system

Abstract

We provide the system. [Solution] A means of generating a virtual customer profile, Means for constructing a sales scenario based on the aforementioned customer profile, A means of analyzing the content of the dialogue in the aforementioned sales scenario and providing feedback, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, 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] At sales sites, it is difficult to provide new employees with immediate combat effectiveness and equal education. The conventional role-playing by colleagues takes time and places a heavy burden on senior employees. Also, the lack of guarantee of the consistency and objectivity of education is an issue.

Means for Solving the Problems

[0005] This invention provides a system that uses AI to generate virtual customer profiles and uses those profiles to build sales scenarios. Users can use this system to instantly analyze conversations and receive feedback, enabling consistent training free from personal bias. Furthermore, diverse scenarios based on customer profiles including attribute information allow new employees to quickly improve their skills in handling various situations.

[0006] A "virtual customer profile" is a collection of data generated by AI that represents the characteristics of a fictional customer, including attribute information such as age, gender, preferences, and purchase history.

[0007] A "sales scenario" is a scenario used in training new employees that shows a sequence of dialogues and actions that simulate customer interactions.

[0008] "Analyzing dialogue content" refers to the process where the system evaluates the responses and actions taken by users during role-playing, identifying their quality and areas for improvement.

[0009] "Providing feedback" is the process of immediately communicating evaluations and improvement advice regarding user responses and actions based on the analysis results.

[0010] "Attribute information" refers to the elements that make up a customer profile, primarily individual data such as age, gender, preferences, and purchase history. [Brief explanation of the drawing]

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

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

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

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

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

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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.

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

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

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

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention provides an AI-powered sales training system aimed at improving the sales skills of new employees. The following describes its embodiments in natural language.

[0033] The server first uses an AI algorithm to generate a virtual customer profile. This profile includes attribute information such as age, gender, preferences, and purchase history, and various patterns are provided to ensure diversity in sales scenarios. The generated customer profiles are stored in a database and accessed for each training session.

[0034] The terminal displays sales scenarios on the user interface based on customer profiles received from the server. Multiple sales scenarios are listed on the screen, and new employees can select one to train on.

[0035] For example, the terminal might present a virtual customer profile such as "a male in his 30s who is a sports enthusiast and has frequently purchased outdoor equipment in the past." A new employee selects a sales scenario based on this profile, and then begins a simulated conversation with the customer within that scenario.

[0036] The user (a new employee) interacts with an AI acting as a customer, following a sales scenario presented on the terminal. The user answers customer questions and explains products. During the interaction, the user's responses are analyzed in real time by the server, and feedback is quickly returned to the terminal. Specifically, the quality of the responses is evaluated, such as "The product's benefits were clearly explained" or "The price explanation was unclear."

[0037] This training system allows new employees to efficiently acquire the skills to handle various virtual customers. Receiving immediate feedback allows them to identify areas for improvement on the spot and utilize this information in subsequent role-playing exercises. In this way, it promotes the immediate deployment of sales skills and contributes to the uniformity and quality of training.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The server utilizes AI algorithms to generate virtual customer profiles. These profiles include attributes such as age, gender, preferences, and purchase history, creating a diverse set of profiles that can handle various sales scenarios. The generated profiles are stored in a database and accessed in later steps.

[0041] Step 2:

[0042] The terminal receives customer profile data from the server. Based on the received data, it displays a list of sales scenarios on the user interface. Multiple scenarios are presented on the screen so that the user (new employee) can make a selection.

[0043] Step 3:

[0044] The user selects the scenario they want to train on from the displayed list of scenarios. Based on the selected scenario, a specific sales scenario related to the customer profile is set up.

[0045] Step 4:

[0046] The device initiates a role-playing scenario with a virtual customer controlled by AI, according to the selected scenario. Questions and lines from the customer are displayed on the device, and the user responds to them.

[0047] Step 5:

[0048] Users respond appropriately to questions from a virtual customer during role-playing, using their own knowledge and skills. In doing so, they explain the product's features and benefits, attempting to engage in a conversation that convinces the customer.

[0049] Step 6:

[0050] The server analyzes user responses in real time and evaluates their content. Natural language processing technology is used for the analysis, evaluating the accuracy of the content and the appropriateness of the expression.

[0051] Step 7:

[0052] The terminal immediately displays feedback to the user regarding the server's response. This feedback includes both positive aspects of the response and areas for improvement, encouraging user understanding and improvement.

[0053] (Example 1)

[0054] 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."

[0055] Training new employees in sales presents a problem: the quality and efficiency of training vary due to individual differences in ability and lack of experience. In particular, developing effective communication skills in a practical setting requires experience dealing with a wide variety of customers, but this is difficult to achieve through conventional training methods.

[0056] 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.

[0057] In this invention, the server includes means for generating virtual attribute information, means for constructing a sales scenario based on the attribute information, and means for analyzing the content of the dialogue in the sales scenario and providing feedback. This enables sales training that anticipates various customer attributes, allowing users to efficiently acquire the ability to respond promptly to diverse situations.

[0058] "Virtual attribute information" refers to a data set that simulates customer characteristics and preferences, and includes information such as age, gender, hobbies, and purchase history.

[0059] A "sales scenario" is a scenario built based on virtual customer attributes, and is a simulation environment used by the user.

[0060] "Dialogue content analysis" is a process that analyzes the content of simulated conversations between users and AI in real time and evaluates how effective the conversations were.

[0061] The "means of providing feedback" refer to a system that, based on an analysis of the conversation content, immediately provides users with specific advice and evaluations to help them improve their sales skills.

[0062] A "user interface" is an interactive display method on a device screen that allows users to experience and interact with a story.

[0063] "Immediate analysis of dialogue records" refers to a process where the content of a conversation between the user and the AI ​​is analyzed immediately after it takes place, and the results are immediately fed back to the user.

[0064] This invention is an AI-powered sales training system aimed at improving the sales skills of new employees. The system consists of three components: a server, a terminal, and a user, each playing a specific role.

[0065] The server first generates virtual attribute information using an AI algorithm. This process utilizes a deep learning model. This virtual attribute information includes the customer's age, gender, preferences, and purchase history. This data serves as the foundation for providing diverse sales scenarios and is stored in a database. A specific example scenario might be "a 30-year-old male who enjoys sports and has frequently purchased outdoor equipment in the past."

[0066] The terminal presents sales scenarios via a user interface based on attribute information provided by the server. Here, a Python GUI library is used to display a list of sales scenarios. New employees can select a scenario of interest and begin an interaction according to that scenario. Depending on the selected scenario, detailed information and related product data are displayed on the screen.

[0067] Users interact with an AI acting as a customer, following a sales scenario presented on their device. A generative AI model is used, allowing the AI ​​to play the role of the customer. By answering questions about product benefits and pricing, users can hone their skills in a realistic setting. Feedback generated during the interaction is presented to the user in real time, allowing them to immediately identify areas for improvement.

[0068] A concrete example of a prompt message would be, "In this scenario, please provide an approach for selling outdoor equipment to a sports enthusiast in their 30s." In this way, sales skills can be improved in a more practical and efficient manner.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The server generates virtual attribute information. Past purchase data and general market trend data are used as input. AI algorithms, particularly deep learning models, are used to generate diverse customer profiles from this data. The output is virtual attribute information including age, gender, preferences, and purchase history, and is stored in a database in JSON format.

[0072] Step 2:

[0073] The terminal presents a sales scenario. It uses virtual attribute information received from the server as input. A Python GUI library is used to visually list multiple sales scenarios on the user interface. The user can select the scenario they are interested in. The output displays detailed information and related products based on the user's selected scenario.

[0074] Step 3:

[0075] The user initiates a dialogue based on a scenario. The input is a sales scenario displayed on the terminal. The user uses a generated AI model to interact with the customer-role AI, explaining product features and pricing based on the information presented. The output consists of the dialogue history and response data, which are sent to the server.

