4:

[0481] The server processes input data using natural language processing techniques to analyze user responses. The input consists of recorded user responses, which are processed using semantic analysis and evaluation algorithms. As a result of the analysis, the server ranks the appropriateness and areas for improvement of the user's responses.

[0482] Step 5:

[0483] The server generates feedback and provides it to the user in real time via the terminal. The feedback is generated based on the analysis results; the input is the analysis result data, and the output is displayed on the terminal as a specific feedback message. The user can use this feedback to improve future interactions.

[0484] 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.

[0485] This invention is a training system consisting of three elements: a server, a terminal, and a user, which works by combining an emotion engine. The server generates fictional customer information via a generation module and starts a simulation based on that information.

[0486] The terminal presents the user with fictitious customer information received from the server, and the user interacts with it. The emotion engine recognizes the user's emotions during the interaction and analyzes the changing emotions in real time. This emotion analysis allows the system to capture what emotions the user is experiencing as they engage in the conversation.

[0487] The analysis results are sent to a server, which generates feedback that takes emotional information into account. This feedback includes not only an evaluation of the previous response, but also suggestions for improving the response based on changes in emotions. Users receive this feedback through their device and can learn how to incorporate emotions into their next interaction.

[0488] As a concrete example, consider a scenario where a user interacts with a persona of a "young person seeking the latest devices." During a conversation with this highly inquisitive young person, if the user exhibits excited emotions, the server recognizes these emotions and provides feedback on how to suggest appropriate products in that excited state. In this way, the emotion engine plays a role in comprehensively improving the user's interaction skills.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The server uses a generation module to create fictional customer information. This customer information includes detailed profiles such as age, hobbies, and needs.

[0492] Step 2:

[0493] The server sends the created fictitious customer information to the terminal. The terminal receives this information and displays it on the screen in a format viewable by the user.

[0494] Step 3:

[0495] The user starts the simulation on their device. Based on customer information, the user interacts with a fictional customer, asking appropriate questions and suggesting products and services.

[0496] Step 4:

[0497] The emotion engine detects and analyzes the user's emotions in real time based on their facial expressions, tone of voice, and content during interactions. The emotion data is then sent to a server for analysis.

[0498] Step 5:

[0499] The server analyzes the user's responses in combination with sentiment data to determine the appropriateness of the user's responses and the influence of emotions.

[0500] Step 6:

[0501] Based on the analysis results, the server sends emotion-sensitive feedback to the terminal. This feedback includes how the user's actions influenced their emotions and suggests specific ways to improve.

[0502] Step 7:

[0503] Users receive feedback through their devices and learn skills for the next simulation. By utilizing this feedback, users can engage in more effective, emotion-conscious dialogue.

[0504] (Example 2)

[0505] 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."

[0506] Conventional dialogue systems have the challenge of not adequately considering user emotions in their feedback during interactions, making it difficult to effectively improve users' dialogue skills. Furthermore, there is a lack of systems capable of analyzing customer emotions in real time during simulations and responding accordingly to those emotional changes.

[0507] 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.

[0508] In this invention, the server includes means for generating fictitious customer data using a generation device, means for simulating a conversation based on the fictitious customer data, and means equipped with an emotion analysis device for analyzing the user's emotions in real time. This makes it possible to provide feedback in response to changes in the user's emotions, thereby effectively improving the user's conversation skills.

[0509] A "generation device" is a device used to generate fictional customer data, and it is responsible for producing various types of data using generation modules and algorithms.

[0510] "Fictional customer data" refers to information about non-existent customers, including their profile such as age, occupation, and interests.

[0511] "Methods for simulating dialogue" refer to methods and systems that conduct virtual interactions with users based on fictional customer data.

[0512] An "emotion analysis device" is a device that analyzes a user's emotions in real time and has the function of evaluating their emotional state using voice and facial expression data.

[0513] "Feedback" refers to information provided to users, including evaluations and suggestions for improvement, based on the results of interactions and sentiment analysis.

[0514] This system consists of three elements: server, terminal, and user, and provides a training environment that effectively utilizes sentiment analysis.

[0515] The server uses a generation device to generate fictional customer data. Here, a natural language processing model, for example, is used as the generation AI model to create diverse customer profiles including age, occupation, and interests. This generation allows users to be trained through various scenarios.

[0516] The terminal presents the user with fictitious customer data sent from the server. The user interacts with the terminal based on the presented customer data. During this interaction, input from the terminal is received via a microphone, keyboard, etc., and the user's speech and text are processed by a dialogue module.

