system

Abstract

We provide the system. [Solution] A means of randomly setting person attribute data for the purpose of training users, A means of constructing a sales procedure based on the attribute data of a set person, A means of presenting the established procedure to the user and recording the user's response, A means for analyzing user responses and generating feedback, A means to record the user's process from the start, dynamically adjust the next steps, and optimize training, 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the current corporate workplace, there is a demand for quickly turning new employees into productive members and providing uniform and high-quality education. However, conventional training methods tend to rely on the experience and skills of instructors, and there is a problem that the quality of education is not consistent for each individual new employee. In addition, one-on-one role-playing by senior employees is required, resulting in a large burden on human resources. As a result, improving the efficiency of training and expanding its scope of application have become issues.

Means for Solving the Problems

[0005] This invention addresses the problem it seeks to solve by using an information processing device that generates virtual customers. Specifically, it provides a means for constructing sales scenarios based on randomly set customer attribute data for the purpose of user training, and for presenting these scenarios to users. It also includes a mechanism for generating immediate feedback by recording and analyzing user responses. This configuration makes it possible to reduce the burden on human resources in training and provide consistent, high-quality education.

[0006] A "virtual customer" is a fictional customer created through computer generation, with its attributes virtually defined.

[0007] An "information processing device" is a device that has the ability to receive, store, convert, and output data, and processes information according to a specific purpose.

[0008] "Customer attribute data" refers to a dataset that includes information such as the customer's age, gender, occupation, hobbies, purchasing motivation, and budget.

[0009] A "sales scenario" is a planned outline that shows a series of exercises and situations in which a product or service is proposed to a hypothetical customer.

[0010] "User response" refers to the answers or reactions that users provide during interactions with virtual customers.

[0011] "Analysis" is the process of evaluating the obtained data and responses and converting them into meaningful information.

[0012] "Feedback" refers to the information provided to users regarding their performance, including evaluations, encouragement, and suggestions for improvement.

[0013] "Training progress" is an indicator that shows how much a user has improved their skills and knowledge during the training process. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [[ID=^9]] [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [ [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. <{ [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. ... [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example / 2 when an emotion engine is combined. ... [[ID=^44]]

Embodiments for Carrying Out the Invention

[0015] Note: There seems to be a formatting issue in the original text with an unexpected '^' in the ID=9 and ID=44 lines which might be a mistake. I've translated as is while keeping that in mind. Also, the ellipsis in the translation of ID=43 is to indicate that the original text might be incomplete or there could be more content related to that sequence diagram description which is not fully shown here. Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, a 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.

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

[0019] In the following embodiments, a 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, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] To implement the present invention, a server as an information processing device, a terminal operated by the user, and a program that manages the entire process are used.

[0036] At system startup, the server first uses an AI engine to generate virtual customers. Customer personas are randomly and rationally generated by the server and include attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0037] Next, the server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario refers to the product catalog database and includes product information that matches the needs of the virtual customer.

[0038] The constructed scenario is presented to the user via the device. Based on this scenario, the user simulates interaction with a virtual customer. Interaction can be conducted via text input or voice input.

[0039] User responses are recorded on the device and sent to the server sequentially. The server analyzes this response data and uses AI algorithms to evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback includes specific advice on what went well and what needs improvement, and is presented to the user through the device.

[0040] Furthermore, the server tracks the user's overall training progress and dynamically adjusts the next scenario as needed. This adjustment is to provide training content of varying difficulty levels tailored to the user's proficiency.

[0041] For example, if the user is a new sales representative, they might be presented with a scenario in which they practice proposing a mobile phone plan to a customer with young children. The user's responses would then be given specific feedback on whether they considered the budget and whether they accurately understood the customer's needs.

[0042] This embodiment ensures training consistency and strengthens customer service skills through diverse scenarios, enabling new employees to become productive quickly and improving the efficiency of their training.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server starts the system and loads the necessary information from the AI ​​engine and database. This information includes customer attribute templates and product catalogs.

[0046] Step 2:

[0047] The server generates random customer personas based on customer attribute templates. These personas are assigned attributes such as age, gender, occupation, hobbies, purchase motivation, and budget.

[0048] Step 3:

[0049] The server builds the optimal sales scenario based on the generated customer persona. In this process, product information that matches the customer persona's needs is selected from the product catalog.

[0050] Step 4:

[0051] The terminal displays the sales scenario and customer persona information received from the server to the user on the screen.

[0052] Step 5:

[0053] Users interact with virtual customers based on presented scenarios and propose products and services. Users can respond via text or voice.

[0054] Step 6:

[0055] The device records user interaction data in real time and sends this data to the server sequentially.

[0056] Step 7:

[0057] The server analyzes the received interaction data and uses an AI algorithm to evaluate the user's response. Based on the accuracy and appropriateness of the response, it generates feedback.

[0058] Step 8:

[0059] The terminal displays feedback sent from the server to the user. This feedback includes specific improvement suggestions and assignments for the next training session.

[0060] Step 9:

[0061] The server logs user performance and tracks training progress. This allows the training content to be dynamically adjusted according to the user's proficiency level.

[0062] Step 10:

[0063] The user reviews the feedback and, if necessary, proceeds to the next scenario or ends the training. The system then initiates the next cycle based on the user's choice.

[0064] (Example 1)

[0065] 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."

[0066] In modern consumer service training, effectively learning within limited time and resources is a challenging task. Specifically, this involves practical dialogues based on diverse consumer scenarios and receiving immediate feedback based on the analysis of the results. However, traditional methods struggle to provide efficient training and generate appropriate feedback, thus creating a need for means to achieve rapid and effective skill improvement.

[0067] 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.

[0068] In this invention, the server includes means for predicting and setting consumer attribute information for the purpose of user education, means for creating a sales plan based on the set consumer attribute information, and means for dynamically adjusting the next plan according to the user's education progress. This enables users to quickly and effectively improve their skills by undergoing practical training through various virtual customer scenarios and receiving immediate feedback.

[0069] A "virtual customer" is a fictional consumer model with consumer attribute information and behavior, digitally generated for the purpose of consumer response training and simulation.

[0070] A "data processing device" is an electronic device or system used for collecting, analyzing, and generating information.

[0071] "Users" refer to individuals or organizations that use this system for training or simulations.

[0072] "Education" refers to training and learning activities that enable users to improve their own skills and knowledge.

[0073] "Consumer attribute information" refers to the individual characteristics and profiles of a hypothetical customer, such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0074] A "sales plan" is a scenario that defines how products and services will be introduced to a hypothetical customer, as well as the content of that introduction.

[0075] "Dynamic adjustment" means changing and optimizing the next scenario and training content in real time or semi-automatically based on the user's training progress and response results.

[0076] "Feedback" refers to the evaluations and advice that users receive after interacting with virtual customers, pointing out specific areas for improvement and successes achieved.

[0077] To implement this invention, a server is required as a data processing device. The server generates virtual customers using a generative AI model and sets the attribute information of those customers. This AI model is designed to randomly and rationally determine attributes such as the consumer's age, gender, occupation, hobbies, purchasing motivation, and budget.

[0078] Next, the server creates a sales plan based on the configured attribute information. This plan includes product information that matches consumer needs, which the server retrieves from the product database. The generated plan is provided to the user via a terminal. The terminal has a visual interface through which the user can review the sales scenario and simulate interactions with virtual customers.

[0079] The user operates the terminal to communicate with a virtual customer based on the presented sales plan. The user's responses, entered as text or voice, are recorded on the terminal and sent to the server in real time. The server uses an AI algorithm to analyze these responses and evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback, which includes specific advice on what went well and what needs improvement, is presented to the user through the terminal.

[0080] Furthermore, the server tracks the user's training progress and dynamically adjusts the next sales plan as needed. This adjustment makes it possible to provide different levels of training content tailored to the user's proficiency.

[0081] As a concrete example, a scenario is presented in which the user, as a new sales representative, proposes a new mobile phone plan to a virtual customer with young children. A possible response from the user might be, for example, "This plan has family benefits, a large data allowance, and is ideal for families looking to keep costs down." Based on this response, the server generates appropriate feedback.

[0082] An example of a prompt might be: "What plan would you recommend to a 30-year-old woman who is a teacher, enjoys reading and traveling, and is looking for a new mobile phone plan within the budget of a family of four?" In this way, users can improve their sales skills in real time.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server generates virtual customers using an AI model at system startup. The input at this stage consists of basic demographic information and market research data. The AI ​​model analyzes this data and outputs customer personas with randomly and rationally combined attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0086] Step 2:

[0087] The server automatically builds a sales plan based on the customer persona generated in Step 1. The inputs are the customer persona and the product catalog database. The server references these and outputs product information best suited to the needs of the virtual customer. This sales plan includes recommended products, benefits, and pricing information.

[0088] Step 3:

[0089] The terminal visually presents the sales plan output from the server to the user. The input is sales plan data from the server, which the terminal displays on a GUI (Graphical User Interface), allowing the user to access it.

[0090] Step 4:

[0091] The user operates the terminal to simulate a conversation with a virtual customer based on the presented sales plan. This step allows for input via text or voice. The user's responses are recorded on the terminal as suggestions or questions to the virtual customer.

[0092] Step 5:

[0093] The terminal records the user's response and sends that data to the server. The input from the terminal is the user's response data, which is then quickly transmitted to the server.

[0094] Step 6:

[0095] The server analyzes the received user response data using an AI algorithm to evaluate the user's performance. The input is the user's response data, and the analysis results output an evaluation of the appropriateness of the suggestions and communication skills.

[0096] Step 7:

[0097] The server generates immediate feedback based on the analysis results and presents it to the user via the terminal. This feedback includes specific advice on successes and areas for improvement. The input is the analysis results, and the feedback message is output.

[0098] Step 8:

[0099] The server tracks the user's overall training progress and dynamically adjusts the next training plan as needed. The input is the user's historical performance data, which is used to output the difficulty and content of the next scenario. This adjustment provides training optimized for each individual user.

[0100] (Application Example 1)

[0101] 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."

[0102] There is a need to provide efficient and personalized training for personnel in online environments, particularly in customer service. Customer support staff on e-commerce sites, in particular, need to acquire the skills to respond quickly and appropriately to diverse customer needs, but traditional training methods have struggled to effectively achieve this.

[0103] 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.

[0104] In this invention, the server includes means for randomly setting person attribute data for the purpose of training the user, means for constructing a sales procedure based on the set person attribute data, and means for presenting the constructed procedure to the user and recording the user's response. This allows the user to train practical customer service skills in individual virtual scenarios and efficiently improve their skills through immediate feedback.

[0105] A "user" is a person who uses the system to receive training.

[0106] "Personal attribute data" refers to data that randomly assigns characteristics such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0107] A "sales procedure" is a sales scenario built based on the attribute data of a virtual customer.

[0108] "Feedback" refers to advice generated by the AI ​​based on user responses, which evaluates the training results and provides suggestions for improvement.

[0109] "Dynamic adjustment" means automatically changing the content and difficulty level of the scenarios provided based on the user's training progress and proficiency.

[0110] "Immediate feedback" refers to evaluation and guidance given immediately after a user interaction.

[0111] "Proficiency level" refers to the degree of knowledge and skills acquired by a user through training.

[0112] The system implementing this invention primarily consists of a server, a terminal, and a user. The server generates virtual customers using an AI engine. These virtual customers have random attribute data, such as age, gender, occupation, hobbies, purchasing motivation, and budget. Based on this attribute data, a sales procedure is dynamically constructed. For this construction, AI models such as "GPT-4®" and "BERT" are used.

[0113] The terminal presents the user with a pre-defined sales procedure and provides an interface for the user to respond. This response can be text or voice input, which the terminal records and sends to the server. Machine learning libraries such as "TENSORFLOW®" or "PyTorch" are used for reactions and evaluation. The server analyzes the user's responses and generates immediate feedback. This feedback includes specific areas for improvement and effective response methods, which the terminal presents to the user.

[0114] As a concrete example, consider a scenario where a new customer support staff member simulates how to handle a customer inquiry about a recent order not arriving. The server generates a virtual customer and provides a scenario for rehearsing the appropriate response.

[0115] A concrete example of a prompt message is: "You are a support staff member for a new e-commerce site. How would you appropriately respond to a customer inquiry? Imagine a scenario where the customer placed an online order, but it has not arrived."

[0116] This allows users to gain practical experience while honing their customer service skills quickly and effectively.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server uses an AI engine to generate virtual customers. First, attribute data (age, gender, occupation, hobbies, purchasing motivation, and budget) is set. This data is generated randomly but is made reasonable based on specific parameters. The output is the attribute data of the virtual customer.