[0076] Step 4:

[0077] The server analyzes the user's responses. The input is the history of the user-AI interaction. A machine learning algorithm is used to evaluate the effectiveness and areas for improvement of the responses. The output is feedback data, which includes specific advice such as "The product features were explained appropriately" or "The price explanation is unclear." The feedback is generated in real time and sent to the terminal.

[0078] Step 5:

[0079] The device displays feedback to the user. It uses feedback data received from the server as input. The analyzed evaluation and advice are immediately displayed in the user interface. The output is information that encourages user performance improvement and can be used to improve future training sessions.

[0080] (Application Example 1)

[0081] 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."

[0082] Traditional sales training systems make it difficult to effectively acquire skills relevant to actual sales work in a short period of time. Furthermore, they have the problem of not being able to grasp training progress and challenges in real time and make immediate improvements. To enable in-store sales staff to perform their duties quickly and accurately on the job, these challenges need to be addressed.

[0083] 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.

[0084] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario based on the customer profile, and means for selecting a training scenario and initiating a virtual dialogue through a user interface operating on a portable electronic device. This enables users to conduct scenario-based training directly related to their daily sales activities on a mobile device and receive real-time feedback.

[0085] A "virtual customer profile" is fictional customer data generated based on attribute information such as age, gender, preferences, and purchase history, and is used to create diverse sales scenarios.

[0086] A "sales scenario" refers to a sales situation or scenario set up based on a hypothetical customer profile, and serves as the foundation for building a specific dialogue flow in sales training.

[0087] "Means of providing feedback" refers to a function that analyzes user responses and dialogue content in sales scenarios, evaluates their quality, and then presents users with areas for improvement in their training.

[0088] A "portable electronic device" refers to a portable electronic device, such as a smartphone or tablet, that presents training scenarios and provides an interface for conducting virtual dialogues.

[0089] "Methods for real-time analysis" refers to technologies that enable a rapid learning cycle by instantly analyzing the content of conversations and displaying feedback and progress records to the user each time.

[0090] The system for carrying out this invention includes a server, a portable electronic device (terminal), and a user. The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history. This allows for the preparation of diverse sales scenarios and enables the user to train in various situations.

[0091] The portable electronic device presents sales scenarios based on customer profiles received from the server. The user interface is developed using React Native, allowing users to select scenarios and engage in virtual dialogues. The device also transmits the content of the dialogue to the server in real time, where it is analyzed using a natural language processing model (e.g., BERT) powered by Tensorflow®.

[0092] The server analyzes user responses and provides immediate feedback. This allows users to understand their challenges and areas for improvement during training and apply that knowledge to future interactions. Real-time feedback helps users learn quickly and improve their sales skills.

[0093] As a concrete example, a user might select a virtual customer profile targeting an "outdoorsy woman in her 40s" and choose a scenario where this customer is looking for sunglasses. In this scenario, the user can explain the features and benefits of the product and receive feedback from the AI ​​such as, "Please explain the benefits of this product in more detail." This entire process allows the user to enhance their face-to-face customer service skills.

[0094] An example of a prompt to a generating AI might be: "The customer is looking for sunglasses. His preference is casual, and he intends to use them mainly for outdoor activities. How should we approach him?" By using this prompt, the AI ​​can be trained to construct conversations and learn more effective customer service methods.

[0095] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0096] Step 1:

[0097] The server uses an AI algorithm to generate virtual customer profiles. It receives data such as age, gender, preferences, and purchase history as input, and uses this information to construct profiles with diverse customer attributes. The output is the data of the generated customer profiles. This allows for a variety of sales scenarios.

[0098] Step 2:

[0099] The server transmits the generated customer profile to a portable electronic device (terminal). The input is the customer profile data on the server, which is output to the terminal via data transfer. The terminal uses the received data to display a list of sales scenarios on the user interface.

[0100] Step 3:

[0101] The user selects their desired sales scenario through the terminal interface. The input is a list of sales scenarios displayed on the terminal, and the user's selection triggers the output of specific scenario data. This output is the scenario data necessary for subsequent training.

[0102] Step 4:

[0103] The terminal initiates a virtual dialogue based on the selected sales scenario. The input is the user's selected scenario data, and a generative AI model is used to generate dialogue text based on this data. The output is presented to the user as the content of the dialogue with a virtual customer. In the dialogue generation process, prompt sentences are input to the AI ​​model, and dialogue appropriate to the scenario is generated.

[0104] Step 5:

[0105] The server analyzes user interactions in real time and generates evaluation feedback. The input is user interaction data. This data is analyzed using natural language processing techniques (TensorFlow and BERT model) to evaluate the quality of the response. The evaluation results are output as feedback data and sent to the terminal.

[0106] Step 6:

[0107] The terminal immediately displays feedback received from the server to the user. The input is feedback data from the server. The output is information presented to the user interface as areas for improvement and evaluation. This allows the user to understand the accuracy of their responses and use that information in future interactions.

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

[0109] This invention provides a sales training system utilizing AI that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training. The following is a detailed description of an embodiment of this system.

[0110] The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history, and is created in a way that can accommodate diverse sales scenarios. This information is stored in a database and used in subsequent training sessions.

[0111] The terminal presents sales scenarios on the user interface based on customer profiles received from the server. New employees can select training content from multiple scenarios. The selected scenario is prepared to initiate an interaction with a virtual customer as part of role-playing.

[0112] As a concrete example, a virtual customer, described as a "middle-aged woman with anxieties about a new product," is displayed on the device. The user communicates with this virtual customer by answering her questions and concerns within a sales scenario tailored to this profile.

[0113] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns to identify emotions in real time. This identification result is transmitted to the server for analysis.

[0114] The server analyzes the user's dialogue in more depth based on the emotional information reported by the emotion engine. This analysis takes into account not only the accuracy and appropriateness of the user's statements, but also an evaluation based on their emotional state.

[0115] The terminal immediately displays analysis results and feedback from the server to the user. The feedback includes an evaluation of the overall interaction, as well as a customized evaluation based on the user's emotional state. For example, feedback might include, "I was able to gain the trust of an anxious customer by explaining things calmly."

[0116] This system allows users to improve the skills necessary for real-world sales situations in a more comprehensive and human-centered way, and to enhance their ability to provide customer service that takes emotions and communication into consideration.

[0117] The following describes the processing flow.

[0118] Step 1:

[0119] The server uses an AI algorithm to generate a virtual customer profile. This profile reflects user attribute information such as age, gender, preferences, and purchase history, and is prepared as a diverse dataset capable of handling various sales scenarios.

[0120] Step 2:

[0121] The terminal displays sales scenarios on the user interface based on customer profiles retrieved from the server. Users can select a scenario they wish to train on from a list of multiple scenarios on this terminal.

[0122] Step 3:

[0123] The user selects a sales scenario of interest from the displayed list of scenarios and initiates a specific customer interaction based on the chosen scenario. This interaction takes place on the device, with a virtual customer posing questions and concerns to the user.

[0124] Step 4:

[0125] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns in real time during a conversation to identify the user's emotions. This analysis information is sent to a server and used for dialogue analysis.

[0126] Step 5:

[0127] The server analyzes the conversation in detail based on user responses and emotional information obtained from the emotion engine. It evaluates not only the accuracy and appropriateness of the user's statements, but also the emotional state related to their manner of speaking and attitude.

[0128] Step 6:

[0129] The device immediately displays feedback to the user based on analysis results from the server. This feedback includes an overall evaluation of the user's response, as well as suggestions for improvement and enhancements tailored to the detected emotions.

[0130] Step 7:

[0131] Users improve their sales skills and customer service abilities by receiving feedback on their devices and using it to inform future interactions. This feedback also promotes emotional awareness, enabling more effective learning.