[0517] During user interaction, an emotion analysis device analyzes the user's emotions in real time. Emotion analysis utilizes technologies such as speech recognition and facial recognition, with services like IBM Watson Tone Analyzer being used as examples. This allows the user's emotional state to be constantly monitored, and analysis to be performed as needed.

[0518] The server generates feedback based on the results of the user's sentiment analysis. This feedback includes suggestions and areas for improvement based on changes in emotion, designed to help the user apply them to their next interaction. The generated feedback is provided to the user via the device to support their learning.

[0519] A concrete example would be a dialogue scenario with a "young person seeking the latest devices." In this scenario, when the user makes a product suggestion to a fictional young customer, if the customer's emotion is detected as "excitement," the server provides feedback such as "emphasize visual demonstrations when explaining to excited customers."

[0520] An example of a prompt is: "When talking to a hypothetical young customer about the benefits of a new smartphone, how can you engage their interest?"

[0521] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0522] Step 1:

[0523] The server generates fictional customer data using a generative AI model. A prompt is given as input, and the AI ​​model processes the data based on that prompt. The output is a fictional customer profile that includes the customer's age, occupation, interests, etc. Specifically, the server starts the generation module and sends the prompt "Create a customer profile for a young person interested in new smartphones" to the AI ​​model.

[0524] Step 2:

[0525] The terminal receives fictitious customer data sent from the server and presents it to the user. The input is customer profile data from the server, which the terminal displays on the screen. The output is a display of customer information in a format that the user can review. Specifically, the terminal displays the received data in a list and prompts the user to prepare for the interaction.

[0526] Step 3:

[0527] The user interacts with the system based on customer data presented via the device. Input is customer information displayed on the device, and output is the conversation entered by the user. User speech and text input are also recorded as data. For example, the user might input a message into the device such as, "The features of this smartphone are..."

[0528] Step 4:

[0529] The emotion analysis device analyzes the user's emotions in real time from their speech and facial expressions. The input is the user's voice data and facial expression data, and the device evaluates changes in emotion through analysis. The output is a detailed analysis result of the emotional state. Specifically, the emotion analysis device uses the user's voice tone and facial expressions to identify emotions such as "excitement" and "satisfaction."

[0530] Step 5:

[0531] The analyzed emotion data is sent to the server to generate feedback. The input is the result of the emotion analysis and the interaction history, and the server creates feedback based on this data. The output is feedback that includes specific countermeasures and improvements based on the change in emotion. For example, if the server determines that the emotion is "excited," it will generate feedback such as "A product demonstration is effective for excited customers."

[0532] Step 6:

[0533] The user receives feedback from the server via the device and uses it to improve future interactions. The input is feedback information from the server, which the device presents to the user. The output is the user's confirmation and understanding of the feedback. Specifically, the device displays the generated feedback as text, and the user learns from it to improve future interactions.

[0534] (Application Example 2)

[0535] 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."

[0536] In modern brick-and-mortar stores, customer service requires quick and accurate interaction. However, understanding customers' emotions and attitudes in real time and responding appropriately is difficult for less experienced service staff. As a result, problems arise such as inconsistent service quality and decreased customer satisfaction. There is a need to develop a system that solves these problems and allows any staff member to consistently provide high-quality customer service.

[0537] 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.

[0538] In this invention, the server includes means for creating fictitious user information using a generation module, means for simulating interactions based on the fictitious user information, means for providing insights to the operator based on the analysis results of the interactions, means for analyzing the operator's emotional state in real time using an emotion analysis engine, and means for generating appropriate action suggestions for the operator based on the emotion analysis results. This enables customer service staff to provide appropriate responses in real time that are in line with the customer's emotions.

[0539] A "generation module" is a component that has the function of creating fictitious user information.

[0540] "User information" refers to various data related to fictional or actual operators, and is the basic information used in simulations.

[0541] "Simulating interaction" means reproducing the actual interaction between the operator and the user in a virtual environment.

[0542] An "emotion analysis engine" is a software or hardware system for recognizing and analyzing the emotional state of an operator in real time.

[0543] "Discussion" refers to information provided to the operator, including evaluations and advice based on the results of the interaction.

[0544] "Action suggestions" are pieces of information that indicate the appropriate next action the operator should take, based on emotion analysis and interaction results.

[0545] In implementing this invention, the server operates as follows: First, it creates fictitious user information using a generation module. This prepares a scenario for staff to train in customer service. The terminal simulates interaction based on this user information and presents the interaction to the operator.

[0546] During the user's interaction via the device, an emotion analysis engine analyzes the user's emotional state in real time. For example, sensors in smart glasses capture the user's facial expressions and tone of voice, and the emotional state is determined based on this data. Based on these results, the server generates action suggestions and provides feedback to the user through the device. This feedback is based on the user's responses and emotional state and includes advice that can lead to improved behavior.