[0120] Step 2:

[0121] The server constructs a sales procedure based on the attribute data of a virtual customer. It references a product catalog database and selects the product information that best matches the virtual customer's attributes. The sales procedure is generated using either the AI ​​model "GPT-4" or "BERT". The output is the constructed sales procedure.

[0122] Step 3:

[0123] The terminal presents the user with a pre-defined sales procedure. The user inputs responses based on this procedure through the terminal's interface. Input can be text or voice. Output is the user's response data.

[0124] Step 4:

[0125] The server analyzes the user's response and generates feedback using AI. The user's response is compared against the sales procedure described earlier, and its appropriateness and areas for improvement are evaluated. TensorFlow or PyTorch is used for the analysis. The output is feedback data.

[0126] Step 5:

[0127] The device presents the generated feedback to the user. The feedback specifically highlights successes and areas for improvement. This allows the user to gain concrete methods for improving their skills. The output is the user's learning behavior based on the feedback.

[0128] Step 6:

[0129] The server records the user's progress and dynamically adjusts the next sales procedure. It automatically changes the content and difficulty of the next training session based on the user's proficiency. This ensures that training is always optimized for the user. The output is the adjusted next sales procedure.

[0130] 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.

[0131] The present invention is implemented by combining an emotion engine with a system in which a server, which is an information processing device, generates virtual customers and provides sales scenarios for the purpose of training users.

[0132] The system begins with the server using AI technology to generate a virtual customer persona to present to the user. This persona includes attributes such as age, occupation, and hobbies. After generation, the server constructs a sales scenario based on the persona. This scenario selects products and services from a product catalog that match the virtual customer's needs and includes them as a sales proposal.

[0133] The user is presented with a scenario via their device, and interacts with a virtual customer within the simulated environment. During the interaction, the device uses an emotion engine to recognize the user's emotional state. This engine uses facial recognition and voice tone analysis to evaluate changes in emotion in real time.

[0134] User responses are recorded on the device and sent to the server. The server analyzes the responses, taking into account the user's emotional state, and generates feedback. This feedback includes an approach based not only on the user's technical skills but also on their emotional responses, providing more personalized advice.

[0135] For example, if the emotion engine determines that a user is frustrated, it can provide feedback suggesting simpler and more persuasive sales techniques or a calmer dialogue approach.

[0136] Furthermore, the server has the ability to dynamically adjust the next scenario as the user's training progresses, and can change the difficulty and type of scenario according to the user's emotional state. This process allows the user to have a more enriching learning experience and maximizes the effectiveness of the training.

[0137] Thus, the information processing device incorporating the emotion engine according to the present invention can be applied to support the improvement of user skills and to provide more advanced educational programs by taking into account emotional adaptation.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server starts the program and prepares the AI ​​engine and emotion engine. At this stage, templates for customer persona generation and the product database are loaded.

[0141] Step 2:

[0142] The server uses AI technology to generate random customer personas. These customer personas are assigned attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0143] Step 3:

[0144] The server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario includes product information that matches the needs of the virtual customer.

[0145] Step 4:

[0146] The terminal displays the proposed sales scenario to the user and prompts the user to start the simulation.

[0147] Step 5:

[0148] Users initiate conversations with virtual customers based on scenarios and make sales proposals. Input can be via text or voice.

[0149] Step 6:

[0150] The device analyzes the user's voice and video in real time and uses an emotion engine to recognize the user's emotional state. This information captures the user's reactions and emotional changes and is sent to the server as data.

[0151] Step 7:

[0152] The server comprehensively analyzes the user's response data and emotional state. Using AI algorithms, not only the accuracy of the user's responses but also their emotional appropriateness is evaluated.

[0153] Step 8:

[0154] Based on the evaluation results, the server generates personalized feedback and adjusts the advice based on the user's emotional state.

[0155] Step 9:

[0156] The device provides the user with the generated feedback, explaining in detail areas for improvement and challenges that need to be addressed.

[0157] Step 10:

[0158] The server tracks the user's training progress and adjusts the next scenario based on the user's proficiency and emotional responses. In this way, an effective training experience that also takes emotional aspects into account is achieved.

[0159] (Example 2)

[0160] 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".

[0161] Traditional training systems have faced the challenge of providing an interactive learning environment that takes into account the user's emotional state. As a result, there were concerns that effective feedback tailored to each user's emotions was not provided, leading to limited learning outcomes. Furthermore, training programs were fixed and could not be flexibly adjusted to the user's progress or emotional changes.

[0162] 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.

[0163] In this invention, the server includes means for automatically setting agent characteristic data for the purpose of improving the user's skills, means for analyzing the user's facial expressions and voice to recognize their emotional state, and means for generating feedback that takes the recognized emotional state into consideration. This provides an interactive and personalized learning environment that responds to the user's emotional state, enabling effective feedback and flexible training adjustments.

[0164] A "virtual agent" is a fictional digital character created using AI technology, possessing specific characteristics such as age, occupation, and hobbies.

[0165] A "data processing device" is a computer system for processing information, and includes hardware such as servers and terminals, as well as corresponding software.

[0166] A "user" refers to an individual who operates this system and improves their skills through interaction with virtual agents.

[0167] "Feature data" refers to the data that makes up the attributes and profile of a virtual agent, including information such as age, occupation, and hobbies.

[0168] The "sales process" refers to a series of scenarios that constitute the activities of proposing products and services optimized based on the needs of the virtual agent.

[0169] "Facial expression and voice analysis" is the process of collecting and analyzing data using cameras and microphones in order to recognize the user's emotional state in real time.

[0170] "Feedback" refers to interaction products that include suggestions for improvement and advice for the next steps, generated based on the user's responses and emotional state.

[0171] "Learning progress" is an indicator that shows the degree to which users have improved their skills through this system.

[0172] "Dynamic adjustment" refers to a function that automatically changes the content and difficulty level of a scenario according to the user's emotional state and learning progress.

[0173] This invention relates to a system that uses a data processing device to provide users with an interactive and emotion-based learning environment. This system is primarily realized through the interaction between a server, a terminal, and the user.

[0174] First, the server generates a virtual agent using a generative AI model. This agent has characteristic data such as age, occupation, and hobbies. The generative AI model uses prompts aimed at improving the user's skills to concretize the characteristic data. An example of this is, "Think of a way to explain a new travel gadget that might interest a 30-year-old digital marketing professional who loves to travel."

[0175] Next, the server presents the sales process to the user's terminal. This process involves the server selecting products and services from a product catalog that match the virtual agent's needs and outlining how to approach the user. The terminal plays the role of interactively presenting this process to the user.

[0176] The device uses an emotion engine to analyze the user's facial expressions and voice in real time and collect emotional data. This is done using facial recognition technology and voice analysis software. Based on these analysis results, the user's emotional state is fed back to the server. The feedback is automatically generated based on the user's responses and emotional state and includes suggestions for improvement and advice for the next steps.

[0177] For example, if a user is feeling stressed during a negotiation, the device recognizes that emotion, and the server suggests a calmer explanation. This emotion-based feedback allows the user to acquire effective communication skills.

[0178] Furthermore, the server monitors the user's learning progress and dynamically adjusts the next process and scenario. This includes adaptive scenario changes based on the user's emotional state and past responses. In this way, the system always provides learning content that is appropriate for the user, supporting efficient skill acquisition.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] The server uses prompt statements as input to generate an AI model, which then generates feature data for a virtual agent. Using the prompt statement "Think of a way to describe a new travel gadget that might interest a 30-year-old travel-loving digital marketing professional" as input, the server outputs an agent with specific characteristics such as age, occupation, and hobbies.

[0182] Step 2:

[0183] Based on the generated virtual agent's characteristic data, the server selects products and services from the product catalog that match the agent's needs and builds a sales process. In this step, the characteristic data is the input, and a process including the selected products and services is output.

[0184] Step 3:

[0185] The server transmits the constructed sales process to the terminal, which then presents it to the user. The sales process serves as input, and the output is an interactive scenario available to the user. The terminal communicates the scenario to the user through visual and auditory information.

[0186] Step 4:

[0187] The user interacts with a virtual agent based on the presented scenario. The user's responses and selections become input and are collected as data on the device.

[0188] Step 5:

[0189] The device uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. In this step, the user's facial expression and voice data are used as input, and their emotional state is output in real time.

[0190] Step 6:

[0191] The terminal sends user response data and emotional state to the server. The analysis results are used as input, and the data transmission to the server is output.

[0192] Step 7:

[0193] The server analyzes the received response data and emotional state, and generates feedback that takes the recognized emotions into account. The input consists of the user's response data and emotional data, and the output is personalized feedback.

[0194] Step 8:

[0195] The server dynamically adjusts the next sales process and scenario based on the user's learning progress. Progress data is used as input, and the newly adjusted sales process and scenario are output. This provides the user with an optimal learning experience.

[0196] (Application Example 2)

[0197] 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".

[0198] Traditional training systems using virtual customers focus on improving users' technical skills but lack support for improving interactions based on users' emotional states. Therefore, we aim to improve sales techniques more effectively and enhance the quality of customer service by utilizing real-time emotion recognition for feedback.

[0199] 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.

[0200] In this invention, the server includes means for randomly setting buyer attribute data for the purpose of training users, means for constructing a sales plan based on the set buyer attribute data, and means for analyzing the user's facial expressions or voice using a visual device worn by the user and improving the sales method based on changes in emotion. This makes it possible to recognize the user's emotional state in real time and provide personalized feedback.

[0201] A "virtual buyer" is a simulated buyer created for the purpose of interacting with the user, and is a person with attribute data such as age, occupation, and hobbies.

[0202] An "information processing system" is a collection of computers and associated software that enables the generation, analysis, and feedback of data.

[0203] A "user" is an individual who receives training using this system and aims to improve their skills through interaction with virtual buyers.

[0204] "Attribute data" refers to information related to a hypothetical buyer, and is a general term for data including age, occupation, hobbies, etc.

[0205] A "sales plan" is a scenario that includes the products and services offered to a hypothetical buyer, and is a proposal system built based on the customer's needs and attributes.

[0206] A "visual device" is a device that, when worn by a user, presents information visually in real time or performs emotional analysis, and includes smart glasses.

[0207] "Emotional changes" refer to fluctuations in the user's facial expressions and tone of voice during the interaction process, and are an important element indicating their emotional state.

[0208] "Feedback" is advice and suggestions for improvement generated based on user interaction and emotional state, and is a process that provides information to help users improve their skills more effectively.

[0209] In order to implement this invention, it is necessary to construct an information processing system that generates virtual buyers and improves the sales skills of users.

[0210] The server first uses AI technology to generate a virtual buyer persona. This persona includes attribute data such as age, occupation, and hobbies. The server then builds a sales plan based on the generated persona and presents it to the user's visual device. This visual device may include smart glasses or similar devices.

[0211] The device analyzes facial expressions and voice tone in real time from the user's visual device. This analysis uses an emotion analysis engine (e.g., Affectiva's Emotion AI), and based on the observed emotional changes, it can generate feedback to improve sales methods. The generated feedback helps improve sales techniques and the quality of customer service.

[0212] For example, if a store staff member is wearing smart glasses while selling a new product, and the emotion analysis engine determines that the customer's interest is waning, it can provide real-time feedback such as "further emphasize the product's key features."

[0213] An example of a prompt for a generative AI model would be: "Explain the appeal of the new product to the customer, analyze their facial expressions and tone of voice in real time to determine their emotions, and provide feedback with appropriate sales advice." This prompt is important for providing specific advice to the user through interaction analysis, including emotion analysis.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server uses a generative AI model to generate virtual customer personas. It receives attribute data such as the virtual customer's age, occupation, and hobbies as input, and generates personas based on this data. This data is randomly combined and output as a unique customer profile.

[0217] Step 2:

[0218] The server builds a sales plan based on the generated virtual buyer persona. It receives information about the products and services to be sold, as well as buyer attribute data, as input. The server selects the products and services best suited to the buyer's needs and outputs them as a sales plan.

[0219] Step 3:

[0220] The terminal presents the sales plan to the user through a visual device (e.g., smart glasses). The previously constructed sales plan is input as visual information and output in real time to the user's field of vision.

[0221] Step 4:

[0222] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone. It collects real-time facial and voice data from the user as input. The emotion analysis engine analyzes this data to determine the user's emotional state. The analysis results are then output.

[0223] Step 5:

[0224] The server generates suggestions for improving sales methods based on the analysis results and sends them to the terminal as feedback. It receives data on the user's emotional state as input and creates appropriate advice and suggestions for improving sales methods based on that data. This advice is output to the terminal and presented to the user.