[0132] (Example 2)

[0133] 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".

[0134] Traditional sales training has faced challenges in providing feedback that aligns with users' emotions, resulting in limitations in improving communication skills. In particular, it is difficult to learn how to respond appropriately and quickly when users encounter a variety of emotional states.

[0135] 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.

[0136] In this invention, the server includes an element for generating virtual customer information, an element for constructing a sales plan based on the customer information, and an element for analyzing voice and video to identify the user's emotions. This enables real-time feedback that responds to the user's emotional state.

[0137] "Virtual customer information" refers to attribute information about customers that do not actually exist but are generated for sales training purposes, including age, gender, preferences, and purchase history.

[0138] A "sales plan" is a sales scenario or strategy built on hypothetical customer information, intended for training in handling diverse customer interactions.

[0139] "Emotional identification" is a process of analyzing a user's voice and video to understand their emotional state at any given time. This process enables analysis based on the user's emotions.

[0140] "Real-time feedback" refers to evaluations and advice provided instantly to users during their interactions with virtual customers, and is a crucial element for improving the quality of those interactions.

[0141] This invention is an AI-powered sales training system that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training.

[0142] The server uses a "virtual customer generation algorithm" to generate virtual customer information. This algorithm constructs diverse virtual customers based on information such as age, gender, preferences, and consumption history obtained from the database. The generated customer information is stored in the database, and sales plans are formulated based on it.

[0143] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. The user selects a scenario from the presented sales plan and improves their sales skills through role-playing with a virtual customer. In this process, the terminal provides the user with a real-time, interactive experience.

[0144] During interactions with virtual customers, users need to adjust their communication as needed based on the customer's reactions. For example, when answering questions about a proposed product, they should provide explanations that address any concerns the customer may have.

[0145] The emotion engine identifies emotions by analyzing the user's facial expressions and voice. This engine utilizes "facial expression analysis technology" and "voice analysis technology" to capture changes in the user's tone and facial expressions in real time. This allows the user's emotional state to be transmitted to the server.

[0146] The server analyzes data from the emotion engine to evaluate user interactions in sales planning. This evaluation includes the accuracy, appropriateness, and quality of user statements. Furthermore, feedback is generated that reflects the user's emotions.

[0147] The device receives feedback from the server and presents it to the user in real time. The feedback includes specific advice on how the user effectively communicated with customers. For example, feedback might be presented such as, "I was able to gain the customer's trust by explaining things in a calm tone."

[0148] As a concrete example, consider a sales training scenario where the user is tasked with "explaining the benefits of an eco-friendly product." The user attempts to provide a clear and emotionally engaging explanation to pique the interest of a virtual customer. An example of a prompt input to the AI ​​model in this scenario would be, "Suggest an effective way to explain the features of an eco-friendly product."

[0149] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0150] Step 1:

[0151] The server retrieves basic customer information such as age, gender, preferences, and consumption history from the database. Using this information as input, a generative AI model generates virtual customer information. The generated customer information is stored in the database and used to build sales plans.

[0152] Step 2:

[0153] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. This plan is output as a user-selectable scenario, using the customer information as input. The user selects the scenario to train from among the displayed options.

[0154] Step 3:

[0155] The user begins role-playing based on a sales scenario selected on the device. The user engages in dialogue, answering customer questions and explaining product features. During this process, the user's words and actions are displayed as the virtual customer's reactions, allowing the user to respond appropriately based on these reactions.

[0156] Step 4:

[0157] The emotion engine analyzes the user's voice and facial expressions in real time. Using voice analysis and facial expression analysis technologies, it identifies the user's emotions. The emotion data obtained through the analysis is sent to a server and used as input for further analysis.

[0158] Step 5:

[0159] The server evaluates user interactions in sales plans by referencing emotional data input from the emotion engine and logs of user conversations. Through data analysis, it assesses the appropriateness of the conversation and the quality of emotional expression, generating feedback based on the results.

[0160] Step 6:

[0161] The terminal receives feedback from the server and presents it to the user in real time. The feedback consists of specific advice on the flow of the conversation and emotional expression, guiding the user to communicate more effectively. An example of such a comment might be, "Your calm explanation increased the customer's sense of security."

[0162] (Application Example 2)

[0163] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0164] In sales training, when aiming for practical and individualized skill improvement based on virtual sales scenarios, it has traditionally been difficult to consider the user's emotional state in real time. As a result, there was a problem in that users lacked the ability to respond in actual sales situations, and the quality of customer service could not be sufficiently improved.

[0165] 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.

[0166] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario, and means for sentiment analysis for identifying the user's emotional state. This enables the provision of customized feedback to the user in real time and allows for emotion-aware sales training.

[0167] A "virtual customer profile" is data about a hypothetical customer generated based on attribute information such as age, gender, preferences, and purchase history, and forms the basis of sales scenarios.

[0168] A "sales scenario" is a scenario used in sales training that concretely represents a conversational situation built based on a hypothetical customer profile.

[0169] "Means of providing feedback" refers to methods for analyzing user interactions in sales scenarios and using the results of that analysis to provide users with suggestions for improvement and evaluations.

[0170] "Emotional analysis means" refers to technology used to analyze a user's voice tone, facial expressions, and language patterns in order to identify their emotional state in real time.

[0171] "Customized feedback" refers to feedback that provides individually tailored evaluations and advice based on an analysis of the user's emotional state.

[0172] In an embodiment of this invention, the system includes three components: a server, a terminal, and a user. The server generates a virtual customer profile and builds a sales scenario based on it. The generated customer profile includes attribute information such as age, gender, preferences, and purchase history. This information is stored in a database and transmitted to the terminal.

[0173] The terminal has the ability to present sales scenarios on the user interface based on the received customer profile. The user selects a sales scenario and begins a conversation with a virtual customer. During the conversation, the terminal captures the user's voice and facial expressions and identifies emotions in real time using emotion analysis tools. This emotion analysis uses emotion analysis tools (e.g., Amazon Rekognition or Google Cloud Vision).

[0174] The identified sentiment information is sent to a server and analyzed by an AI model (e.g., TensorFlow or PyTorch). Based on this analysis, the server generates customized feedback and sends it to the device. The device immediately displays this feedback to the user to help improve their sales skills.

[0175] For example, when a user asks a virtual customer to "explain the new product," if their tone of voice is too high, feedback will be displayed recommending a calmer tone. This allows the user to learn how to communicate in a way that builds more trust.

[0176] An example of a prompt message is: "Generate the content of the feedback to be provided based on the sentiment analysis results. Virtual customer profile: Age: 45, Gender: Female, Interests: Technology-related; User's emotional state: Anxious."

[0177] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0178] Step 1:

[0179] The server generates virtual customer profiles. The input includes data on the customer's age, gender, preferences, and purchase history. This information is retrieved from the database to generate diverse profiles that can accommodate various sales scenarios. The output is the generated customer profile.

[0180] Step 2:

[0181] The server sends the generated customer profile to the terminal. The terminal receives this information and presents a sales scenario on the user interface. The user then selects the scenario to train. The input is the customer profile sent from the server, and the output is the sales scenario presented to the user.

[0182] Step 3:

[0183] The user initiates an interaction with a virtual customer. The terminal uses a microphone and camera to capture the user's voice and facial expressions. The input for this step is the user's voice and facial expressions, and the output is the captured data. This data is used for subsequent processing.

[0184] Step 4:

[0185] The terminal analyzes the captured data using emotion analysis tools. Here, voice tone, facial expressions, and language patterns are analyzed. The input is the voice and facial expression data obtained in the previous step, and the output is the identified emotional state. This emotional information is obtained as analysis results in real time.

[0186] Step 5:

[0187] The server receives the identified emotional state and analyzes the data using an AI model. The model evaluates the emotional state and the content of the conversation, and generates customized feedback. The input is emotional state data, and the output is specific feedback. It utilizes a generative AI model to respond flexibly.