[0547] For example, if smart glasses detect a customer's excitement level while they are receiving a new product explanation in a physical store, the server analyzes this information and provides feedback to the operator suggesting actions such as "providing detailed product information and feature descriptions." This allows the operator to respond smoothly in a way that aligns with the customer's emotions.

[0548] An example of a prompt would be, "Create a program that performs sentiment analysis and generates appropriate suggestion feedback in real time for customer service training using smart glasses for a new product." This prompt facilitates the generation of specific training scenarios.

[0549] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0550] Step 1:

[0551] The server generates fictional user information through a generation module. User profile information (e.g., age, interests, desired information) is provided as input. Based on this input, a generation AI model is used to generate fictional user information for various scenarios in a database. The output is the fictional user information used by the operator for training.

[0552] Step 2:

[0553] The terminal receives fictitious user information sent from the server and presents it to the user. The input is fictitious user information from the server. Based on this information, the terminal simulates an interaction and presents it to the operator through the display and audio output. The output is expressed as a simulated interaction experienced by the operator.

[0554] Step 3:

[0555] The user interacts with the presented hypothetical user information. The input here is the simulated information and scenarios the user receives. The user's responses are input into the sentiment analysis engine in real time, and the user's emotional state data is generated as output.

[0556] Step 4:

[0557] The server uses an emotion analysis engine to analyze emotional state data received from the user. The input consists of the user's responses and emotional state data. This allows the server to capture changes in the user's emotions and perform data calculations to determine appropriate action suggestions. The output is the emotion-based analysis result.

[0558] Step 5:

[0559] The server generates feedback for the user based on the analysis results. The input is the analysis results based on emotions. Based on the analysis results, prompt messages are created that indicate areas for improvement and specific action suggestions to the user. This output is presented to the user as feedback information through the terminal.

[0560] Step 6:

[0561] The user receives feedback sent from the server via their device and uses it to improve their next interaction. The input is the feedback information from the server. Based on this feedback, the user learns specific areas for improvement to enhance their customer service skills. The output is the user's improved customer service skills.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] [Fourth Embodiment]

[0566] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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".

[0579] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. This system is built via a server that has a built-in generation module. The server first generates fictional customer information. This information includes a detailed profile, such as age, gender, hobbies, specific needs, and problems.

[0580] The server then sends the generated customer information to the terminal. The terminal is a device operated by the user, and it starts an interaction simulation based on the received information. During this simulation, the user can interact with a fictional customer through the terminal, asking appropriate questions and making suggestions. All of the user's responses are recorded.

[0581] The server then analyzes the user's responses in real time. This analysis includes natural language processing techniques to evaluate how appropriate the user's responses are. Based on this evaluation, the server sends feedback to the terminal. This feedback specifically highlights the user's successes and areas for improvement.

[0582] As a concrete example, consider a simulation where a server generates a persona of an "elderly person who doesn't know how to operate something," and a user responds by explaining the operating procedure in simple language. The server evaluates whether the user's explanation was easy to understand and sends feedback to the terminal. This feedback becomes valuable information for the user to improve in subsequent simulations. Through this process, the user can efficiently improve their customer service skills.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] The server uses a generation module to generate fictional customer information. This customer information includes age, gender, hobbies, and specific needs or challenges, creating a detailed profile based on a scenario.

[0586] Step 2:

[0587] The server sends the generated customer information to the terminal. The terminal receives this information and presents it to the user through an interface.

[0588] Step 3:

[0589] The user operates the terminal and starts a simulation based on the fictional customer information presented. The user asks questions and makes suggestions for products and services.

[0590] Step 4:

[0591] The terminal records user responses and suggestions and sends them to the server in real time. The server receives this data.

[0592] Step 5:

[0593] The server analyzes the user's response data it receives. Using natural language processing techniques, it evaluates the user's response and determines its appropriateness and specificity.

[0594] Step 6:

[0595] The server generates feedback based on the analysis results. This feedback includes the user's strengths, areas for improvement, and specific advice.

[0596] Step 7:

[0597] The server sends the generated feedback to the terminal and presents it to the user. Through this feedback, the user gains clues to improve their skills for the next simulation.

[0598] (Example 1)

[0599] 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".

[0600] To effectively improve customer service skills, an interaction simulation system is needed that analyzes responses in real time and provides specific feedback. However, existing systems do not adequately perform real-time analysis or offer concrete improvement suggestions, limiting the improvement of users' skills. Therefore, there is a need for effective technology to solve this problem and cultivate more advanced customer service capabilities.