[0225] Step 6:

[0226] The user receives feedback from smart glasses and improves their skills through interaction with a virtual buyer. In this step, the user tries out sales techniques based on the feedback received and inputs the results back into the device. Subsequent interactions lead to further analysis of the emotional state and feedback.

[0227] 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.

[0228] Data generation model 58 is a type of 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.

[0229] 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.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] 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.

[0233] 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).

[0234] 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.

[0235] 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.

[0236] 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).

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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".

[0243] To implement the present invention, a server as an information processing device, a terminal operated by the user, and a program that manages the entire process are used.

[0244] At system startup, the server first uses an AI engine to generate virtual customers. Customer personas are randomly and rationally generated by the server and include attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0245] Next, the server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario refers to the product catalog database and includes product information that matches the needs of the virtual customer.

[0246] The constructed scenario is presented to the user via the device. Based on this scenario, the user simulates interaction with a virtual customer. Interaction can be conducted via text input or voice input.

[0247] User responses are recorded on the device and sent to the server sequentially. The server analyzes this response data and uses AI algorithms to evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback includes specific advice on what went well and what needs improvement, and is presented to the user through the device.

[0248] Furthermore, the server tracks the user's overall training progress and dynamically adjusts the next scenario as needed. This adjustment is to provide training content of varying difficulty levels tailored to the user's proficiency.

[0249] For example, if the user is a new sales representative, they might be presented with a scenario in which they practice proposing a mobile phone plan to a customer with young children. The user's responses would then be given specific feedback on whether they considered the budget and whether they accurately understood the customer's needs.

[0250] This embodiment ensures training consistency and strengthens customer service skills through diverse scenarios, enabling new employees to become productive quickly and improving the efficiency of their training.

[0251] The following describes the processing flow.

[0252] Step 1:

[0253] The server starts the system and loads the necessary information from the AI ​​engine and database. This information includes customer attribute templates and product catalogs.

[0254] Step 2:

[0255] The server generates random customer personas based on customer attribute templates. These personas are assigned attributes such as age, gender, occupation, hobbies, purchase motivation, and budget.

[0256] Step 3:

[0257] The server builds the optimal sales scenario based on the generated customer persona. In this process, product information that matches the customer persona's needs is selected from the product catalog.

[0258] Step 4:

[0259] The terminal displays the sales scenario and customer persona information received from the server to the user on the screen.

[0260] Step 5:

[0261] Users interact with virtual customers based on presented scenarios and propose products and services. Users can respond via text or voice.

[0262] Step 6:

[0263] The device records user interaction data in real time and sends this data to the server sequentially.

[0264] Step 7:

[0265] The server analyzes the received interaction data and uses an AI algorithm to evaluate the user's response. Based on the accuracy and appropriateness of the response, it generates feedback.

[0266] Step 8:

[0267] The terminal displays feedback sent from the server to the user. This feedback includes specific improvement suggestions and assignments for the next training session.

[0268] Step 9:

[0269] The server logs user performance and tracks training progress. This allows the training content to be dynamically adjusted according to the user's proficiency level.

[0270] Step 10:

[0271] The user reviews the feedback and, if necessary, proceeds to the next scenario or ends the training. The system then initiates the next cycle based on the user's choice.

[0272] (Example 1)

[0273] 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."

[0274] In modern consumer service training, effectively learning within limited time and resources is a challenging task. Specifically, this involves practical dialogues based on diverse consumer scenarios and receiving immediate feedback based on the analysis of the results. However, traditional methods struggle to provide efficient training and generate appropriate feedback, thus creating a need for means to achieve rapid and effective skill improvement.

[0275] 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.

[0276] In this invention, the server includes means for predicting and setting consumer attribute information for the purpose of user education, means for creating a sales plan based on the set consumer attribute information, and means for dynamically adjusting the next plan according to the progress of user education. As a result, users can conduct practical training through various virtual customer scenarios and receive immediate feedback, thereby enabling them to improve their skills quickly and effectively.

[0277] A "virtual customer" is a fictional consumer model with consumer attribute information and behaviors, digitally generated for the purpose of consumer response training and simulation.

[0278] A "data processing device" is an electronic device or system for collecting, analyzing, and generating information.

[0279] A "user" refers to an individual or organization that conducts training or simulation using this system.

[0280] "Education" refers to training and learning activities for users to improve their skills and knowledge.

[0281] "Consumer attribute information" refers to individual characteristics and profiles that virtual customers are supposed to have, such as age, gender, occupation, hobbies, purchase motivation, budget, etc.

[0282] A "sales plan" refers to a scenario that defines the method of introducing products and services proposed to virtual customers and their content.

[0283] "Dynamically adjusting" means changing and optimizing the next scenario or training content in real-time or semi-automatically based on the training progress and response results of users.

[0284] "Feedback" refers to the evaluation and advice that users receive after interacting with virtual customers, and points out specific areas for improvement and achieved successes.

[0285] To implement the present invention, it is necessary to use a server as a data processing device. The server uses a generated AI model to generate virtual customers and set their attribute information. This AI model is for randomly and reasonably determining attributes such as the age, gender, occupation, hobbies, purchase motivation, and budget of consumers.

[0286] Next, the server creates a sales plan based on the set attribute information. This plan includes product information that matches the needs of consumers, and the server obtains it from the product database. The generated plan is provided to the user via the terminal. The terminal has a visual interface through which the user can check the sales scenario and simulate the interaction with the virtual customer.

[0287] The user operates the terminal to communicate with the virtual customer based on the presented sales plan. The user's responses entered in text or voice are recorded by the terminal and sequentially transmitted to the server. The server analyzes this response using an AI algorithm and evaluates the user's performance. Based on this evaluation, immediate feedback is generated. The feedback includes specific advice on which parts went well and what needs to be improved, and is presented to the user through the terminal.

[0288] Furthermore, the server tracks the user's training progress and dynamically adjusts the next sales plan as needed. This adjustment makes it possible to provide different levels of training content according to the user's proficiency.

[0289] As a specific example, when the user is a new salesperson, a scenario of proposing a new mobile phone plan to a virtual customer with children is presented. The user's response to this could be, for example, "This plan has benefits for families, has a large data capacity, and is optimal for families who want to keep costs down." Based on this response, the server generates appropriate feedback.

[0290] An example of a prompt might be: "What plan would you recommend to a 30-year-old woman who is a teacher, enjoys reading and traveling, and is looking for a new mobile phone plan within the budget of a family of four?" In this way, users can improve their sales skills in real time.

[0291] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0292] Step 1:

[0293] The server generates virtual customers using an AI model at system startup. The input at this stage consists of basic demographic information and market research data. The AI ​​model analyzes this data and outputs customer personas with randomly and rationally combined attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0294] Step 2:

[0295] The server automatically builds a sales plan based on the customer persona generated in Step 1. The inputs are the customer persona and the product catalog database. The server references these and outputs product information best suited to the needs of the virtual customer. This sales plan includes recommended products, benefits, and pricing information.

[0296] Step 3:

[0297] The terminal visually presents the sales plan output from the server to the user. The input is sales plan data from the server, which the terminal displays on a GUI (Graphical User Interface), allowing the user to access it.

[0298] Step 4:

[0299] The user operates the terminal to simulate a conversation with a virtual customer based on the presented sales plan. In this step, text or voice input is possible. The response as the user's input is recorded on the terminal as a proposal or question to the virtual customer.

[0300] Step 5:

[0301] The terminal records the response from the user and transmits the data to the server. The input of the terminal is the user's response data, which is quickly transmitted to the server.

[0302] Step 6:

[0303] The server analyzes the received user response data with an AI algorithm to evaluate the user's performance. The input is the user's response data, and as a result of the analysis, an evaluation of the appropriateness of the proposal and communication skills is output.

[0304] Step 7:

[0305] The server generates immediate feedback based on the analysis results and presents it to the user via the terminal. This feedback includes specific advice on points of success and areas for improvement. The input is the analysis results, and a feedback message is output. <00009志3>

[0306] Step 8:

[0307] The server tracks the overall training progress of the user and dynamically adjusts the next sales plan as needed. The input is the user's past performance data, and based on this, the difficulty level and content of the next scenario are output. This adjustment provides training optimized for individual users.

[0308] (Application Example 1) <俊72>

[0309] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0310] There is a need to provide efficient and personalized training for personnel in online environments, particularly in customer service. Customer support staff on e-commerce sites, in particular, need to acquire the skills to respond quickly and appropriately to diverse customer needs, but traditional training methods have struggled to effectively achieve this.

[0311] 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.

[0312] In this invention, the server includes means for randomly setting person attribute data for the purpose of training the user, means for constructing a sales procedure based on the set person attribute data, and means for presenting the constructed procedure to the user and recording the user's response. This allows the user to train practical customer service skills in individual virtual scenarios and efficiently improve their skills through immediate feedback.

[0313] A "user" is a person who uses the system to receive training.

[0314] "Personal attribute data" refers to data that randomly assigns characteristics such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0315] A "sales procedure" is a sales scenario built based on the attribute data of a virtual customer.

[0316] "Feedback" refers to advice generated by the AI ​​based on user responses, which evaluates the training results and provides suggestions for improvement.

[0317] "Dynamic adjustment" means automatically changing the content and difficulty level of the scenarios provided based on the user's training progress and proficiency.

[0318] "Immediate feedback" refers to evaluation and guidance given immediately after a user interaction.

[0319] "Proficiency level" refers to the degree of knowledge and skills acquired by a user through training.

[0320] The system implementing this invention mainly consists of a server, a terminal, and a user. The server generates virtual customers using an AI engine. These virtual customers have random attribute data, such as age, gender, occupation, hobbies, purchasing motivation, and budget. Based on this attribute data, a sales procedure is dynamically constructed. For this construction, AI models such as "GPT-4" and "BERT" are used.

[0321] The terminal presents the user with a pre-defined sales procedure and provides an interface for the user to respond. This response can be text or voice input, which the terminal records and sends to the server. Machine learning libraries such as TensorFlow or PyTorch are used for reactions and evaluation. The server analyzes the user's responses and generates immediate feedback. This feedback includes specific areas for improvement and effective response methods, which the terminal presents to the user.

[0322] As a concrete example, consider a scenario where a new customer support staff member simulates how to handle a customer inquiry about a recent order not arriving. The server generates a virtual customer and provides a scenario for rehearsing the appropriate response.

[0323] A concrete example of a prompt message is: "You are a support staff member for a new e-commerce site. How would you appropriately respond to a customer inquiry? Imagine a scenario where the customer placed an online order, but it has not arrived."

[0324] This allows users to gain practical experience while honing their customer service skills quickly and effectively.

[0325] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0326] Step 1:

[0327] The server uses an AI engine to generate virtual customers. First, attribute data (age, gender, occupation, hobbies, purchasing motivation, and budget) is set. This data is generated randomly but is made reasonable based on specific parameters. The output is the attribute data of the virtual customer.

[0328] Step 2:

[0329] The server constructs a sales procedure based on the attribute data of a virtual customer. It references a product catalog database and selects the product information that best matches the virtual customer's attributes. The sales procedure is generated using either the AI ​​model "GPT-4" or "BERT". The output is the constructed sales procedure.

[0330] Step 3:

[0331] The terminal presents the user with a pre-defined sales procedure. The user inputs responses based on this procedure through the terminal's interface. Input can be text or voice. Output is the user's response data.

[0332] Step 4:

[0333] The server analyzes the user's response and generates feedback using AI. The user's response is compared against the sales procedure described earlier, and its appropriateness and areas for improvement are evaluated. TensorFlow or PyTorch is used for the analysis. The output is feedback data.

[0334] Step 5:

[0335] The device presents the generated feedback to the user. The feedback specifically highlights successes and areas for improvement. This allows the user to gain concrete methods for improving their skills. The output is the user's learning behavior based on the feedback.

[0336] Step 6:

[0337] The server records the user's progress and dynamically adjusts the next sales procedure. It automatically changes the content and difficulty of the next training session based on the user's proficiency. This ensures that training is always optimized for the user. The output is the adjusted next sales procedure.

[0338] 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.

[0339] The present invention is implemented by combining an emotion engine with a system in which a server, which is an information processing device, generates virtual customers and provides sales scenarios for the purpose of training users.

[0340] The system begins with the server using AI technology to generate a virtual customer persona to present to the user. This persona includes attributes such as age, occupation, and hobbies. After generation, the server constructs a sales scenario based on the persona. This scenario selects products and services from a product catalog that match the virtual customer's needs and includes them as a sales proposal.