[0188] Step 6:

[0189] The server sends the generated feedback to the terminal. The terminal immediately displays the feedback to the user. Here, the input is the feedback from the server, and the output is the displayed feedback. This feedback allows the user to improve their sales skills.

[0190] 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.

[0191] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0192] 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.

[0193] [Second Embodiment]

[0194] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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".

[0206] This invention provides an AI-powered sales training system aimed at improving the sales skills of new employees. The following describes its embodiments in natural language.

[0207] The server first uses an AI algorithm to generate a virtual customer profile. This profile includes attribute information such as age, gender, preferences, and purchase history, and various patterns are provided to ensure diversity in sales scenarios. The generated customer profiles are stored in a database and accessed for each training session.

[0208] The terminal displays sales scenarios on the user interface based on customer profiles received from the server. Multiple sales scenarios are listed on the screen, and new employees can select one to train on.

[0209] For example, the terminal might present a virtual customer profile such as "a male in his 30s who is a sports enthusiast and has frequently purchased outdoor equipment in the past." A new employee selects a sales scenario based on this profile, and then begins a simulated conversation with the customer within that scenario.

[0210] The user (a new employee) interacts with an AI acting as a customer, following a sales scenario presented on the terminal. The user answers customer questions and explains products. During the interaction, the user's responses are analyzed in real time by the server, and feedback is quickly returned to the terminal. Specifically, the quality of the responses is evaluated, such as "The product's benefits were clearly explained" or "The price explanation was unclear."

[0211] This training system allows new employees to efficiently acquire the skills to handle various virtual customers. Receiving immediate feedback allows them to identify areas for improvement on the spot and utilize this information in subsequent role-playing exercises. In this way, it promotes the immediate deployment of sales skills and contributes to the uniformity and quality of training.

[0212] The following describes the processing flow.

[0213] Step 1:

[0214] The server utilizes AI algorithms to generate virtual customer profiles. These profiles include attributes such as age, gender, preferences, and purchase history, creating a diverse set of profiles that can handle various sales scenarios. The generated profiles are stored in a database and accessed in later steps.

[0215] Step 2:

[0216] The terminal receives customer profile data from the server. Based on the received data, it displays a list of sales scenarios on the user interface. Multiple scenarios are presented on the screen so that the user (new employee) can make a selection.

[0217] Step 3:

[0218] The user selects the scenario they want to train on from the displayed list of scenarios. Based on the selected scenario, a specific sales scenario related to the customer profile is set up.

[0219] Step 4:

[0220] The device initiates a role-playing scenario with a virtual customer controlled by AI, according to the selected scenario. Questions and lines from the customer are displayed on the device, and the user responds to them.

[0221] Step 5:

[0222] Users respond appropriately to questions from a virtual customer during role-playing, using their own knowledge and skills. In doing so, they explain the product's features and benefits, attempting to engage in a conversation that convinces the customer.

[0223] Step 6:

[0224] The server analyzes user responses in real time and evaluates their content. Natural language processing technology is used for the analysis, evaluating the accuracy of the content and the appropriateness of the expression.

[0225] Step 7:

[0226] The terminal immediately displays feedback to the user regarding the server's response. This feedback includes both positive aspects of the response and areas for improvement, encouraging user understanding and improvement.

[0227] (Example 1)

[0228] 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."

[0229] Training new employees in sales presents a problem: the quality and efficiency of training vary due to individual differences in ability and lack of experience. In particular, developing effective communication skills in a practical setting requires experience dealing with a wide variety of customers, but this is difficult to achieve through conventional training methods.

[0230] 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.

[0231] In this invention, the server includes means for generating virtual attribute information, means for constructing a sales scenario based on the attribute information, and means for analyzing the content of the dialogue in the sales scenario and providing feedback. This enables sales training that anticipates various customer attributes, allowing users to efficiently acquire the ability to respond promptly to diverse situations.

[0232] "Virtual attribute information" refers to a data set that simulates customer characteristics and preferences, and includes information such as age, gender, hobbies, and purchase history.

[0233] A "sales scenario" is a scenario built based on virtual customer attributes, and is a simulation environment used by the user.

[0234] "Dialogue content analysis" is a process that analyzes the content of simulated conversations between users and AI in real time and evaluates how effective the conversations were.

[0235] The "means of providing feedback" refer to a system that, based on an analysis of the conversation content, immediately provides users with specific advice and evaluations to help them improve their sales skills.

[0236] A "user interface" is an interactive display method on a device screen that allows users to experience and interact with a story.

[0237] "Immediate analysis of dialogue records" refers to a process where the content of a conversation between the user and the AI ​​is analyzed immediately after it takes place, and the results are immediately fed back to the user.

[0238] This invention is an AI-powered sales training system aimed at improving the sales skills of new employees. The system consists of three components: a server, a terminal, and a user, each playing a specific role.

[0239] The server first generates virtual attribute information using an AI algorithm. This process utilizes a deep learning model. This virtual attribute information includes the customer's age, gender, preferences, and purchase history. This data serves as the foundation for providing diverse sales scenarios and is stored in a database. A specific example scenario might be "a 30-year-old male who enjoys sports and has frequently purchased outdoor equipment in the past."

[0240] The terminal presents sales scenarios via a user interface based on attribute information provided by the server. Here, a Python GUI library is used to display a list of sales scenarios. New employees can select a scenario of interest and begin an interaction according to that scenario. Depending on the selected scenario, detailed information and related product data are displayed on the screen.

[0241] Users interact with an AI acting as a customer, following a sales scenario presented on their device. A generative AI model is used, allowing the AI ​​to play the role of the customer. By answering questions about product benefits and pricing, users can hone their skills in a realistic setting. Feedback generated during the interaction is presented to the user in real time, allowing them to immediately identify areas for improvement.

[0242] A concrete example of a prompt message would be, "In this scenario, please provide an approach for selling outdoor equipment to a sports enthusiast in their 30s." In this way, sales skills can be improved in a more practical and efficient manner.

[0243] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0244] Step 1:

[0245] The server generates virtual attribute information. Past purchase data and general market trend data are used as input. AI algorithms, particularly deep learning models, are used to generate diverse customer profiles from this data. The output is virtual attribute information including age, gender, preferences, and purchase history, and is stored in a database in JSON format.

[0246] Step 2:

[0247] The terminal presents a sales scenario. It uses virtual attribute information received from the server as input. A Python GUI library is used to visually list multiple sales scenarios on the user interface. The user can select the scenario they are interested in. The output displays detailed information and related products based on the user's selected scenario.

[0248] Step 3:

[0249] The user initiates a dialogue based on a scenario. The input is a sales scenario displayed on the terminal. The user uses a generated AI model to interact with the customer-role AI, explaining product features and pricing based on the information presented. The output consists of the dialogue history and response data, which are sent to the server.

[0250] Step 4:

[0251] The server analyzes the user's responses. The input is the history of the user-AI interaction. A machine learning algorithm is used to evaluate the effectiveness and areas for improvement of the responses. The output is feedback data, which includes specific advice such as "The product features were explained appropriately" or "The price explanation is unclear." The feedback is generated in real time and sent to the terminal.

[0252] Step 5:

[0253] The device displays feedback to the user. It uses feedback data received from the server as input. The analyzed evaluation and advice are immediately displayed in the user interface. The output is information that encourages user performance improvement and can be used to improve future training sessions.

[0254] (Application Example 1)

[0255] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0256] Traditional sales training systems make it difficult to effectively acquire skills relevant to actual sales work in a short period of time. Furthermore, they have the problem of not being able to grasp training progress and challenges in real time and make immediate improvements. To enable in-store sales staff to perform their duties quickly and accurately on the job, these challenges need to be addressed.

[0257] 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.