[0601] 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.

[0602] In this invention, the server includes means for creating virtual entity information using a generative model, means for simulating a dialogue based on the virtual entity information, and means for providing an evaluation result to the operator based on the dialogue analysis results. This allows the operator to have their responses analyzed in real time and receive specific, quantifiable feedback, thereby effectively improving their customer service skills.

[0603] A "generative model" is an algorithm or program for automatically creating information about virtual entities.

[0604] "Virtual entity information" refers to data sets about people and objects that do not actually exist but are generated by computers for the purpose of simulation and analysis.

[0605] A "means of simulating dialogue" is a mechanism that provides an environment in which an operator can communicate with a virtual entity by imitating actual interactions.

[0606] A "means of real-time analysis" refers to a technology that has the ability to rapidly analyze the content of an operator's response as soon as it is received and to immediately generate evaluation results.

[0607] "Means of providing evaluation results" refers to a system that, based on analyzed data, provides an evaluation of the operator's actions and decisions, and offers advice and guidance for improvement.

[0608] This invention is primarily implemented by a server, a terminal, and a user. First, the server is responsible for generating virtual entity information. The server has a generative model, which it uses to generate virtual entity information. The generative model employs machine learning algorithms and automatically generates information based on specific conditions by inputting various prompt statements. In terms of hardware, a data processing server with a high-performance processor and sufficient memory is required, and the software typically uses platforms such as Python or TensorFlow.

[0609] The generated virtual entity information is sent from the server to the terminal. The terminal provides an interface for the user to interact with the virtual entity. The terminal uses the received information to launch dedicated simulation software. During interaction, the terminal provides the user with feedback from the virtual entity. This feedback is generated by the server based on the analysis of the response and is intended to help improve the operator's skills.

[0610] Users can participate in interactions using their devices and engage in dialogue with virtual entities. For example, a user might explain the setup procedure in simple terms to an elderly virtual customer who complains that they "don't know how to set up their new smartphone." This information is recorded by the device and sent to the server.

[0611] The server is equipped with natural language processing technology to analyze recorded user responses. This allows the server to quantify the responses and evaluate how effectively the operator supported the virtual entities. The evaluation results are returned to the terminal as numerical data and specific feedback.

[0612] As a concrete example, by entering the prompt statement "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone," entity information based on this condition can be generated. The information generated using this prompt statement enables a more realistic simulation.

[0613] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0614] Step 1:

[0615] The server creates virtual entity information using a generative model.

[0616] The server receives input such as "A 65-year-old person unfamiliar with technology is having trouble setting up their smartphone" as a prompt message.

[0617] The generative AI model uses this prompt to generate a detailed profile of a virtual entity. For example, it outputs data for a person that includes information such as age, gender, and specific problems they are facing.

[0618] Step 2:

[0619] The server sends the virtual entity information it generates to the terminal.

[0620] The input is the virtual entity information generated in Step 1.

[0621] The server uses a secure communication protocol to send this information to the terminal. As a result, the entity information reaches and is received by the terminal.

[0622] Step 3:

[0623] The terminal starts an interaction simulation based on virtual entity information.

[0624] The terminal uses entity information received from the server as input.

[0625] The simulation software starts up and is ready to provide the user with the opportunity to interact with virtual entities. The output is an environment where the user can interact with virtual entities on the screen.

[0626] Step 4:

[0627] Users interact with virtual entities through their devices.

[0628] Users use the terminal interface to ask questions to virtual entities and offer suggestions for problems they encounter.

[0629] The input consists of problems or questions presented by a virtual entity, to which the user provides responses. The output is a record of the user's responses, which are later analyzed.

[0630] Step 5:

[0631] The server analyzes user responses in real time.

[0632] The server receives user response data from the terminal as input.

[0633] The system uses natural language processing tools to analyze the content of responses and scores how effective the dialogue was. The output generates points and specific comments as a result of the evaluation.

[0634] Step 6:

[0635] The server generates feedback based on the analysis results and sends it to the terminal.

[0636] The input is the evaluation result obtained in step 5.

[0637] The server generates specific feedback based on the analysis and sends it to the terminal. The user can receive this feedback and use it to improve their next interaction. The output is the feedback information that the user can view.

[0638] (Application Example 1)

[0639] 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".

[0640] Traditional customer service training systems typically rely on hypothetical scenarios, lacking efficient means of providing real-time evaluation and feedback. This makes it difficult for users to immediately understand where they need to improve their responses. Furthermore, the systems struggle to provide realistic customer service experiences, hindering practical skill development.