[0341] The user is presented with a scenario via their device, and interacts with a virtual customer within the simulated environment. During the interaction, the device uses an emotion engine to recognize the user's emotional state. This engine uses facial recognition and voice tone analysis to evaluate changes in emotion in real time.

[0342] User responses are recorded on the device and sent to the server. The server analyzes the responses, taking into account the user's emotional state, and generates feedback. This feedback includes an approach based not only on the user's technical skills but also on their emotional responses, providing more personalized advice.

[0343] For example, if the emotion engine determines that a user is frustrated, it can provide feedback suggesting simpler and more persuasive sales techniques or a calmer dialogue approach.

[0344] Furthermore, the server has the ability to dynamically adjust the next scenario as the user's training progresses, and can change the difficulty and type of scenario according to the user's emotional state. This process allows the user to have a more enriching learning experience and maximizes the effectiveness of the training.

[0345] Thus, the information processing device incorporating the emotion engine according to the present invention can be applied to support the improvement of user skills and to provide more advanced educational programs by taking into account emotional adaptation.

[0346] The following describes the processing flow.

[0347] Step 1:

[0348] The server starts the program and prepares the AI ​​engine and emotion engine. At this stage, templates for customer persona generation and the product database are loaded.

[0349] Step 2:

[0350] The server uses AI technology to generate random customer personas. These customer personas are assigned attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0351] Step 3:

[0352] The server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario includes product information that matches the needs of the virtual customer.

[0353] Step 4:

[0354] The terminal displays the proposed sales scenario to the user and prompts the user to start the simulation.

[0355] Step 5:

[0356] Users initiate conversations with virtual customers based on scenarios and make sales proposals. Input can be via text or voice.

[0357] Step 6:

[0358] The device analyzes the user's voice and video in real time and uses an emotion engine to recognize the user's emotional state. This information captures the user's reactions and emotional changes and is sent to the server as data.

[0359] Step 7:

[0360] The server comprehensively analyzes the user's response data and emotional state. Using AI algorithms, not only the accuracy of the user's responses but also their emotional appropriateness is evaluated.

[0361] Step 8:

[0362] Based on the evaluation results, the server generates personalized feedback and adjusts the advice based on the user's emotional state.

[0363] Step 9:

[0364] The device provides the user with the generated feedback, explaining in detail areas for improvement and challenges that need to be addressed.

[0365] Step 10:

[0366] The server tracks the user's training progress and adjusts the next scenario based on the user's proficiency and emotional responses. In this way, an effective training experience that also takes emotional aspects into account is achieved.

[0367] (Example 2)

[0368] 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".

[0369] Traditional training systems have faced the challenge of providing an interactive learning environment that takes into account the user's emotional state. As a result, there were concerns that effective feedback tailored to each user's emotions was not provided, leading to limited learning outcomes. Furthermore, training programs were fixed and could not be flexibly adjusted to the user's progress or emotional changes.

[0370] 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.

[0371] In this invention, the server includes means for automatically setting agent characteristic data for the purpose of improving the user's skills, means for analyzing the user's facial expressions and voice to recognize their emotional state, and means for generating feedback that takes the recognized emotional state into consideration. This provides an interactive and personalized learning environment that responds to the user's emotional state, enabling effective feedback and flexible training adjustments.

[0372] A "virtual agent" is a fictional digital character created using AI technology, possessing specific characteristics such as age, occupation, and hobbies.

[0373] A "data processing device" is a computer system for processing information, and includes hardware such as servers and terminals, as well as corresponding software.

[0374] A "user" refers to an individual who operates this system and improves their skills through interaction with virtual agents.

[0375] "Feature data" refers to the data that makes up the attributes and profile of a virtual agent, including information such as age, occupation, and hobbies.

[0376] The "sales process" refers to a series of scenarios that constitute the activities of proposing products and services optimized based on the needs of the virtual agent.

[0377] "Facial expression and voice analysis" is the process of collecting and analyzing data using cameras and microphones in order to recognize the user's emotional state in real time.

[0378] "Feedback" refers to interaction products that include suggestions for improvement and advice for the next steps, generated based on the user's responses and emotional state.

[0379] "Learning progress" is an indicator that shows the degree to which users have improved their skills through this system.

[0380] "Dynamic adjustment" refers to a function that automatically changes the content and difficulty level of a scenario according to the user's emotional state and learning progress.

[0381] This invention relates to a system that uses a data processing device to provide users with an interactive and emotion-based learning environment. This system is primarily realized through the interaction between a server, a terminal, and the user.

[0382] First, the server generates a virtual agent using a generative AI model. This agent has characteristic data such as age, occupation, and hobbies. The generative AI model uses prompts aimed at improving the user's skills to concretize the characteristic data. An example of this is, "Think of a way to explain a new travel gadget that might interest a 30-year-old digital marketing professional who loves to travel."

[0383] Next, the server presents the sales process to the user's terminal. This process involves the server selecting products and services from a product catalog that match the virtual agent's needs and outlining how to approach the user. The terminal plays the role of interactively presenting this process to the user.

[0384] The device uses an emotion engine to analyze the user's facial expressions and voice in real time and collect emotional data. This is done using facial recognition technology and voice analysis software. Based on these analysis results, the user's emotional state is fed back to the server. The feedback is automatically generated based on the user's responses and emotional state and includes suggestions for improvement and advice for the next steps.

[0385] For example, if a user is feeling stressed during a negotiation, the device recognizes that emotion, and the server suggests a calmer explanation. This emotion-based feedback allows the user to acquire effective communication skills.

[0386] Furthermore, the server monitors the user's learning progress and dynamically adjusts the next process and scenario. This includes adaptive scenario changes based on the user's emotional state and past responses. In this way, the system always provides learning content that is appropriate for the user, supporting efficient skill acquisition.

[0387] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0388] Step 1:

[0389] The server uses prompt statements as input to generate an AI model, which then generates feature data for a virtual agent. Using the prompt statement "Think of a way to describe a new travel gadget that might interest a 30-year-old travel-loving digital marketing professional" as input, the server outputs an agent with specific characteristics such as age, occupation, and hobbies.

[0390] Step 2:

[0391] Based on the generated virtual agent's characteristic data, the server selects products and services from the product catalog that match the agent's needs and builds a sales process. In this step, the characteristic data is the input, and a process including the selected products and services is output.

[0392] Step 3:

[0393] The server transmits the constructed sales process to the terminal, which then presents it to the user. The sales process serves as input, and the output is an interactive scenario available to the user. The terminal communicates the scenario to the user through visual and auditory information.

[0394] Step 4:

[0395] The user interacts with a virtual agent based on the presented scenario. The user's responses and selections become input and are collected as data on the device.

[0396] Step 5:

[0397] The device uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. In this step, the user's facial expression and voice data are used as input, and their emotional state is output in real time.

[0398] Step 6:

[0399] The terminal sends user response data and emotional state to the server. The analysis results are used as input, and the data transmission to the server is output.

[0400] Step 7:

[0401] The server analyzes the received response data and emotional state, and generates feedback that takes the recognized emotions into account. The input consists of the user's response data and emotional data, and the output is personalized feedback.

[0402] Step 8:

[0403] The server dynamically adjusts the next sales process and scenario based on the user's learning progress. Progress data is used as input, and the newly adjusted sales process and scenario are output. This provides the user with an optimal learning experience.

[0404] (Application Example 2)

[0405] 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."

[0406] Traditional training systems using virtual customers focus on improving users' technical skills but lack support for improving interactions based on users' emotional states. Therefore, we aim to improve sales techniques more effectively and enhance the quality of customer service by utilizing real-time emotion recognition for feedback.

[0407] 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.

[0408] In this invention, the server includes means for randomly setting buyer attribute data for the purpose of training users, means for constructing a sales plan based on the set buyer attribute data, and means for analyzing the user's facial expressions or voice using a visual device worn by the user and improving the sales method based on changes in emotion. This makes it possible to recognize the user's emotional state in real time and provide personalized feedback.

[0409] A "virtual buyer" is a simulated buyer created for the purpose of interacting with the user, and is a person with attribute data such as age, occupation, and hobbies.

[0410] An "information processing system" is a collection of computers and associated software that enables the generation, analysis, and feedback of data.

[0411] A "user" is an individual who receives training using this system and aims to improve their skills through interaction with virtual buyers.

[0412] "Attribute data" refers to information related to a hypothetical buyer, and is a general term for data including age, occupation, hobbies, etc.

[0413] A "sales plan" is a scenario that includes the products and services offered to a hypothetical buyer, and is a proposal system built based on the customer's needs and attributes.

[0414] A "visual device" is a device that, when worn by a user, presents information visually in real time or performs emotional analysis, and includes smart glasses.

[0415] "Emotional changes" refer to fluctuations in the user's facial expressions and tone of voice during the interaction process, and are an important element indicating their emotional state.

[0416] "Feedback" is advice and suggestions for improvement generated based on user interaction and emotional state, and is a process that provides information to help users improve their skills more effectively.

[0417] In order to implement this invention, it is necessary to construct an information processing system that generates virtual buyers and improves the sales skills of users.

[0418] The server first uses AI technology to generate a virtual buyer persona. This persona includes attribute data such as age, occupation, and hobbies. The server then builds a sales plan based on the generated persona and presents it to the user's visual device. This visual device may include smart glasses or similar devices.

[0419] The device analyzes facial expressions and voice tone in real time from the user's visual device. This analysis uses an emotion analysis engine (e.g., Affectiva's Emotion AI), and based on the observed emotional changes, it can generate feedback to improve sales methods. The generated feedback helps improve sales techniques and the quality of customer service.

[0420] For example, if a store staff member is wearing smart glasses while selling a new product, and the emotion analysis engine determines that the customer's interest is waning, it can provide real-time feedback such as "further emphasize the product's key features."

[0421] An example of a prompt for a generative AI model would be: "Explain the appeal of the new product to the customer, analyze their facial expressions and tone of voice in real time to determine their emotions, and provide feedback with appropriate sales advice." This prompt is important for providing specific advice to the user through interaction analysis, including emotion analysis.

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The server uses a generative AI model to generate virtual customer personas. It receives attribute data such as the virtual customer's age, occupation, and hobbies as input, and generates personas based on this data. This data is randomly combined and output as a unique customer profile.

[0425] Step 2:

[0426] The server builds a sales plan based on the generated virtual buyer persona. It receives information about the products and services to be sold, as well as buyer attribute data, as input. The server selects the products and services best suited to the buyer's needs and outputs them as a sales plan.

[0427] Step 3:

[0428] The terminal presents the sales plan to the user through a visual device (e.g., smart glasses). The previously constructed sales plan is input as visual information and output in real time to the user's field of vision.

[0429] Step 4:

[0430] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone. It collects real-time facial and voice data from the user as input. The emotion analysis engine analyzes this data to determine the user's emotional state. The analysis results are then output.

[0431] Step 5:

[0432] The server generates suggestions for improving sales methods based on the analysis results and sends them to the terminal as feedback. It receives data on the user's emotional state as input and creates appropriate advice and suggestions for improving sales methods based on that data. This advice is output to the terminal and presented to the user.

[0433] Step 6:

[0434] The user receives feedback from smart glasses and improves their skills through interaction with a virtual buyer. In this step, the user tries out sales techniques based on the feedback received and inputs the results back into the device. Subsequent interactions lead to further analysis of the emotional state and feedback.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] [Third Embodiment]

[0439] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0440] 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.

[0441] 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).

[0442] 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.

[0443] 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.

[0444] 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).

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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".

[0451] To implement the present invention, a server as an information processing device, a terminal operated by the user, and a program that manages the entire process are used.

[0452] At system startup, the server first uses an AI engine to generate virtual customers. Customer personas are randomly and rationally generated by the server and include attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0453] Next, the server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario refers to the product catalog database and includes product information that matches the needs of the virtual customer.

[0454] The constructed scenario is presented to the user via the device. Based on this scenario, the user simulates interaction with a virtual customer. Interaction can be conducted via text input or voice input.

[0455] User responses are recorded on the device and sent to the server sequentially. The server analyzes this response data and uses AI algorithms to evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback includes specific advice on what went well and what needs improvement, and is presented to the user through the device.

[0456] Furthermore, the server tracks the user's overall training progress and dynamically adjusts the next scenario as needed. This adjustment is to provide training content of varying difficulty levels tailored to the user's proficiency.

[0457] For example, if the user is a new sales representative, they might be presented with a scenario in which they practice proposing a mobile phone plan to a customer with young children. The user's responses would then be given specific feedback on whether they considered the budget and whether they accurately understood the customer's needs.