[0258] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario based on the customer profile, and means for selecting a training scenario and initiating a virtual dialogue through a user interface operating on a portable electronic device. This enables users to conduct scenario-based training directly related to their daily sales activities on a mobile device and receive real-time feedback.

[0259] A "virtual customer profile" is fictional customer data generated based on attribute information such as age, gender, preferences, and purchase history, and is used to create diverse sales scenarios.

[0260] A "sales scenario" refers to a sales situation or scenario set up based on a hypothetical customer profile, and serves as the foundation for building a specific dialogue flow in sales training.

[0261] "Means of providing feedback" refers to a function that analyzes user responses and dialogue content in sales scenarios, evaluates their quality, and then presents users with areas for improvement in their training.

[0262] A "portable electronic device" refers to a portable electronic device, such as a smartphone or tablet, that presents training scenarios and provides an interface for conducting virtual dialogues.

[0263] "Methods for real-time analysis" refers to technologies that enable a rapid learning cycle by instantly analyzing the content of conversations and displaying feedback and progress records to the user each time.

[0264] The system for carrying out this invention includes a server, a portable electronic device (terminal), and a user. The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history. This allows for the preparation of diverse sales scenarios and enables the user to train in various situations.

[0265] The portable electronic device presents sales scenarios based on customer profiles received from a server. The user interface is developed using React Native, allowing users to select scenarios and engage in virtual dialogues. The device also sends the content of the dialogue to the server in real time, where it is analyzed using a natural language processing model (e.g., BERT) powered by TensorFlow.

[0266] The server analyzes user responses and provides immediate feedback. This allows users to understand their challenges and areas for improvement during training and apply that knowledge to future interactions. Real-time feedback helps users learn quickly and improve their sales skills.

[0267] As a concrete example, a user might select a virtual customer profile targeting an "outdoorsy woman in her 40s" and choose a scenario where this customer is looking for sunglasses. In this scenario, the user can explain the features and benefits of the product and receive feedback from the AI ​​such as, "Please explain the benefits of this product in more detail." This entire process allows the user to enhance their face-to-face customer service skills.

[0268] An example of a prompt to a generating AI might be: "The customer is looking for sunglasses. His preference is casual, and he intends to use them mainly for outdoor activities. How should we approach him?" By using this prompt, the AI ​​can be trained to construct conversations and learn more effective customer service methods.

[0269] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0270] Step 1:

[0271] The server uses an AI algorithm to generate virtual customer profiles. It receives data such as age, gender, preferences, and purchase history as input, and uses this information to construct profiles with diverse customer attributes. The output is the data of the generated customer profiles. This allows for a variety of sales scenarios.

[0272] Step 2:

[0273] The server transmits the generated customer profile to a portable electronic device (terminal). The input is the customer profile data on the server, which is output to the terminal via data transfer. The terminal uses the received data to display a list of sales scenarios on the user interface.

[0274] Step 3:

[0275] The user selects their desired sales scenario through the terminal interface. The input is a list of sales scenarios displayed on the terminal, and the user's selection triggers the output of specific scenario data. This output is the scenario data necessary for subsequent training.

[0276] Step 4:

[0277] The terminal initiates a virtual dialogue based on the selected sales scenario. The input is the user's selected scenario data, and a generative AI model is used to generate dialogue text based on this data. The output is presented to the user as the content of the dialogue with a virtual customer. In the dialogue generation process, prompt sentences are input to the AI ​​model, and dialogue appropriate to the scenario is generated.

[0278] Step 5:

[0279] The server analyzes the conversation content with the user in real time and generates evaluation feedback. The input is the user's conversation content data. This is analyzed using natural language processing techniques (TensorFlow and BERT models) to evaluate the quality of the response behavior. The evaluation result is output as feedback data and sent to the terminal.

[0280] Step 6:

[0281] The terminal immediately displays the feedback received from the server to the user. The input is the feedback data from the server. The output is the information presented to the user interface as improvement points and evaluation content. This allows the user to understand the accuracy of their own responses and utilize them in the next conversation.

[0282] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0283] This invention realizes more practical and individualized training in a sales training system utilizing AI by identifying the user's emotion and providing corresponding feedback. The following is a detailed description of the embodiments of this system.

[0284] The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history, and is created in a form that can handle various sales scenarios. This information is stored in a database and used in subsequent training sessions.

[0285] Based on the customer profile received from the server, the terminal presents a sales scenario on the user interface. New employees can select training content from multiple scenarios. The selected scenario is prepared to start a conversation with a virtual customer as part of role-playing.

[0286] As a specific example, a virtual customer named "Middle-aged woman with concerns about new products" is displayed on the terminal. The user proceeds with communication while answering the questions and doubts of the virtual customer within the sales scenario according to this profile.

[0287] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns to identify emotions in real-time. The identification result is transmitted to the server for analysis.

[0288] Based on the emotion information reported by the emotion engine, the server analyzes the user's conversation content more deeply. This analysis takes into account not only the accuracy and appropriateness of the user's speech content but also an evaluation according to the emotional state.

[0289] The terminal immediately displays the analysis results and feedback from the server to the user. The feedback includes an evaluation of the entire conversation as well as a customized evaluation based on the user's emotional state. For example, there may be feedback such as "By explaining gently to a customer with a sense of uneasiness, trust could be obtained."

[0290] With this system, the user can improve the necessary skills in a more three-dimensional and human-like manner in the actual sales situation, and strengthen the customer service ability considering emotions and communication.

[0291] The following describes the processing flow.

[0292] Step 1:

[0293] The server uses an AI algorithm to generate a virtual customer profile. This profile reflects user attribute information such as age, gender, preferences, and purchase history, and is prepared as a diverse dataset capable of handling various sales scenarios.

[0294] Step 2:

[0295] The terminal displays sales scenarios on the user interface based on customer profiles retrieved from the server. Users can select a scenario they wish to train on from a list of multiple scenarios on this terminal.

[0296] Step 3:

[0297] The user selects a sales scenario of interest from the displayed list of scenarios and initiates a specific customer interaction based on the chosen scenario. This interaction takes place on the device, with a virtual customer posing questions and concerns to the user.

[0298] Step 4:

[0299] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns in real time during a conversation to identify the user's emotions. This analysis information is sent to a server and used for dialogue analysis.

[0300] Step 5:

[0301] The server analyzes the conversation in detail based on user responses and emotional information obtained from the emotion engine. It evaluates not only the accuracy and appropriateness of the user's statements, but also the emotional state related to their manner of speaking and attitude.

[0302] Step 6:

[0303] The device immediately displays feedback to the user based on analysis results from the server. This feedback includes an overall evaluation of the user's response, as well as suggestions for improvement and enhancements tailored to the detected emotions.

[0304] Step 7:

[0305] The user receives feedback on the terminal and applies it to the next interaction, thereby enhancing their sales skills and customer service capabilities. This feedback also promotes awareness on the emotional level to enable more effective learning.

[0306] (Example 2)

[0307] Next, Example 2 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".

[0308] In conventional sales training, it has been difficult to provide feedback according to the user's emotions, resulting in a limitation in improving the interaction ability. In particular, it is difficult to learn appropriate and prompt responses when the user faces various emotional states.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0310] In this invention, the server includes an element for generating virtual customer information, an element for constructing a sales plan based on the customer information, and an element for analyzing voice and video to identify the user's emotions. This enables real-time feedback according to the user's emotional state.

[0311] "Virtual customer information" is attribute information about customers that does not actually exist but is generated for sales training, and includes age, gender, hobbies, and consumption history.

[0312] "Sales plan" is a sales scenario or strategy constructed based on virtual customer information and is intended for training in various customer interactions.

[0313] "Emotional identification" is a process of analyzing a user's voice and video to understand their emotional state at any given time. This process enables analysis based on the user's emotions.