[0641] 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.

[0642] In this invention, the server includes means for creating fictitious customer information using a generation module, means for simulating interactions based on the fictitious customer information, and means for providing real-time feedback using a display device to improve the user's customer service capabilities. This allows the user to receive real-time evaluations of their responses and make quick and concrete improvements.

[0643] A "generation module" is a device or software used to create fictitious customer information and has the function of providing data to simulate interactions based on that information.

[0644] "Fictional customer information" refers to a dataset that models a hypothetical customer and includes information such as their profile, specific needs, and problems.

[0645] "Interaction" is the process of simulating the dialogue and response behavior that takes place between a user and a virtual customer.

[0646] "Analysis results" refer to the output of evaluation and analysis obtained based on data collected to assess user responses and behavior.

[0647] "Feedback" refers to information provided to users that specifically indicates the appropriateness of their responses and areas for improvement.

[0648] A "display device" is an electronic device used to provide information to a user visually, and includes, for example, smart glasses and head-mounted displays.

[0649] "Real-time" refers to the timing of processing and evaluation that allows for immediate response to user actions and reactions.

[0650] "Customer service ability" refers to the skills and knowledge required to accurately and quickly understand and respond to customer needs, thereby increasing customer satisfaction.

[0651] The system based on this invention provides training to improve customer service capabilities using a user-accessible display device. Multiple processes take place between the server, terminal, and user.

[0652] The server utilizes a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems, allowing users to simulate realistic customer interactions. This generated customer information is sent to the terminal for the user to visually review.

[0653] The terminal uses a display device such as smart glasses or a head-mounted display to initiate an interaction simulation for the user. In this simulation, the user can interact with a fictional customer based on generated customer information, asking appropriate questions and making suggestions.

[0654] All user responses are recorded, and the server analyzes these responses in real time using natural language processing technology (e.g., NLTK). The analysis results are displayed as feedback on a display device, specifically indicating the appropriateness and areas for improvement of the user's responses. This allows the user to immediately improve their responses.

[0655] As a concrete example, a user wearing smart glasses can practice responding to a hypothetical customer asking for directions to a new television. Based on the prompt, "Let's practice guiding a customer looking for the television section. The customer is elderly and wants to know more about the features of the latest model," the user provides a product description using polite language. If the response is accurate and prompt, feedback such as "Your explanation is accurate" will be displayed. This allows for the realistic simulation of effective customer service, which is expected to improve the user's skills.

[0656] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0657] Step 1:

[0658] The server uses a generative AI model to generate fictional customer information. This information includes the customer's age, gender, hobbies, and specific needs or problems. As input, the server provides data parameters for creating the customer information based on prompt messages. As output, the generated customer information is sent to the terminal.

[0659] Step 2:

[0660] The terminal presents an interaction simulation to the user via a display device, based on the received fictitious customer information. The input is customer information data from the server, which is processed into a format that can be visually presented on the display. The output is a display of customer information visible to the user.

[0661] Step 3:

[0662] The user initiates the simulation through a terminal and interacts with a fictional customer. User input is provided via voice or other input devices, and the content is recorded on the terminal. As output, the recorded data is sent to a server for later analysis.

[0663] Step 4:

[0664] The server processes input data using natural language processing techniques to analyze user responses. The input consists of recorded user responses, which are processed using semantic analysis and evaluation algorithms. As a result of the analysis, the server ranks the appropriateness and areas for improvement of the user's responses.

[0665] Step 5:

[0666] The server generates feedback and provides it to the user in real time via the terminal. The feedback is generated based on the analysis results; the input is the analysis result data, and the output is displayed on the terminal as a specific feedback message. The user can use this feedback to improve future interactions.

[0667] 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.

[0668] This invention is a training system consisting of three elements: a server, a terminal, and a user, which works by combining an emotion engine. The server generates fictional customer information via a generation module and starts a simulation based on that information.

[0669] The terminal presents the user with fictitious customer information received from the server, and the user interacts with it. The emotion engine recognizes the user's emotions during the interaction and analyzes the changing emotions in real time. This emotion analysis allows the system to capture what emotions the user is experiencing as they engage in the conversation.

[0670] The analysis results are sent to a server, which generates feedback that takes emotional information into account. This feedback includes not only an evaluation of the previous response, but also suggestions for improving the response based on changes in emotions. Users receive this feedback through their device and can learn how to incorporate emotions into their next interaction.