[0458] This embodiment ensures training consistency and strengthens customer service skills through diverse scenarios, enabling new employees to become productive quickly and improving the efficiency of their training.

[0459] The following describes the processing flow.

[0460] Step 1:

[0461] The server starts the system and loads the necessary information from the AI ​​engine and database. This information includes customer attribute templates and product catalogs.

[0462] Step 2:

[0463] The server generates random customer personas based on customer attribute templates. These personas are assigned attributes such as age, gender, occupation, hobbies, purchase motivation, and budget.

[0464] Step 3:

[0465] The server builds the optimal sales scenario based on the generated customer persona. In this process, product information that matches the customer persona's needs is selected from the product catalog.

[0466] Step 4:

[0467] The terminal displays the sales scenario and customer persona information received from the server to the user on the screen.

[0468] Step 5:

[0469] Users interact with virtual customers based on presented scenarios and propose products and services. Users can respond via text or voice.

[0470] Step 6:

[0471] The device records user interaction data in real time and sends this data to the server sequentially.

[0472] Step 7:

[0473] The server analyzes the received interaction data and uses an AI algorithm to evaluate the user's response. Based on the accuracy and appropriateness of the response, it generates feedback.

[0474] Step 8:

[0475] The terminal displays feedback sent from the server to the user. This feedback includes specific improvement suggestions and assignments for the next training session.

[0476] Step 9:

[0477] The server logs user performance and tracks training progress. This allows the training content to be dynamically adjusted according to the user's proficiency level.

[0478] Step 10:

[0479] The user reviews the feedback and, if necessary, proceeds to the next scenario or ends the training. The system then initiates the next cycle based on the user's choice.

[0480] (Example 1)

[0481] 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."

[0482] In modern consumer service training, effectively learning within limited time and resources is a challenging task. Specifically, this involves practical dialogues based on diverse consumer scenarios and receiving immediate feedback based on the analysis of the results. However, traditional methods struggle to provide efficient training and generate appropriate feedback, thus creating a need for means to achieve rapid and effective skill improvement.

[0483] 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.

[0484] In this invention, the server includes means for predicting and setting consumer attribute information for the purpose of user education, means for creating a sales plan based on the set consumer attribute information, and means for dynamically adjusting the next plan according to the user's education progress. This enables users to quickly and effectively improve their skills by undergoing practical training through various virtual customer scenarios and receiving immediate feedback.

[0485] A "virtual customer" is a fictional consumer model with consumer attribute information and behavior, digitally generated for the purpose of consumer response training and simulation.

[0486] A "data processing device" is an electronic device or system used for collecting, analyzing, and generating information.

[0487] "Users" refer to individuals or organizations that use this system for training or simulations.

[0488] "Education" refers to training and learning activities that enable users to improve their own skills and knowledge.

[0489] "Consumer attribute information" refers to the individual characteristics and profiles of a hypothetical customer, such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0490] A "sales plan" is a scenario that defines how products and services will be introduced to a hypothetical customer, as well as the content of that introduction.

[0491] "Dynamic adjustment" means changing and optimizing the next scenario and training content in real time or semi-automatically based on the user's training progress and response results.

[0492] "Feedback" refers to the evaluations and advice that users receive after interacting with virtual customers, pointing out specific areas for improvement and successes achieved.

[0493] To implement this invention, a server is required as a data processing device. The server generates virtual customers using a generative AI model and sets the attribute information of those customers. This AI model is designed to randomly and rationally determine attributes such as the consumer's age, gender, occupation, hobbies, purchasing motivation, and budget.

[0494] Next, the server creates a sales plan based on the configured attribute information. This plan includes product information that matches consumer needs, which the server retrieves from the product database. The generated plan is provided to the user via a terminal. The terminal has a visual interface through which the user can review the sales scenario and simulate interactions with virtual customers.

[0495] The user operates the terminal to communicate with a virtual customer based on the presented sales plan. The user's responses, entered as text or voice, are recorded on the terminal and sent to the server in real time. The server uses an AI algorithm to analyze these responses and evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback, which includes specific advice on what went well and what needs improvement, is presented to the user through the terminal.

[0496] Furthermore, the server tracks the user's training progress and dynamically adjusts the next sales plan as needed. This adjustment makes it possible to provide different levels of training content tailored to the user's proficiency.

[0497] As a concrete example, a scenario is presented in which the user, as a new sales representative, proposes a new mobile phone plan to a virtual customer with young children. A possible response from the user might be, for example, "This plan has family benefits, a large data allowance, and is ideal for families looking to keep costs down." Based on this response, the server generates appropriate feedback.

[0498] An example of a prompt might be: "What plan would you recommend to a 30-year-old woman who is a teacher, enjoys reading and traveling, and is looking for a new mobile phone plan within the budget of a family of four?" In this way, users can improve their sales skills in real time.

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

[0500] Step 1:

[0501] The server generates virtual customers using an AI model at system startup. The input at this stage consists of basic demographic information and market research data. The AI ​​model analyzes this data and outputs customer personas with randomly and rationally combined attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0502] Step 2:

[0503] The server automatically builds a sales plan based on the customer persona generated in Step 1. The inputs are the customer persona and the product catalog database. The server references these and outputs product information best suited to the needs of the virtual customer. This sales plan includes recommended products, benefits, and pricing information.

[0504] Step 3:

[0505] The terminal visually presents the sales plan output from the server to the user. The input is sales plan data from the server, which the terminal displays on a GUI (Graphical User Interface), allowing the user to access it.

[0506] Step 4:

[0507] The user operates the terminal to simulate a conversation with a virtual customer based on the presented sales plan. This step allows for input via text or voice. The user's responses are recorded on the terminal as suggestions or questions to the virtual customer.

[0508] Step 5:

[0509] The terminal records the user's response and sends that data to the server. The input from the terminal is the user's response data, which is then quickly transmitted to the server.

[0510] Step 6:

[0511] The server analyzes the received user response data using an AI algorithm to evaluate the user's performance. The input is the user's response data, and the analysis results output an evaluation of the appropriateness of the suggestions and communication skills.

[0512] Step 7:

[0513] The server generates immediate feedback based on the analysis results and presents it to the user via the terminal. This feedback includes specific advice on successes and areas for improvement. The input is the analysis results, and the feedback message is output.

[0514] Step 8:

[0515] The server tracks the user's overall training progress and dynamically adjusts the next training plan as needed. The input is the user's historical performance data, which is used to output the difficulty and content of the next scenario. This adjustment provides training optimized for each individual user.

[0516] (Application Example 1)

[0517] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0518] There is a need to provide efficient and personalized training for personnel in online environments, particularly in customer service. Customer support staff on e-commerce sites, in particular, need to acquire the skills to respond quickly and appropriately to diverse customer needs, but traditional training methods have struggled to effectively achieve this.

[0519] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0520] In this invention, the server includes means for randomly setting person attribute data for the purpose of training the user, means for constructing a sales procedure based on the set person attribute data, and means for presenting the constructed procedure to the user and recording the user's response. This allows the user to train practical customer service skills in individual virtual scenarios and efficiently improve their skills through immediate feedback.

[0521] A "user" is a person who uses the system to receive training.

[0522] "Personal attribute data" refers to data that randomly assigns characteristics such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0523] A "sales procedure" is a sales scenario built based on the attribute data of a virtual customer.

[0524] "Feedback" refers to advice generated by the AI ​​based on user responses, which evaluates the training results and provides suggestions for improvement.

[0525] "Dynamic adjustment" means automatically changing the content and difficulty level of the scenarios provided based on the user's training progress and proficiency.

[0526] "Immediate feedback" refers to evaluation and guidance given immediately after a user interaction.

[0527] "Proficiency level" refers to the degree of knowledge and skills acquired by a user through training.

[0528] The system implementing this invention mainly consists of a server, a terminal, and a user. The server generates virtual customers using an AI engine. These virtual customers have random attribute data, such as age, gender, occupation, hobbies, purchasing motivation, and budget. Based on this attribute data, a sales procedure is dynamically constructed. For this construction, AI models such as "GPT-4" and "BERT" are used.

[0529] The terminal presents the user with a pre-defined sales procedure and provides an interface for the user to respond. This response can be text or voice input, which the terminal records and sends to the server. Machine learning libraries such as TensorFlow or PyTorch are used for reactions and evaluation. The server analyzes the user's responses and generates immediate feedback. This feedback includes specific areas for improvement and effective response methods, which the terminal presents to the user.

[0530] As a concrete example, consider a scenario where a new customer support staff member simulates how to handle a customer inquiry about a recent order not arriving. The server generates a virtual customer and provides a scenario for rehearsing the appropriate response.

[0531] A concrete example of a prompt message is: "You are a support staff member for a new e-commerce site. How would you appropriately respond to a customer inquiry? Imagine a scenario where the customer placed an online order, but it has not arrived."

[0532] This allows users to gain practical experience while honing their customer service skills quickly and effectively.

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] The server uses an AI engine to generate virtual customers. First, attribute data (age, gender, occupation, hobbies, purchasing motivation, and budget) is set. This data is generated randomly but is made reasonable based on specific parameters. The output is the attribute data of the virtual customer.

[0536] Step 2:

[0537] The server constructs a sales procedure based on the attribute data of a virtual customer. It references a product catalog database and selects the product information that best matches the virtual customer's attributes. The sales procedure is generated using either the AI ​​model "GPT-4" or "BERT". The output is the constructed sales procedure.

[0538] Step 3:

[0539] The terminal presents the user with a pre-defined sales procedure. The user inputs responses based on this procedure through the terminal's interface. Input can be text or voice. Output is the user's response data.

[0540] Step 4:

[0541] The server analyzes the user's response and generates feedback using AI. The user's response is compared against the sales procedure described earlier, and its appropriateness and areas for improvement are evaluated. TensorFlow or PyTorch is used for the analysis. The output is feedback data.

[0542] Step 5:

[0543] The device presents the generated feedback to the user. The feedback specifically highlights successes and areas for improvement. This allows the user to gain concrete methods for improving their skills. The output is the user's learning behavior based on the feedback.

[0544] Step 6:

[0545] The server records the user's progress and dynamically adjusts the next sales procedure. It automatically changes the content and difficulty of the next training session based on the user's proficiency. This ensures that training is always optimized for the user. The output is the adjusted next sales procedure.

[0546] 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.

[0547] The present invention is implemented by combining an emotion engine with a system in which a server, which is an information processing device, generates virtual customers and provides sales scenarios for the purpose of training users.

[0548] The system begins with the server using AI technology to generate a virtual customer persona to present to the user. This persona includes attributes such as age, occupation, and hobbies. After generation, the server constructs a sales scenario based on the persona. This scenario selects products and services from a product catalog that match the virtual customer's needs and includes them as a sales proposal.

[0549] The user is presented with a scenario via their device, and interacts with a virtual customer within the simulated environment. During the interaction, the device uses an emotion engine to recognize the user's emotional state. This engine uses facial recognition and voice tone analysis to evaluate changes in emotion in real time.

[0550] User responses are recorded on the device and sent to the server. The server analyzes the responses, taking into account the user's emotional state, and generates feedback. This feedback includes an approach based not only on the user's technical skills but also on their emotional responses, providing more personalized advice.

[0551] For example, if the emotion engine determines that a user is frustrated, it can provide feedback suggesting simpler and more persuasive sales techniques or a calmer dialogue approach.

[0552] Furthermore, the server has the ability to dynamically adjust the next scenario as the user's training progresses, and can change the difficulty and type of scenario according to the user's emotional state. This process allows the user to have a more enriching learning experience and maximizes the effectiveness of the training.

[0553] Thus, the information processing device incorporating the emotion engine according to the present invention can be applied to support the improvement of user skills and to provide more advanced educational programs by taking into account emotional adaptation.

[0554] The following describes the processing flow.

[0555] Step 1:

[0556] The server starts the program and prepares the AI ​​engine and emotion engine. At this stage, templates for customer persona generation and the product database are loaded.

[0557] Step 2:

[0558] The server uses AI technology to generate random customer personas. These customer personas are assigned attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0559] Step 3:

[0560] The server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario includes product information that matches the needs of the virtual customer.

[0561] Step 4:

[0562] The terminal displays the proposed sales scenario to the user and prompts the user to start the simulation.

[0563] Step 5:

[0564] Users initiate conversations with virtual customers based on scenarios and make sales proposals. Input can be via text or voice.

[0565] Step 6:

[0566] The device analyzes the user's voice and video in real time and uses an emotion engine to recognize the user's emotional state. This information captures the user's reactions and emotional changes and is sent to the server as data.