[0314] "Real-time feedback" refers to evaluations and advice provided instantly to users during their interactions with virtual customers, and is a crucial element for improving the quality of those interactions.

[0315] This invention is an AI-powered sales training system that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training.

[0316] The server uses a "virtual customer generation algorithm" to generate virtual customer information. This algorithm constructs diverse virtual customers based on information such as age, gender, preferences, and consumption history obtained from the database. The generated customer information is stored in the database, and sales plans are formulated based on it.

[0317] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. The user selects a scenario from the presented sales plan and improves their sales skills through role-playing with a virtual customer. In this process, the terminal provides the user with a real-time, interactive experience.

[0318] During interactions with virtual customers, users need to adjust their communication as needed based on the customer's reactions. For example, when answering questions about a proposed product, they should provide explanations that address any concerns the customer may have.

[0319] The emotion engine identifies emotions by analyzing the user's facial expressions and voice. This engine utilizes "facial expression analysis technology" and "voice analysis technology" to capture changes in the user's tone and facial expressions in real time. This allows the user's emotional state to be transmitted to the server.

[0320] The server analyzes data from the emotion engine to evaluate user interactions in sales planning. This evaluation includes the accuracy, appropriateness, and quality of user statements. Furthermore, feedback is generated that reflects the user's emotions.

[0321] The device receives feedback from the server and presents it to the user in real time. The feedback includes specific advice on how the user effectively communicated with customers. For example, feedback might be presented such as, "I was able to gain the customer's trust by explaining things in a calm tone."

[0322] As a concrete example, consider a sales training scenario where the user is tasked with "explaining the benefits of an eco-friendly product." The user attempts to provide a clear and emotionally engaging explanation to pique the interest of a virtual customer. An example of a prompt input to the AI ​​model in this scenario would be, "Suggest an effective way to explain the features of an eco-friendly product."

[0323] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0324] Step 1:

[0325] The server retrieves basic customer information such as age, gender, preferences, and consumption history from the database. Using this information as input, a generative AI model generates virtual customer information. The generated customer information is stored in the database and used to build sales plans.

[0326] Step 2:

[0327] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. This plan is output as a user-selectable scenario, using the customer information as input. The user selects the scenario to train from among the displayed options.

[0328] Step 3:

[0329] The user begins role-playing based on a sales scenario selected on the device. The user engages in dialogue, answering customer questions and explaining product features. During this process, the user's words and actions are displayed as the virtual customer's reactions, allowing the user to respond appropriately based on these reactions.

[0330] Step 4:

[0331] The emotion engine analyzes the user's voice and facial expressions in real time. Using voice analysis and facial expression analysis technologies, it identifies the user's emotions. The emotion data obtained through the analysis is sent to a server and used as input for further analysis.

[0332] Step 5:

[0333] The server evaluates user interactions in sales plans by referencing emotional data input from the emotion engine and logs of user conversations. Through data analysis, it assesses the appropriateness of the conversation and the quality of emotional expression, generating feedback based on the results.

[0334] Step 6:

[0335] The terminal receives feedback from the server and presents it to the user in real time. The feedback consists of specific advice on the flow of the conversation and emotional expression, guiding the user to communicate more effectively. An example of such a comment might be, "Your calm explanation increased the customer's sense of security."

[0336] (Application Example 2)

[0337] 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."

[0338] In sales training, when aiming for practical and individualized skill improvement based on virtual sales scenarios, it has traditionally been difficult to consider the user's emotional state in real time. As a result, there was a problem in that users lacked the ability to respond in actual sales situations, and the quality of customer service could not be sufficiently improved.

[0339] 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.

[0340] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario, and means for sentiment analysis for identifying the user's emotional state. This enables the provision of customized feedback to the user in real time and allows for emotion-aware sales training.

[0341] A "virtual customer profile" is data about a hypothetical customer generated based on attribute information such as age, gender, preferences, and purchase history, and forms the basis of sales scenarios.

[0342] A "sales scenario" is a scenario used in sales training that concretely represents a conversational situation built based on a hypothetical customer profile.

[0343] "Means of providing feedback" refers to methods for analyzing user interactions in sales scenarios and using the results of that analysis to provide users with suggestions for improvement and evaluations.

[0344] "Emotional analysis means" refers to technology used to analyze a user's voice tone, facial expressions, and language patterns in order to identify their emotional state in real time.

[0345] "Customized feedback" refers to feedback that provides individually tailored evaluations and advice based on an analysis of the user's emotional state.

[0346] In an embodiment of this invention, the system includes three components: a server, a terminal, and a user. The server generates a virtual customer profile and builds a sales scenario based on it. The generated customer profile includes attribute information such as age, gender, preferences, and purchase history. This information is stored in a database and transmitted to the terminal.

[0347] The terminal has the ability to present sales scenarios on the user interface based on the received customer profile. The user selects a sales scenario and begins a conversation with a virtual customer. During the conversation, the terminal captures the user's voice and facial expressions and identifies emotions in real time using emotion analysis tools. This emotion analysis uses emotion analysis tools (e.g., Amazon Rekognition or Google Cloud Vision).

[0348] The identified sentiment information is sent to a server and analyzed by an AI model (e.g., TensorFlow or PyTorch). Based on this analysis, the server generates customized feedback and sends it to the device. The device immediately displays this feedback to the user to help improve their sales skills.

[0349] For example, when a user asks a virtual customer to "explain the new product," if their tone of voice is too high, feedback will be displayed recommending a calmer tone. This allows the user to learn how to communicate in a way that builds more trust.

[0350] An example of a prompt message is: "Generate the content of the feedback to be provided based on the sentiment analysis results. Virtual customer profile: Age: 45, Gender: Female, Interests: Technology-related; User's emotional state: Anxious."

[0351] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0352] Step 1:

[0353] The server generates virtual customer profiles. The input includes data on the customer's age, gender, preferences, and purchase history. This information is retrieved from the database to generate diverse profiles that can accommodate various sales scenarios. The output is the generated customer profile.

[0354] Step 2:

[0355] The server sends the generated customer profile to the terminal. The terminal receives this information and presents a sales scenario on the user interface. The user then selects the scenario to train. The input is the customer profile sent from the server, and the output is the sales scenario presented to the user.

[0356] Step 3:

[0357] The user initiates an interaction with a virtual customer. The terminal uses a microphone and camera to capture the user's voice and facial expressions. The input for this step is the user's voice and facial expressions, and the output is the captured data. This data is used for subsequent processing.

[0358] Step 4:

[0359] The terminal analyzes the captured data using emotion analysis tools. Here, voice tone, facial expressions, and language patterns are analyzed. The input is the voice and facial expression data obtained in the previous step, and the output is the identified emotional state. This emotional information is obtained as analysis results in real time.

[0360] Step 5:

[0361] The server receives the identified emotional state and analyzes the data using an AI model. The model evaluates the emotional state and the content of the conversation, and generates customized feedback. The input is emotional state data, and the output is specific feedback. It utilizes a generative AI model to respond flexibly.

[0362] Step 6:

[0363] The server sends the generated feedback to the terminal. The terminal immediately displays the feedback to the user. Here, the input is the feedback from the server, and the output is the displayed feedback. This feedback allows the user to improve their sales skills.

[0364] 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.

[0365] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0366] 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.

[0367] [Third Embodiment]

[0368] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0369] 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.

[0370] 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).

[0371] 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.

[0372] 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.

[0373] 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).

[0374] 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.

[0375] 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.

[0376] 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.

[0377] 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.

[0378] 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.

[0379] 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".

[0380] This invention provides an AI-powered sales training system aimed at improving the sales skills of new employees. The following describes its embodiments in natural language.

[0381] The server first uses an AI algorithm to generate a virtual customer profile. This profile includes attribute information such as age, gender, preferences, and purchase history, and various patterns are provided to ensure diversity in sales scenarios. The generated customer profiles are stored in a database and accessed for each training session.