[0671] As a concrete example, consider a scenario where a user interacts with a persona of a "young person seeking the latest devices." During a conversation with this highly inquisitive young person, if the user exhibits excited emotions, the server recognizes these emotions and provides feedback on how to suggest appropriate products in that excited state. In this way, the emotion engine plays a role in comprehensively improving the user's interaction skills.

[0672] The following describes the processing flow.

[0673] Step 1:

[0674] The server uses a generation module to create fictional customer information. This customer information includes detailed profiles such as age, hobbies, and needs.

[0675] Step 2:

[0676] The server sends the created fictitious customer information to the terminal. The terminal receives this information and displays it on the screen in a format viewable by the user.

[0677] Step 3:

[0678] The user starts the simulation on their device. Based on customer information, the user interacts with a fictional customer, asking appropriate questions and suggesting products and services.

[0679] Step 4:

[0680] The emotion engine detects and analyzes the user's emotions in real time based on their facial expressions, tone of voice, and content during interactions. The emotion data is then sent to a server for analysis.

[0681] Step 5:

[0682] The server analyzes the user's responses in combination with sentiment data to determine the appropriateness of the user's responses and the influence of emotions.

[0683] Step 6:

[0684] Based on the analysis results, the server sends emotion-sensitive feedback to the terminal. This feedback includes how the user's actions influenced their emotions and suggests specific ways to improve.

[0685] Step 7:

[0686] Users receive feedback through their devices and learn skills for the next simulation. By utilizing this feedback, users can engage in more effective, emotion-conscious dialogue.

[0687] (Example 2)

[0688] 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".

[0689] Conventional dialogue systems have the challenge of not adequately considering user emotions in their feedback during interactions, making it difficult to effectively improve users' dialogue skills. Furthermore, there is a lack of systems capable of analyzing customer emotions in real time during simulations and responding accordingly to those emotional changes.

[0690] 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.

[0691] In this invention, the server includes means for generating fictitious customer data using a generation device, means for simulating a conversation based on the fictitious customer data, and means equipped with an emotion analysis device for analyzing the user's emotions in real time. This makes it possible to provide feedback in response to changes in the user's emotions, thereby effectively improving the user's conversation skills.

[0692] A "generation device" is a device used to generate fictional customer data, and it is responsible for producing various types of data using generation modules and algorithms.

[0693] "Fictional customer data" refers to information about non-existent customers, including their profile such as age, occupation, and interests.

[0694] "Methods for simulating dialogue" refer to methods and systems that conduct virtual interactions with users based on fictional customer data.

[0695] An "emotion analysis device" is a device that analyzes a user's emotions in real time and has the function of evaluating their emotional state using voice and facial expression data.

[0696] "Feedback" refers to information provided to users, including evaluations and suggestions for improvement, based on the results of interactions and sentiment analysis.

[0697] This system consists of three elements: server, terminal, and user, and provides a training environment that effectively utilizes sentiment analysis.

[0698] The server uses a generation device to generate fictional customer data. Here, a natural language processing model, for example, is used as the generation AI model to create diverse customer profiles including age, occupation, and interests. This generation allows users to be trained through various scenarios.

[0699] The terminal presents the user with fictitious customer data sent from the server. The user interacts with the terminal based on the presented customer data. During this interaction, input from the terminal is received via a microphone, keyboard, etc., and the user's speech and text are processed by a dialogue module.

[0700] During user interaction, an emotion analysis device analyzes the user's emotions in real time. Emotion analysis utilizes technologies such as speech recognition and facial recognition, with services like IBM Watson Tone Analyzer being used as examples. This allows the user's emotional state to be constantly monitored, and analysis to be performed as needed.

[0701] The server generates feedback based on the results of the user's sentiment analysis. This feedback includes suggestions and areas for improvement based on changes in emotion, designed to help the user apply them to their next interaction. The generated feedback is provided to the user via the device to support their learning.

[0702] A concrete example would be a dialogue scenario with a "young person seeking the latest devices." In this scenario, when the user makes a product suggestion to a fictional young customer, if the customer's emotion is detected as "excitement," the server provides feedback such as "emphasize visual demonstrations when explaining to excited customers."

[0703] An example of a prompt is: "When talking to a hypothetical young customer about the benefits of a new smartphone, how can you engage their interest?"

[0704] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0705] Step 1:

[0706] The server generates fictional customer data using a generative AI model. A prompt is given as input, and the AI ​​model processes the data based on that prompt. The output is a fictional customer profile that includes the customer's age, occupation, interests, etc. Specifically, the server starts the generation module and sends the prompt "Create a customer profile for a young person interested in new smartphones" to the AI ​​model.