[0567] Step 7:

[0568] The server comprehensively analyzes the user's response data and emotional state. Using AI algorithms, not only the accuracy of the user's responses but also their emotional appropriateness is evaluated.

[0569] Step 8:

[0570] Based on the evaluation results, the server generates personalized feedback and adjusts the advice based on the user's emotional state.

[0571] Step 9:

[0572] The device provides the user with the generated feedback, explaining in detail areas for improvement and challenges that need to be addressed.

[0573] Step 10:

[0574] The server tracks the user's training progress and adjusts the next scenario based on the user's proficiency and emotional responses. In this way, an effective training experience that also takes emotional aspects into account is achieved.

[0575] (Example 2)

[0576] 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."

[0577] Traditional training systems have faced the challenge of providing an interactive learning environment that takes into account the user's emotional state. As a result, there were concerns that effective feedback tailored to each user's emotions was not provided, leading to limited learning outcomes. Furthermore, training programs were fixed and could not be flexibly adjusted to the user's progress or emotional changes.

[0578] 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.

[0579] In this invention, the server includes means for automatically setting agent characteristic data for the purpose of improving the user's skills, means for analyzing the user's facial expressions and voice to recognize their emotional state, and means for generating feedback that takes the recognized emotional state into consideration. This provides an interactive and personalized learning environment that responds to the user's emotional state, enabling effective feedback and flexible training adjustments.

[0580] A "virtual agent" is a fictional digital character created using AI technology, possessing specific characteristics such as age, occupation, and hobbies.

[0581] A "data processing device" is a computer system for processing information, and includes hardware such as servers and terminals, as well as corresponding software.

[0582] A "user" refers to an individual who operates this system and improves their skills through interaction with virtual agents.

[0583] "Feature data" refers to the data that makes up the attributes and profile of a virtual agent, including information such as age, occupation, and hobbies.

[0584] The "sales process" refers to a series of scenarios that constitute the activities of proposing products and services optimized based on the needs of the virtual agent.

[0585] "Facial expression and voice analysis" is the process of collecting and analyzing data using cameras and microphones in order to recognize the user's emotional state in real time.

[0586] "Feedback" refers to interaction products that include suggestions for improvement and advice for the next steps, generated based on the user's responses and emotional state.

[0587] "Learning progress" is an indicator that shows the degree to which users have improved their skills through this system.

[0588] "Dynamic adjustment" refers to a function that automatically changes the content and difficulty level of a scenario according to the user's emotional state and learning progress.

[0589] This invention relates to a system that uses a data processing device to provide users with an interactive and emotion-based learning environment. This system is primarily realized through the interaction between a server, a terminal, and the user.

[0590] First, the server generates a virtual agent using a generative AI model. This agent has characteristic data such as age, occupation, and hobbies. The generative AI model uses prompts aimed at improving the user's skills to concretize the characteristic data. An example of this is, "Think of a way to explain a new travel gadget that might interest a 30-year-old digital marketing professional who loves to travel."

[0591] Next, the server presents the sales process to the user's terminal. This process involves the server selecting products and services from a product catalog that match the virtual agent's needs and outlining how to approach the user. The terminal plays the role of interactively presenting this process to the user.

[0592] The device uses an emotion engine to analyze the user's facial expressions and voice in real time and collect emotional data. This is done using facial recognition technology and voice analysis software. Based on these analysis results, the user's emotional state is fed back to the server. The feedback is automatically generated based on the user's responses and emotional state and includes suggestions for improvement and advice for the next steps.

[0593] For example, if a user is feeling stressed during a negotiation, the device recognizes that emotion, and the server suggests a calmer explanation. This emotion-based feedback allows the user to acquire effective communication skills.

[0594] Furthermore, the server monitors the user's learning progress and dynamically adjusts the next process and scenario. This includes adaptive scenario changes based on the user's emotional state and past responses. In this way, the system always provides learning content that is appropriate for the user, supporting efficient skill acquisition.

[0595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0596] Step 1:

[0597] The server uses prompt statements as input to generate an AI model, which then generates feature data for a virtual agent. Using the prompt statement "Think of a way to describe a new travel gadget that might interest a 30-year-old travel-loving digital marketing professional" as input, the server outputs an agent with specific characteristics such as age, occupation, and hobbies.

[0598] Step 2:

[0599] Based on the generated virtual agent's characteristic data, the server selects products and services from the product catalog that match the agent's needs and builds a sales process. In this step, the characteristic data is the input, and a process including the selected products and services is output.

[0600] Step 3:

[0601] The server transmits the constructed sales process to the terminal, which then presents it to the user. The sales process serves as input, and the output is an interactive scenario available to the user. The terminal communicates the scenario to the user through visual and auditory information.

[0602] Step 4:

[0603] The user interacts with a virtual agent based on the presented scenario. The user's responses and selections become input and are collected as data on the device.

[0604] Step 5:

[0605] The device uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. In this step, the user's facial expression and voice data are used as input, and their emotional state is output in real time.

[0606] Step 6:

[0607] The terminal sends user response data and emotional state to the server. The analysis results are used as input, and the data transmission to the server is output.

[0608] Step 7:

[0609] The server analyzes the received response data and emotional state, and generates feedback that takes the recognized emotions into account. The input consists of the user's response data and emotional data, and the output is personalized feedback.

[0610] Step 8:

[0611] The server dynamically adjusts the next sales process and scenario based on the user's learning progress. Progress data is used as input, and the newly adjusted sales process and scenario are output. This provides the user with an optimal learning experience.

[0612] (Application Example 2)

[0613] 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."

[0614] Traditional training systems using virtual customers focus on improving users' technical skills but lack support for improving interactions based on users' emotional states. Therefore, we aim to improve sales techniques more effectively and enhance the quality of customer service by utilizing real-time emotion recognition for feedback.

[0615] 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.

[0616] In this invention, the server includes means for randomly setting buyer attribute data for the purpose of training users, means for constructing a sales plan based on the set buyer attribute data, and means for analyzing the user's facial expressions or voice using a visual device worn by the user and improving the sales method based on changes in emotion. This makes it possible to recognize the user's emotional state in real time and provide personalized feedback.

[0617] A "virtual buyer" is a simulated buyer created for the purpose of interacting with the user, and is a person with attribute data such as age, occupation, and hobbies.

[0618] An "information processing system" is a collection of computers and associated software that enables the generation, analysis, and feedback of data.

[0619] A "user" is an individual who receives training using this system and aims to improve their skills through interaction with virtual buyers.

[0620] "Attribute data" refers to information related to a hypothetical buyer, and is a general term for data including age, occupation, hobbies, etc.

[0621] A "sales plan" is a scenario that includes the products and services offered to a hypothetical buyer, and is a proposal system built based on the customer's needs and attributes.

[0622] A "visual device" is a device that, when worn by a user, presents information visually in real time or performs emotional analysis, and includes smart glasses.

[0623] "Emotional changes" refer to fluctuations in the user's facial expressions and tone of voice during the interaction process, and are an important element indicating their emotional state.

[0624] "Feedback" is advice and suggestions for improvement generated based on user interaction and emotional state, and is a process that provides information to help users improve their skills more effectively.

[0625] In order to implement this invention, it is necessary to construct an information processing system that generates virtual buyers and improves the sales skills of users.

[0626] The server first uses AI technology to generate a virtual buyer persona. This persona includes attribute data such as age, occupation, and hobbies. The server then builds a sales plan based on the generated persona and presents it to the user's visual device. This visual device may include smart glasses or similar devices.

[0627] The device analyzes facial expressions and voice tone in real time from the user's visual device. This analysis uses an emotion analysis engine (e.g., Affectiva's Emotion AI), and based on the observed emotional changes, it can generate feedback to improve sales methods. The generated feedback helps improve sales techniques and the quality of customer service.

[0628] For example, if a store staff member is wearing smart glasses while selling a new product, and the emotion analysis engine determines that the customer's interest is waning, it can provide real-time feedback such as "further emphasize the product's key features."

[0629] An example of a prompt for a generative AI model would be: "Explain the appeal of the new product to the customer, analyze their facial expressions and tone of voice in real time to determine their emotions, and provide feedback with appropriate sales advice." This prompt is important for providing specific advice to the user through interaction analysis, including emotion analysis.

[0630] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0631] Step 1:

[0632] The server uses a generative AI model to generate virtual customer personas. It receives attribute data such as the virtual customer's age, occupation, and hobbies as input, and generates personas based on this data. This data is randomly combined and output as a unique customer profile.

[0633] Step 2:

[0634] The server builds a sales plan based on the generated virtual buyer persona. It receives information about the products and services to be sold, as well as buyer attribute data, as input. The server selects the products and services best suited to the buyer's needs and outputs them as a sales plan.

[0635] Step 3:

[0636] The terminal presents the sales plan to the user through a visual device (e.g., smart glasses). The previously constructed sales plan is input as visual information and output in real time to the user's field of vision.

[0637] Step 4:

[0638] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone. It collects real-time facial and voice data from the user as input. The emotion analysis engine analyzes this data to determine the user's emotional state. The analysis results are then output.

[0639] Step 5:

[0640] The server generates suggestions for improving sales methods based on the analysis results and sends them to the terminal as feedback. It receives data on the user's emotional state as input and creates appropriate advice and suggestions for improving sales methods based on that data. This advice is output to the terminal and presented to the user.

[0641] Step 6:

[0642] The user receives feedback from smart glasses and improves their skills through interaction with a virtual buyer. In this step, the user tries out sales techniques based on the feedback received and inputs the results back into the device. Subsequent interactions lead to further analysis of the emotional state and feedback.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] [Fourth Embodiment]

[0647] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0648] 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.

[0649] 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).

[0650] 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.

[0651] 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.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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".

[0660] To implement the present invention, a server as an information processing device, a terminal operated by the user, and a program that manages the entire process are used.

[0661] At system startup, the server first uses an AI engine to generate virtual customers. Customer personas are randomly and rationally generated by the server and include attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0662] Next, the server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario refers to the product catalog database and includes product information that matches the needs of the virtual customer.

[0663] The constructed scenario is presented to the user via the device. Based on this scenario, the user simulates interaction with a virtual customer. Interaction can be conducted via text input or voice input.

[0664] User responses are recorded on the device and sent to the server sequentially. The server analyzes this response data and uses AI algorithms to evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback includes specific advice on what went well and what needs improvement, and is presented to the user through the device.

[0665] Furthermore, the server tracks the user's overall training progress and dynamically adjusts the next scenario as needed. This adjustment is to provide training content of varying difficulty levels tailored to the user's proficiency.

[0666] For example, if the user is a new sales representative, they might be presented with a scenario in which they practice proposing a mobile phone plan to a customer with young children. The user's responses would then be given specific feedback on whether they considered the budget and whether they accurately understood the customer's needs.

[0667] This embodiment ensures training consistency and strengthens customer service skills through diverse scenarios, enabling new employees to become productive quickly and improving the efficiency of their training.

[0668] The following describes the processing flow.

[0669] Step 1:

[0670] The server starts the system and loads the necessary information from the AI ​​engine and database. This information includes customer attribute templates and product catalogs.

[0671] Step 2:

[0672] The server generates random customer personas based on customer attribute templates. These personas are assigned attributes such as age, gender, occupation, hobbies, purchase motivation, and budget.

[0673] Step 3:

[0674] The server builds the optimal sales scenario based on the generated customer persona. In this process, product information that matches the customer persona's needs is selected from the product catalog.

[0675] Step 4:

[0676] The terminal displays the sales scenario and customer persona information received from the server to the user on the screen.

[0677] Step 5:

[0678] Users interact with virtual customers based on presented scenarios and propose products and services. Users can respond via text or voice.

[0679] Step 6:

[0680] The device records user interaction data in real time and sends this data to the server sequentially.

[0681] Step 7:

[0682] The server analyzes the received interaction data and uses an AI algorithm to evaluate the user's response. Based on the accuracy and appropriateness of the response, it generates feedback.

[0683] Step 8:

[0684] The terminal displays feedback sent from the server to the user. This feedback includes specific improvement suggestions and assignments for the next training session.

[0685] Step 9:

[0686] The server logs user performance and tracks training progress. This allows the training content to be dynamically adjusted according to the user's proficiency level.

[0687] Step 10:

[0688] The user reviews the feedback and, if necessary, proceeds to the next scenario or ends the training. The system then initiates the next cycle based on the user's choice.

[0689] (Example 1)

[0690] 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".

[0691] In modern consumer service training, effectively learning within limited time and resources is a challenging task. Specifically, this involves practical dialogues based on diverse consumer scenarios and receiving immediate feedback based on the analysis of the results. However, traditional methods struggle to provide efficient training and generate appropriate feedback, thus creating a need for means to achieve rapid and effective skill improvement.