[0382] The terminal displays sales scenarios on the user interface based on customer profiles received from the server. Multiple sales scenarios are listed on the screen, and new employees can select one to train on.

[0383] For example, the terminal might present a virtual customer profile such as "a male in his 30s who is a sports enthusiast and has frequently purchased outdoor equipment in the past." A new employee selects a sales scenario based on this profile, and then begins a simulated conversation with the customer within that scenario.

[0384] The user (a new employee) interacts with an AI acting as a customer, following a sales scenario presented on the terminal. The user answers customer questions and explains products. During the interaction, the user's responses are analyzed in real time by the server, and feedback is quickly returned to the terminal. Specifically, the quality of the responses is evaluated, such as "The product's benefits were clearly explained" or "The price explanation was unclear."

[0385] This training system allows new employees to efficiently acquire the skills to handle various virtual customers. Receiving immediate feedback allows them to identify areas for improvement on the spot and utilize this information in subsequent role-playing exercises. In this way, it promotes the immediate deployment of sales skills and contributes to the uniformity and quality of training.

[0386] The following describes the processing flow.

[0387] Step 1:

[0388] The server utilizes AI algorithms to generate virtual customer profiles. These profiles include attributes such as age, gender, preferences, and purchase history, creating a diverse set of profiles that can handle various sales scenarios. The generated profiles are stored in a database and accessed in later steps.

[0389] Step 2:

[0390] The terminal receives customer profile data from the server. Based on the received data, it displays a list of sales scenarios on the user interface. Multiple scenarios are presented on the screen so that the user (new employee) can make a selection.

[0391] Step 3:

[0392] The user selects the scenario they want to train on from the displayed list of scenarios. Based on the selected scenario, a specific sales scenario related to the customer profile is set up.

[0393] Step 4:

[0394] The device initiates a role-playing scenario with a virtual customer controlled by AI, according to the selected scenario. Questions and lines from the customer are displayed on the device, and the user responds to them.

[0395] Step 5:

[0396] Users respond appropriately to questions from a virtual customer during role-playing, using their own knowledge and skills. In doing so, they explain the product's features and benefits, attempting to engage in a conversation that convinces the customer.

[0397] Step 6:

[0398] The server analyzes user responses in real time and evaluates their content. Natural language processing technology is used for the analysis, evaluating the accuracy of the content and the appropriateness of the expression.

[0399] Step 7:

[0400] The terminal immediately displays feedback to the user regarding the server's response. This feedback includes both positive aspects of the response and areas for improvement, encouraging user understanding and improvement.

[0401] (Example 1)

[0402] 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."

[0403] Training new employees in sales presents a problem: the quality and efficiency of training vary due to individual differences in ability and lack of experience. In particular, developing effective communication skills in a practical setting requires experience dealing with a wide variety of customers, but this is difficult to achieve through conventional training methods.

[0404] 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.

[0405] In this invention, the server includes means for generating virtual attribute information, means for constructing a sales scenario based on the attribute information, and means for analyzing the content of the dialogue in the sales scenario and providing feedback. This enables sales training that anticipates various customer attributes, allowing users to efficiently acquire the ability to respond promptly to diverse situations.

[0406] "Virtual attribute information" refers to a data set that simulates customer characteristics and preferences, and includes information such as age, gender, hobbies, and purchase history.

[0407] A "sales scenario" is a scenario built based on virtual customer attributes, and is a simulation environment used by the user.

[0408] "Dialogue content analysis" is a process that analyzes the content of simulated conversations between users and AI in real time and evaluates how effective the conversations were.

[0409] The "means of providing feedback" refer to a system that, based on an analysis of the conversation content, immediately provides users with specific advice and evaluations to help them improve their sales skills.

[0410] A "user interface" is an interactive display method on a device screen that allows users to experience and interact with a story.

[0411] "Immediate analysis of dialogue records" refers to a process where the content of a conversation between the user and the AI ​​is analyzed immediately after it takes place, and the results are immediately fed back to the user.

[0412] This invention is an AI-powered sales training system aimed at improving the sales skills of new employees. The system consists of three components: a server, a terminal, and a user, each playing a specific role.

[0413] The server first generates virtual attribute information using an AI algorithm. This process utilizes a deep learning model. This virtual attribute information includes the customer's age, gender, preferences, and purchase history. This data serves as the foundation for providing diverse sales scenarios and is stored in a database. A specific example scenario might be "a 30-year-old male who enjoys sports and has frequently purchased outdoor equipment in the past."

[0414] The terminal presents sales scenarios via a user interface based on attribute information provided by the server. Here, a Python GUI library is used to display a list of sales scenarios. New employees can select a scenario of interest and begin an interaction according to that scenario. Depending on the selected scenario, detailed information and related product data are displayed on the screen.

[0415] Users interact with an AI acting as a customer, following a sales scenario presented on their device. A generative AI model is used, allowing the AI ​​to play the role of the customer. By answering questions about product benefits and pricing, users can hone their skills in a realistic setting. Feedback generated during the interaction is presented to the user in real time, allowing them to immediately identify areas for improvement.

[0416] A concrete example of a prompt message would be, "In this scenario, please provide an approach for selling outdoor equipment to a sports enthusiast in their 30s." In this way, sales skills can be improved in a more practical and efficient manner.

[0417] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0418] Step 1:

[0419] The server generates virtual attribute information. Past purchase data and general market trend data are used as input. AI algorithms, particularly deep learning models, are used to generate diverse customer profiles from this data. The output is virtual attribute information including age, gender, preferences, and purchase history, and is stored in a database in JSON format.

[0420] Step 2:

[0421] The terminal presents a sales scenario. It uses virtual attribute information received from the server as input. A Python GUI library is used to visually list multiple sales scenarios on the user interface. The user can select the scenario they are interested in. The output displays detailed information and related products based on the user's selected scenario.

[0422] Step 3:

[0423] The user initiates a dialogue based on a scenario. The input is a sales scenario displayed on the terminal. The user uses a generated AI model to interact with the customer-role AI, explaining product features and pricing based on the information presented. The output consists of the dialogue history and response data, which are sent to the server.

[0424] Step 4:

[0425] The server analyzes the user's responses. The input is the history of the user-AI interaction. A machine learning algorithm is used to evaluate the effectiveness and areas for improvement of the responses. The output is feedback data, which includes specific advice such as "The product features were explained appropriately" or "The price explanation is unclear." The feedback is generated in real time and sent to the terminal.

[0426] Step 5:

[0427] The device displays feedback to the user. It uses feedback data received from the server as input. The analyzed evaluation and advice are immediately displayed in the user interface. The output is information that encourages user performance improvement and can be used to improve future training sessions.

[0428] (Application Example 1)

[0429] 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."

[0430] Traditional sales training systems make it difficult to effectively acquire skills relevant to actual sales work in a short period of time. Furthermore, they have the problem of not being able to grasp training progress and challenges in real time and make immediate improvements. To enable in-store sales staff to perform their duties quickly and accurately on the job, these challenges need to be addressed.

[0431] 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.

[0432] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario based on the customer profile, and means for selecting a training scenario and initiating a virtual dialogue through a user interface operating on a portable electronic device. This enables users to conduct scenario-based training directly related to their daily sales activities on a mobile device and receive real-time feedback.

[0433] A "virtual customer profile" is fictional customer data generated based on attribute information such as age, gender, preferences, and purchase history, and is used to create diverse sales scenarios.

[0434] A "sales scenario" refers to a sales situation or scenario set up based on a hypothetical customer profile, and serves as the foundation for building a specific dialogue flow in sales training.

[0435] "Means of providing feedback" refers to a function that analyzes user responses and dialogue content in sales scenarios, evaluates their quality, and then presents users with areas for improvement in their training.