[0707] Step 2:

[0708] The terminal receives fictitious customer data sent from the server and presents it to the user. The input is customer profile data from the server, which the terminal displays on the screen. The output is a display of customer information in a format that the user can review. Specifically, the terminal displays the received data in a list and prompts the user to prepare for the interaction.

[0709] Step 3:

[0710] The user interacts with the system based on customer data presented via the device. Input is customer information displayed on the device, and output is the conversation entered by the user. User speech and text input are also recorded as data. For example, the user might input a message into the device such as, "The features of this smartphone are..."

[0711] Step 4:

[0712] The emotion analysis device analyzes the user's emotions in real time from their speech and facial expressions. The input is the user's voice data and facial expression data, and the device evaluates changes in emotion through analysis. The output is a detailed analysis result of the emotional state. Specifically, the emotion analysis device uses the user's voice tone and facial expressions to identify emotions such as "excitement" and "satisfaction."

[0713] Step 5:

[0714] The analyzed emotion data is sent to the server to generate feedback. The input is the result of the emotion analysis and the interaction history, and the server creates feedback based on this data. The output is feedback that includes specific countermeasures and improvements based on the change in emotion. For example, if the server determines that the emotion is "excited," it will generate feedback such as "A product demonstration is effective for excited customers."

[0715] Step 6:

[0716] The user receives feedback from the server via the device and uses it to improve future interactions. The input is feedback information from the server, which the device presents to the user. The output is the user's confirmation and understanding of the feedback. Specifically, the device displays the generated feedback as text, and the user learns from it to improve future interactions.

[0717] (Application Example 2)

[0718] 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".

[0719] In modern brick-and-mortar stores, customer service requires quick and accurate interaction. However, understanding customers' emotions and attitudes in real time and responding appropriately is difficult for less experienced service staff. As a result, problems arise such as inconsistent service quality and decreased customer satisfaction. There is a need to develop a system that solves these problems and allows any staff member to consistently provide high-quality customer service.

[0720] 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.

[0721] In this invention, the server includes means for creating fictitious user information using a generation module, means for simulating interactions based on the fictitious user information, means for providing insights to the operator based on the analysis results of the interactions, means for analyzing the operator's emotional state in real time using an emotion analysis engine, and means for generating appropriate action suggestions for the operator based on the emotion analysis results. This enables customer service staff to provide appropriate responses in real time that are in line with the customer's emotions.

[0722] A "generation module" is a component that has the function of creating fictitious user information.

[0723] "User information" refers to various data related to fictional or actual operators, and is the basic information used in simulations.

[0724] "Simulating interaction" means reproducing the actual interaction between the operator and the user in a virtual environment.

[0725] An "emotion analysis engine" is a software or hardware system for recognizing and analyzing the emotional state of an operator in real time.

[0726] "Discussion" refers to information provided to the operator, including evaluations and advice based on the results of the interaction.

[0727] "Action suggestions" are pieces of information that indicate the appropriate next action the operator should take, based on emotion analysis and interaction results.

[0728] In implementing this invention, the server operates as follows: First, it creates fictitious user information using a generation module. This prepares a scenario for staff to train in customer service. The terminal simulates interaction based on this user information and presents the interaction to the operator.

[0729] During the user's interaction via the device, an emotion analysis engine analyzes the user's emotional state in real time. For example, sensors in smart glasses capture the user's facial expressions and tone of voice, and the emotional state is determined based on this data. Based on these results, the server generates action suggestions and provides feedback to the user through the device. This feedback is based on the user's responses and emotional state and includes advice that can lead to improved behavior.

[0730] For example, if smart glasses detect a customer's excitement level while they are receiving a new product explanation in a physical store, the server analyzes this information and provides feedback to the operator suggesting actions such as "providing detailed product information and feature descriptions." This allows the operator to respond smoothly in a way that aligns with the customer's emotions.

[0731] An example of a prompt would be, "Create a program that performs sentiment analysis and generates appropriate suggestion feedback in real time for customer service training using smart glasses for a new product." This prompt facilitates the generation of specific training scenarios.

[0732] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0733] Step 1:

[0734] The server generates fictional user information through a generation module. User profile information (e.g., age, interests, desired information) is provided as input. Based on this input, a generation AI model is used to generate fictional user information for various scenarios in a database. The output is the fictional user information used by the operator for training.

[0735] Step 2:

[0736] The terminal receives fictitious user information sent from the server and presents it to the user. The input is fictitious user information from the server. Based on this information, the terminal simulates an interaction and presents it to the operator through the display and audio output. The output is expressed as a simulated interaction experienced by the operator.