[0692] 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.

[0693] In this invention, the server includes means for predicting and setting consumer attribute information for the purpose of user education, means for creating a sales plan based on the set consumer attribute information, and means for dynamically adjusting the next plan according to the user's education progress. This enables users to quickly and effectively improve their skills by undergoing practical training through various virtual customer scenarios and receiving immediate feedback.

[0694] A "virtual customer" is a fictional consumer model with consumer attribute information and behavior, digitally generated for the purpose of consumer response training and simulation.

[0695] A "data processing device" is an electronic device or system used for collecting, analyzing, and generating information.

[0696] "Users" refer to individuals or organizations that use this system for training or simulations.

[0697] "Education" refers to training and learning activities that enable users to improve their own skills and knowledge.

[0698] "Consumer attribute information" refers to the individual characteristics and profiles of a hypothetical customer, such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0699] A "sales plan" is a scenario that defines how products and services will be introduced to a hypothetical customer, as well as the content of that introduction.

[0700] "Dynamic adjustment" means changing and optimizing the next scenario and training content in real time or semi-automatically based on the user's training progress and response results.

[0701] "Feedback" refers to the evaluations and advice that users receive after interacting with virtual customers, pointing out specific areas for improvement and successes achieved.

[0702] To implement this invention, a server is required as a data processing device. The server generates virtual customers using a generative AI model and sets the attribute information of those customers. This AI model is designed to randomly and rationally determine attributes such as the consumer's age, gender, occupation, hobbies, purchasing motivation, and budget.

[0703] Next, the server creates a sales plan based on the configured attribute information. This plan includes product information that matches consumer needs, which the server retrieves from the product database. The generated plan is provided to the user via a terminal. The terminal has a visual interface through which the user can review the sales scenario and simulate interactions with virtual customers.

[0704] The user operates the terminal to communicate with a virtual customer based on the presented sales plan. The user's responses, entered as text or voice, are recorded on the terminal and sent to the server in real time. The server uses an AI algorithm to analyze these responses and evaluate the user's performance. Based on this evaluation, immediate feedback is generated. This feedback, which includes specific advice on what went well and what needs improvement, is presented to the user through the terminal.

[0705] Furthermore, the server tracks the user's training progress and dynamically adjusts the next sales plan as needed. This adjustment makes it possible to provide different levels of training content tailored to the user's proficiency.

[0706] As a concrete example, a scenario is presented in which the user, as a new sales representative, proposes a new mobile phone plan to a virtual customer with young children. A possible response from the user might be, for example, "This plan has family benefits, a large data allowance, and is ideal for families looking to keep costs down." Based on this response, the server generates appropriate feedback.

[0707] An example of a prompt might be: "What plan would you recommend to a 30-year-old woman who is a teacher, enjoys reading and traveling, and is looking for a new mobile phone plan within the budget of a family of four?" In this way, users can improve their sales skills in real time.

[0708] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0709] Step 1:

[0710] The server generates virtual customers using an AI model at system startup. The input at this stage consists of basic demographic information and market research data. The AI ​​model analyzes this data and outputs customer personas with randomly and rationally combined attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0711] Step 2:

[0712] The server automatically builds a sales plan based on the customer persona generated in Step 1. The inputs are the customer persona and the product catalog database. The server references these and outputs product information best suited to the needs of the virtual customer. This sales plan includes recommended products, benefits, and pricing information.

[0713] Step 3:

[0714] The terminal visually presents the sales plan output from the server to the user. The input is sales plan data from the server, which the terminal displays on a GUI (Graphical User Interface), allowing the user to access it.

[0715] Step 4:

[0716] The user operates the terminal to simulate a conversation with a virtual customer based on the presented sales plan. This step allows for input via text or voice. The user's responses are recorded on the terminal as suggestions or questions to the virtual customer.

[0717] Step 5:

[0718] The terminal records the user's response and sends that data to the server. The input from the terminal is the user's response data, which is then quickly transmitted to the server.

[0719] Step 6:

[0720] The server analyzes the received user response data using an AI algorithm to evaluate the user's performance. The input is the user's response data, and the analysis results output an evaluation of the appropriateness of the suggestions and communication skills.

[0721] Step 7:

[0722] The server generates immediate feedback based on the analysis results and presents it to the user via the terminal. This feedback includes specific advice on successes and areas for improvement. The input is the analysis results, and the feedback message is output.

[0723] Step 8:

[0724] The server tracks the user's overall training progress and dynamically adjusts the next training plan as needed. The input is the user's historical performance data, which is used to output the difficulty and content of the next scenario. This adjustment provides training optimized for each individual user.

[0725] (Application Example 1)

[0726] 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".

[0727] There is a need to provide efficient and personalized training for personnel in online environments, particularly in customer service. Customer support staff on e-commerce sites, in particular, need to acquire the skills to respond quickly and appropriately to diverse customer needs, but traditional training methods have struggled to effectively achieve this.

[0728] 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.

[0729] In this invention, the server includes means for randomly setting person attribute data for the purpose of training the user, means for constructing a sales procedure based on the set person attribute data, and means for presenting the constructed procedure to the user and recording the user's response. This allows the user to train practical customer service skills in individual virtual scenarios and efficiently improve their skills through immediate feedback.

[0730] A "user" is a person who uses the system to receive training.

[0731] "Personal attribute data" refers to data that randomly assigns characteristics such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0732] A "sales procedure" is a sales scenario built based on the attribute data of a virtual customer.

[0733] "Feedback" refers to advice generated by the AI ​​based on user responses, which evaluates the training results and provides suggestions for improvement.

[0734] "Dynamic adjustment" means automatically changing the content and difficulty level of the scenarios provided based on the user's training progress and proficiency.

[0735] "Immediate feedback" refers to evaluation and guidance given immediately after a user interaction.

[0736] "Proficiency level" refers to the degree of knowledge and skills acquired by a user through training.

[0737] The system implementing this invention mainly consists of a server, a terminal, and a user. The server generates virtual customers using an AI engine. These virtual customers have random attribute data, such as age, gender, occupation, hobbies, purchasing motivation, and budget. Based on this attribute data, a sales procedure is dynamically constructed. For this construction, AI models such as "GPT-4" and "BERT" are used.

[0738] The terminal presents the user with a pre-defined sales procedure and provides an interface for the user to respond. This response can be text or voice input, which the terminal records and sends to the server. Machine learning libraries such as TensorFlow or PyTorch are used for reactions and evaluation. The server analyzes the user's responses and generates immediate feedback. This feedback includes specific areas for improvement and effective response methods, which the terminal presents to the user.

[0739] As a concrete example, consider a scenario where a new customer support staff member simulates how to handle a customer inquiry about a recent order not arriving. The server generates a virtual customer and provides a scenario for rehearsing the appropriate response.

[0740] A concrete example of a prompt message is: "You are a support staff member for a new e-commerce site. How would you appropriately respond to a customer inquiry? Imagine a scenario where the customer placed an online order, but it has not arrived."

[0741] This allows users to gain practical experience while honing their customer service skills quickly and effectively.

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

[0743] Step 1:

[0744] The server uses an AI engine to generate virtual customers. First, attribute data (age, gender, occupation, hobbies, purchasing motivation, and budget) is set. This data is generated randomly but is made reasonable based on specific parameters. The output is the attribute data of the virtual customer.

[0745] Step 2:

[0746] The server constructs a sales procedure based on the attribute data of a virtual customer. It references a product catalog database and selects the product information that best matches the virtual customer's attributes. The sales procedure is generated using either the AI ​​model "GPT-4" or "BERT". The output is the constructed sales procedure.

[0747] Step 3:

[0748] The terminal presents the user with a pre-defined sales procedure. The user inputs responses based on this procedure through the terminal's interface. Input can be text or voice. Output is the user's response data.

[0749] Step 4:

[0750] The server analyzes the user's response and generates feedback using AI. The user's response is compared against the sales procedure described earlier, and its appropriateness and areas for improvement are evaluated. TensorFlow or PyTorch is used for the analysis. The output is feedback data.

[0751] Step 5:

[0752] The device presents the generated feedback to the user. The feedback specifically highlights successes and areas for improvement. This allows the user to gain concrete methods for improving their skills. The output is the user's learning behavior based on the feedback.

[0753] Step 6:

[0754] The server records the user's progress and dynamically adjusts the next sales procedure. It automatically changes the content and difficulty of the next training session based on the user's proficiency. This ensures that training is always optimized for the user. The output is the adjusted next sales procedure.

[0755] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0756] The present invention is implemented by combining an emotion engine with a system in which a server, which is an information processing device, generates virtual customers and provides sales scenarios for the purpose of training users.

[0757] The system begins with the server using AI technology to generate a virtual customer persona to present to the user. This persona includes attributes such as age, occupation, and hobbies. After generation, the server constructs a sales scenario based on the persona. This scenario selects products and services from a product catalog that match the virtual customer's needs and includes them as a sales proposal.

[0758] The user is presented with a scenario via their device, and interacts with a virtual customer within the simulated environment. During the interaction, the device uses an emotion engine to recognize the user's emotional state. This engine uses facial recognition and voice tone analysis to evaluate changes in emotion in real time.

[0759] User responses are recorded on the device and sent to the server. The server analyzes the responses, taking into account the user's emotional state, and generates feedback. This feedback includes an approach based not only on the user's technical skills but also on their emotional responses, providing more personalized advice.

[0760] For example, if the emotion engine determines that a user is frustrated, it can provide feedback suggesting simpler and more persuasive sales techniques or a calmer dialogue approach.

[0761] Furthermore, the server has the ability to dynamically adjust the next scenario as the user's training progresses, and can change the difficulty and type of scenario according to the user's emotional state. This process allows the user to have a more enriching learning experience and maximizes the effectiveness of the training.

[0762] Thus, the information processing device incorporating the emotion engine according to the present invention can be applied to support the improvement of user skills and to provide more advanced educational programs by taking into account emotional adaptation.

[0763] The following describes the processing flow.

[0764] Step 1:

[0765] The server starts the program and prepares the AI ​​engine and emotion engine. At this stage, templates for customer persona generation and the product database are loaded.

[0766] Step 2:

[0767] The server uses AI technology to generate random customer personas. These customer personas are assigned attributes such as age, gender, occupation, hobbies, purchasing motivation, and budget.

[0768] Step 3:

[0769] The server automatically builds an appropriate sales scenario based on the generated customer persona. This scenario includes product information that matches the needs of the virtual customer.

[0770] Step 4:

[0771] The terminal displays the proposed sales scenario to the user and prompts the user to start the simulation.

[0772] Step 5:

[0773] Users initiate conversations with virtual customers based on scenarios and make sales proposals. Input can be via text or voice.

[0774] Step 6:

[0775] The device analyzes the user's voice and video in real time and uses an emotion engine to recognize the user's emotional state. This information captures the user's reactions and emotional changes and is sent to the server as data.

[0776] Step 7:

[0777] The server comprehensively analyzes the user's response data and emotional state. Using AI algorithms, not only the accuracy of the user's responses but also their emotional appropriateness is evaluated.

[0778] Step 8:

[0779] Based on the evaluation results, the server generates personalized feedback and adjusts the advice based on the user's emotional state.

[0780] Step 9:

[0781] The device provides the user with the generated feedback, explaining in detail areas for improvement and challenges that need to be addressed.

[0782] Step 10:

[0783] The server tracks the user's training progress and adjusts the next scenario based on the user's proficiency and emotional responses. In this way, an effective training experience that also takes emotional aspects into account is achieved.

[0784] (Example 2)

[0785] 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".

[0786] Traditional training systems have faced the challenge of providing an interactive learning environment that takes into account the user's emotional state. As a result, there were concerns that effective feedback tailored to each user's emotions was not provided, leading to limited learning outcomes. Furthermore, training programs were fixed and could not be flexibly adjusted to the user's progress or emotional changes.

[0787] 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.

[0788] In this invention, the server includes means for automatically setting agent characteristic data for the purpose of improving the user's skills, means for analyzing the user's facial expressions and voice to recognize their emotional state, and means for generating feedback that takes the recognized emotional state into consideration. This provides an interactive and personalized learning environment that responds to the user's emotional state, enabling effective feedback and flexible training adjustments.

[0789] A "virtual agent" is a fictional digital character created using AI technology, possessing specific characteristics such as age, occupation, and hobbies.

[0790] A "data processing device" is a computer system for processing information, and includes hardware such as servers and terminals, as well as corresponding software.