[0737] Step 3:

[0738] The user interacts with the presented hypothetical user information. The input here is the simulated information and scenarios the user receives. The user's responses are input into the sentiment analysis engine in real time, and the user's emotional state data is generated as output.

[0739] Step 4:

[0740] The server uses an emotion analysis engine to analyze emotional state data received from the user. The input consists of the user's responses and emotional state data. This allows the server to capture changes in the user's emotions and perform data calculations to determine appropriate action suggestions. The output is the emotion-based analysis result.

[0741] Step 5:

[0742] The server generates feedback for the user based on the analysis results. The input is the analysis results based on emotions. Based on the analysis results, prompt messages are created that indicate areas for improvement and specific action suggestions to the user. This output is presented to the user as feedback information through the terminal.

[0743] Step 6:

[0744] The user receives feedback sent from the server via their device and uses it to improve their next interaction. The input is the feedback information from the server. Based on this feedback, the user learns specific areas for improvement to enhance their customer service skills. The output is the user's improved customer service skills.

[0745] 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.

[0746] 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.

[0747] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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."

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0766] The following is further disclosed regarding the embodiments described above.

[0767] (Claim 1)

[0768] A means of creating fictitious customer information using a generation module,

[0769] A means for simulating interaction based on the aforementioned fictitious customer information,

[0770] A means for providing feedback to the user based on the analysis results of the aforementioned interaction,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, further comprising means for analyzing the user's response obtained through the aforementioned interaction in real time.

[0774] (Claim 3)

[0775] The system according to claim 1, further comprising means for specifically indicating areas for improvement based on the user's response in the feedback.

[0776] "Example 1"

[0777] (Claim 1)

[0778] A means of creating virtual entity information using a generative model,

[0779] A means for simulating a dialogue based on the aforementioned virtual entity information,

[0780] A means for providing evaluation results to the operator based on the analysis results of the aforementioned dialogue,

[0781] In the aforementioned evaluation results, a means for quantifying the effect of the operator's response content,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, further comprising means for analyzing the operator's response obtained through the aforementioned dialogue in real time.

[0785] (Claim 3)

[0786] The system according to claim 1, further comprising means for specifically indicating areas for improvement based on the operator's response in the evaluation results.

[0787] "Application Example 1"

[0788] (Claim 1)

[0789] A means of creating fictitious customer information using a generation module,

[0790] A means for simulating interaction based on the aforementioned fictitious customer information,

[0791] A means for providing feedback to the user based on the analysis results of the aforementioned interaction,

[0792] A means of providing real-time feedback using a display device to improve the user's customer service skills,

[0793] A system that includes this.

[0794] (Claim 2)

[0795] The system according to claim 1, wherein the display device includes means for simulating user actions in a realistic environment.

[0796] (Claim 3)

[0797] The system according to claim 1, further comprising means for specifically indicating areas for improvement based on the user's response in the feedback.

[0798] "Example 2 of combining an emotion engine"

[0799] (Claim 1)

[0800] A means for generating fictitious customer data using a generation device,

[0801] A means for simulating a conversation based on the aforementioned fictitious customer data,

[0802] A means equipped with an emotion analysis device that analyzes the user's emotions in real time,

[0803] A means for providing feedback to the user based on the aforementioned emotion analysis results,

[0804] A system that includes this.

[0805] (Claim 2)

[0806] The system according to claim 1, further comprising means for analyzing the user's response obtained through the aforementioned dialogue in real time.

[0807] (Claim 3)

[0808] The system according to claim 1, which includes means for specifically indicating areas for improvement based on changes in the user's emotions in the feedback.

[0809] "Application example 2 when combining with an emotional engine"

[0810] (Claim 1)

[0811] A means of creating fictitious user information using a generation module,

[0812] Based on the aforementioned fictitious user information, a means for simulating interaction,

[0813] A means for providing insights to the operator based on the analysis results of the aforementioned AC,

[0814] A means of analyzing the operator's emotional state in real time using an emotion analysis engine,

[0815] A means for generating appropriate action suggestions for the operator based on the emotion analysis results,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, further comprising means for analyzing the operator's response obtained through the aforementioned communication in real time.

[0819] (Claim 3)

[0820] The system according to claim 1, further comprising means for specifically indicating areas for improvement based on the operator's response content and emotional state. [Explanation of Symbols]

[0821] 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 creating fictitious customer information using a generation module, A means for simulating interaction based on the aforementioned fictitious customer information, A means for providing feedback to the user based on the analysis results of the aforementioned interaction, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the user's response obtained through the aforementioned interaction in real time.

3. The system according to claim 1, further comprising means for specifically indicating areas for improvement based on the user's response in the feedback.

Images