[0791] A "user" refers to an individual who operates this system and improves their skills through interaction with virtual agents.

[0792] "Feature data" refers to the data that makes up the attributes and profile of a virtual agent, including information such as age, occupation, and hobbies.

[0793] The "sales process" refers to a series of scenarios that constitute the activities of proposing products and services optimized based on the needs of the virtual agent.

[0794] "Facial expression and voice analysis" is the process of collecting and analyzing data using cameras and microphones in order to recognize the user's emotional state in real time.

[0795] "Feedback" refers to interaction products that include suggestions for improvement and advice for the next steps, generated based on the user's responses and emotional state.

[0796] "Learning progress" is an indicator that shows the degree to which users have improved their skills through this system.

[0797] "Dynamic adjustment" refers to a function that automatically changes the content and difficulty level of a scenario according to the user's emotional state and learning progress.

[0798] This invention relates to a system that uses a data processing device to provide users with an interactive and emotion-based learning environment. This system is primarily realized through the interaction between a server, a terminal, and the user.

[0799] First, the server generates a virtual agent using a generative AI model. This agent has characteristic data such as age, occupation, and hobbies. The generative AI model uses prompts aimed at improving the user's skills to concretize the characteristic data. An example of this is, "Think of a way to explain a new travel gadget that might interest a 30-year-old digital marketing professional who loves to travel."

[0800] Next, the server presents the sales process to the user's terminal. This process involves the server selecting products and services from a product catalog that match the virtual agent's needs and outlining how to approach the user. The terminal plays the role of interactively presenting this process to the user.

[0801] The device uses an emotion engine to analyze the user's facial expressions and voice in real time and collect emotional data. This is done using facial recognition technology and voice analysis software. Based on these analysis results, the user's emotional state is fed back to the server. The feedback is automatically generated based on the user's responses and emotional state and includes suggestions for improvement and advice for the next steps.

[0802] For example, if a user is feeling stressed during a negotiation, the device recognizes that emotion, and the server suggests a calmer explanation. This emotion-based feedback allows the user to acquire effective communication skills.

[0803] Furthermore, the server monitors the user's learning progress and dynamically adjusts the next process and scenario. This includes adaptive scenario changes based on the user's emotional state and past responses. In this way, the system always provides learning content that is appropriate for the user, supporting efficient skill acquisition.

[0804] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0805] Step 1:

[0806] The server uses prompt statements as input to generate an AI model, which then generates feature data for a virtual agent. Using the prompt statement "Think of a way to describe a new travel gadget that might interest a 30-year-old travel-loving digital marketing professional" as input, the server outputs an agent with specific characteristics such as age, occupation, and hobbies.

[0807] Step 2:

[0808] Based on the generated virtual agent's characteristic data, the server selects products and services from the product catalog that match the agent's needs and builds a sales process. In this step, the characteristic data is the input, and a process including the selected products and services is output.

[0809] Step 3:

[0810] The server transmits the constructed sales process to the terminal, which then presents it to the user. The sales process serves as input, and the output is an interactive scenario available to the user. The terminal communicates the scenario to the user through visual and auditory information.

[0811] Step 4:

[0812] The user interacts with a virtual agent based on the presented scenario. The user's responses and selections become input and are collected as data on the device.

[0813] Step 5:

[0814] The device uses an emotion engine to analyze the user's facial expressions and voice to recognize their emotional state. In this step, the user's facial expression and voice data are used as input, and their emotional state is output in real time.

[0815] Step 6:

[0816] The terminal sends user response data and emotional state to the server. The analysis results are used as input, and the data transmission to the server is output.

[0817] Step 7:

[0818] The server analyzes the received response data and emotional state, and generates feedback that takes the recognized emotions into account. The input consists of the user's response data and emotional data, and the output is personalized feedback.

[0819] Step 8:

[0820] The server dynamically adjusts the next sales process and scenario based on the user's learning progress. Progress data is used as input, and the newly adjusted sales process and scenario are output. This provides the user with an optimal learning experience.

[0821] (Application Example 2)

[0822] 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".

[0823] Traditional training systems using virtual customers focus on improving users' technical skills but lack support for improving interactions based on users' emotional states. Therefore, we aim to improve sales techniques more effectively and enhance the quality of customer service by utilizing real-time emotion recognition for feedback.

[0824] 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.

[0825] In this invention, the server includes means for randomly setting buyer attribute data for the purpose of training users, means for constructing a sales plan based on the set buyer attribute data, and means for analyzing the user's facial expressions or voice using a visual device worn by the user and improving the sales method based on changes in emotion. This makes it possible to recognize the user's emotional state in real time and provide personalized feedback.

[0826] A "virtual buyer" is a simulated buyer created for the purpose of interacting with the user, and is a person with attribute data such as age, occupation, and hobbies.

[0827] An "information processing system" is a collection of computers and associated software that enables the generation, analysis, and feedback of data.

[0828] A "user" is an individual who receives training using this system and aims to improve their skills through interaction with virtual buyers.

[0829] "Attribute data" refers to information related to a hypothetical buyer, and is a general term for data including age, occupation, hobbies, etc.

[0830] A "sales plan" is a scenario that includes the products and services offered to a hypothetical buyer, and is a proposal system built based on the customer's needs and attributes.

[0831] A "visual device" is a device that, when worn by a user, presents information visually in real time or performs emotional analysis, and includes smart glasses.

[0832] "Emotional changes" refer to fluctuations in the user's facial expressions and tone of voice during the interaction process, and are an important element indicating their emotional state.

[0833] "Feedback" is advice and suggestions for improvement generated based on user interaction and emotional state, and is a process that provides information to help users improve their skills more effectively.

[0834] In order to implement this invention, it is necessary to construct an information processing system that generates virtual buyers and improves the sales skills of users.

[0835] The server first uses AI technology to generate a virtual buyer persona. This persona includes attribute data such as age, occupation, and hobbies. The server then builds a sales plan based on the generated persona and presents it to the user's visual device. This visual device may include smart glasses or similar devices.

[0836] The device analyzes facial expressions and voice tone in real time from the user's visual device. This analysis uses an emotion analysis engine (e.g., Affectiva's Emotion AI), and based on the observed emotional changes, it can generate feedback to improve sales methods. The generated feedback helps improve sales techniques and the quality of customer service.

[0837] For example, if a store staff member is wearing smart glasses while selling a new product, and the emotion analysis engine determines that the customer's interest is waning, it can provide real-time feedback such as "further emphasize the product's key features."

[0838] An example of a prompt for a generative AI model would be: "Explain the appeal of the new product to the customer, analyze their facial expressions and tone of voice in real time to determine their emotions, and provide feedback with appropriate sales advice." This prompt is important for providing specific advice to the user through interaction analysis, including emotion analysis.

[0839] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0840] Step 1:

[0841] The server uses a generative AI model to generate virtual customer personas. It receives attribute data such as the virtual customer's age, occupation, and hobbies as input, and generates personas based on this data. This data is randomly combined and output as a unique customer profile.

[0842] Step 2:

[0843] The server builds a sales plan based on the generated virtual buyer persona. It receives information about the products and services to be sold, as well as buyer attribute data, as input. The server selects the products and services best suited to the buyer's needs and outputs them as a sales plan.

[0844] Step 3:

[0845] The terminal presents the sales plan to the user through a visual device (e.g., smart glasses). The previously constructed sales plan is input as visual information and output in real time to the user's field of vision.

[0846] Step 4:

[0847] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone. It collects real-time facial and voice data from the user as input. The emotion analysis engine analyzes this data to determine the user's emotional state. The analysis results are then output.

[0848] Step 5:

[0849] The server generates suggestions for improving sales methods based on the analysis results and sends them to the terminal as feedback. It receives data on the user's emotional state as input and creates appropriate advice and suggestions for improving sales methods based on that data. This advice is output to the terminal and presented to the user.

[0850] Step 6:

[0851] The user receives feedback from smart glasses and improves their skills through interaction with a virtual buyer. In this step, the user tries out sales techniques based on the feedback received and inputs the results back into the device. Subsequent interactions lead to further analysis of the emotional state and feedback.

[0852] 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.

[0853] 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.

[0854] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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."

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] The following is further disclosed regarding the embodiments described above.

[0874] (Claim 1)

[0875] An information processing device for generating virtual customers,

[0876] A means of randomly setting customer attribute data for the purpose of training users,

[0877] A means of constructing a sales scenario based on the set customer attribute data,

[0878] A means of presenting a constructed scenario to the user and recording the user's response,

[0879] A means for analyzing user responses and generating feedback,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, comprising means for sequentially analyzing the content of conversations with virtual customers and evaluating individual responses.

[0883] (Claim 3)

[0884] The system according to claim 1, comprising means for dynamically adjusting the next scenario according to the user's training progress.

[0885] "Example 1"

[0886] (Claim 1)

[0887] A data processing device for generating virtual customers,

[0888] A means of predicting and setting consumer attribute information for the purpose of educating users,

[0889] A means of creating a sales plan based on the set consumer attribute information,

[0890] A means of providing the created plan to the user and recording the user's response,

[0891] A means for analyzing user responses and generating feedback,

[0892] A means of providing visual feedback based on the analysis results,

[0893] A means to dynamically adjust the next plan according to the user's educational progress,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] The system according to claim 1, comprising means for sequentially analyzing the content of conversations with a virtual customer, evaluating individual responses, and generating immediate feedback.

[0897] (Claim 3)

[0898] The system according to claim 1, comprising means for dynamically changing the plan in order to provide various training contents according to the user's abilities.

[0899] "Application Example 1"

[0900] (Claim 1)

[0901] A means of randomly setting person attribute data for the purpose of training users,

[0902] A means of constructing a sales procedure based on the attribute data of a set person,

[0903] A means of presenting the established procedure to the user and recording the user's response,

[0904] A means for analyzing user responses and generating feedback,

[0905] A means to record the user's process from the start, dynamically adjust the next steps, and optimize training,

[0906] A system that includes this.

[0907] (Claim 2)

[0908] The system according to claim 1, comprising means for sequentially analyzing the content of conversations with a virtual customer, evaluating individual responses, and generating immediate feedback.

[0909] (Claim 3)

[0910] The system according to claim 1, comprising means for selecting and adjusting the next scenario from multiple difficulty levels based on the user's proficiency level.

[0911] "Example 2 of combining an emotion engine"

[0912] (Claim 1)

[0913] A data processing device for generating a virtual agent,

[0914] A means of automatically setting agent characteristic data with the aim of improving the skills of users,

[0915] A means of building a sales process based on the configured agent characteristic data,

[0916] A means of presenting the constructed process to the user and recording the user's response,

[0917] A means of recognizing the emotional state by analyzing the user's facial expressions and voice,

[0918] A means of generating feedback that takes into account the recognized emotional state,

[0919] A means to dynamically adjust the next process according to the user's learning progress,

[0920] A system that includes this.

[0921] (Claim 2)

[0922] The system according to claim 1, comprising means for sequentially analyzing the content of interactions with a virtual agent and evaluating individual responses based on emotional states.

[0923] (Claim 3)

[0924] The system according to claim 1, comprising means for changing the difficulty level and type of process according to the emotional state of the user.

[0925] "Application example 2 when combining with an emotional engine"

[0926] (Claim 1)

[0927] An information processing system for generating virtual buyers,

[0928] A means of randomly setting buyer attribute data for the purpose of training users,

[0929] A means of constructing a sales plan based on the set buyer attribute data,

[0930] A means of presenting the constructed plan to the user and recording the user's response,

[0931] A means of analyzing the user's emotional state and generating feedback,

[0932] A means of improving sales methods based on changes in emotion by analyzing the user's facial expressions or voice using a visual device worn by the user,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, comprising means for sequentially analyzing the content of conversations with a virtual buyer and providing feedback that takes into account the evaluation of individual responses and changes in emotion.

[0936] (Claim 3)

[0937] The system according to claim 1, comprising means for dynamically adjusting the next plan in accordance with the user's training progress and emotional response. [Explanation of Symbols]

[0938] 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 randomly setting person attribute data for the purpose of training users, A means of constructing a sales procedure based on the attribute data of a set person, A means of presenting the established procedure to the user and recording the user's response, A means for analyzing user responses and generating feedback, A means to record the user's process from the start, dynamically adjust the next steps, and optimize training, A system that includes this.

2. The system according to claim 1, comprising means for sequentially analyzing the content of conversations with a virtual customer, evaluating individual responses, and generating immediate feedback.

3. The system according to claim 1, comprising means for selecting and adjusting the next scenario from multiple difficulty levels based on the user's proficiency level.

Images