[0436] A "portable electronic device" refers to a portable electronic device, such as a smartphone or tablet, that presents training scenarios and provides an interface for conducting virtual dialogues.

[0437] "Methods for real-time analysis" refers to technologies that enable a rapid learning cycle by instantly analyzing the content of conversations and displaying feedback and progress records to the user each time.

[0438] The system for carrying out this invention includes a server, a portable electronic device (terminal), and a user. The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history. This allows for the preparation of diverse sales scenarios and enables the user to train in various situations.

[0439] The portable electronic device presents sales scenarios based on customer profiles received from a server. The user interface is developed using React Native, allowing users to select scenarios and engage in virtual dialogues. The device also sends the content of the dialogue to the server in real time, where it is analyzed using a natural language processing model (e.g., BERT) powered by TensorFlow.

[0440] The server analyzes user responses and provides immediate feedback. This allows users to understand their challenges and areas for improvement during training and apply that knowledge to future interactions. Real-time feedback helps users learn quickly and improve their sales skills.

[0441] As a concrete example, a user might select a virtual customer profile targeting an "outdoorsy woman in her 40s" and choose a scenario where this customer is looking for sunglasses. In this scenario, the user can explain the features and benefits of the product and receive feedback from the AI ​​such as, "Please explain the benefits of this product in more detail." This entire process allows the user to enhance their face-to-face customer service skills.

[0442] An example of a prompt to a generating AI might be: "The customer is looking for sunglasses. His preference is casual, and he intends to use them mainly for outdoor activities. How should we approach him?" By using this prompt, the AI ​​can be trained to construct conversations and learn more effective customer service methods.

[0443] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0444] Step 1:

[0445] The server uses an AI algorithm to generate virtual customer profiles. It receives data such as age, gender, preferences, and purchase history as input, and uses this information to construct profiles with diverse customer attributes. The output is the data of the generated customer profiles. This allows for a variety of sales scenarios.

[0446] Step 2:

[0447] The server transmits the generated customer profile to a portable electronic device (terminal). The input is the customer profile data on the server, which is output to the terminal via data transfer. The terminal uses the received data to display a list of sales scenarios on the user interface.

[0448] Step 3:

[0449] The user selects their desired sales scenario through the terminal interface. The input is a list of sales scenarios displayed on the terminal, and the user's selection triggers the output of specific scenario data. This output is the scenario data necessary for subsequent training.

[0450] Step 4:

[0451] The terminal initiates a virtual dialogue based on the selected sales scenario. The input is the user's selected scenario data, and a generative AI model is used to generate dialogue text based on this data. The output is presented to the user as the content of the dialogue with a virtual customer. In the dialogue generation process, prompt sentences are input to the AI ​​model, and dialogue appropriate to the scenario is generated.

[0452] Step 5:

[0453] The server analyzes user interactions in real time and generates evaluation feedback. The input is user interaction data. This data is analyzed using natural language processing techniques (TensorFlow and BERT model) to evaluate the quality of the response. The evaluation results are output as feedback data and sent to the terminal.

[0454] Step 6:

[0455] The terminal immediately displays feedback received from the server to the user. The input is feedback data from the server. The output is information presented to the user interface as areas for improvement and evaluation. This allows the user to understand the accuracy of their responses and use that information in future interactions.

[0456] 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.

[0457] This invention provides a sales training system utilizing AI that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training. The following is a detailed description of an embodiment of this system.

[0458] The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history, and is created in a way that can accommodate diverse sales scenarios. This information is stored in a database and used in subsequent training sessions.

[0459] The terminal presents sales scenarios on the user interface based on customer profiles received from the server. New employees can select training content from multiple scenarios. The selected scenario is prepared to initiate an interaction with a virtual customer as part of role-playing.

[0460] As a concrete example, a virtual customer, described as a "middle-aged woman with anxieties about a new product," is displayed on the device. The user communicates with this virtual customer by answering her questions and concerns within a sales scenario tailored to this profile.

[0461] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns to identify emotions in real time. This identification result is transmitted to the server for analysis.

[0462] The server analyzes the user's dialogue in more depth based on the emotional information reported by the emotion engine. This analysis takes into account not only the accuracy and appropriateness of the user's statements, but also an evaluation based on their emotional state.

[0463] The terminal immediately displays analysis results and feedback from the server to the user. The feedback includes an evaluation of the overall interaction, as well as a customized evaluation based on the user's emotional state. For example, feedback might include, "I was able to gain the trust of an anxious customer by explaining things calmly."

[0464] This system allows users to improve the skills necessary for real-world sales situations in a more comprehensive and human-centered way, and to enhance their ability to provide customer service that takes emotions and communication into consideration.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The server uses an AI algorithm to generate a virtual customer profile. This profile reflects user attribute information such as age, gender, preferences, and purchase history, and is prepared as a diverse dataset capable of handling various sales scenarios.

[0468] Step 2:

[0469] The terminal displays sales scenarios on the user interface based on customer profiles retrieved from the server. Users can select a scenario they wish to train on from a list of multiple scenarios on this terminal.

[0470] Step 3:

[0471] The user selects a sales scenario of interest from the displayed list of scenarios and initiates a specific customer interaction based on the chosen scenario. This interaction takes place on the device, with a virtual customer posing questions and concerns to the user.

[0472] Step 4:

[0473] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns in real time during a conversation to identify the user's emotions. This analysis information is sent to a server and used for dialogue analysis.

[0474] Step 5:

[0475] The server analyzes the conversation in detail based on user responses and emotional information obtained from the emotion engine. It evaluates not only the accuracy and appropriateness of the user's statements, but also the emotional state related to their manner of speaking and attitude.

[0476] Step 6:

[0477] The device immediately displays feedback to the user based on analysis results from the server. This feedback includes an overall evaluation of the user's response, as well as suggestions for improvement and enhancements tailored to the detected emotions.

[0478] Step 7:

[0479] Users improve their sales skills and customer service abilities by receiving feedback on their devices and using it to inform future interactions. This feedback also promotes emotional awareness, enabling more effective learning.

[0480] (Example 2)

[0481] 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."

[0482] Traditional sales training has faced challenges in providing feedback that aligns with users' emotions, resulting in limitations in improving communication skills. In particular, it is difficult to learn how to respond appropriately and quickly when users encounter a variety of emotional states.

[0483] 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.

[0484] In this invention, the server includes an element for generating virtual customer information, an element for constructing a sales plan based on the customer information, and an element for analyzing voice and video to identify the user's emotions. This enables real-time feedback that responds to the user's emotional state.

[0485] "Virtual customer information" refers to attribute information about customers that do not actually exist but are generated for sales training purposes, including age, gender, preferences, and purchase history.

[0486] A "sales plan" is a sales scenario or strategy built on hypothetical customer information, intended for training in handling diverse customer interactions.

[0487] "Emotional identification" is a process of analyzing a user's voice and video to understand their emotional state at any given time. This process enables analysis based on the user's emotions.

[0488] "Real-time feedback" refers to evaluations and advice provided instantly to users during their interactions with virtual customers, and is a crucial element for improving the quality of those interactions.

[0489] This invention is an AI-powered sales training system that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training.

[0490] The server uses a "virtual customer generation algorithm" to generate virtual customer information. This algorithm constructs diverse virtual customers based on information such as age, gender, preferences, and consumption history obtained from the database. The generated customer information is stored in the database, and sales plans are formulated based on it.

[0491] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. The user selects a scenario from the presented sales plan and improves their sales skills through role-playing with a virtual customer. In this process, the terminal provides the user with a real-time, interactive experience.

[0492] During interactions with virtual customers, users need to adjust their communication as needed based on the customer's reactions. For example, when answering questions about a proposed product, they should provide explanations that address any concerns the customer may have.

[0493] The emotion engine identifies emotions by analyzing the user's facial expressions and voice. This engine utilizes "facial expression analysis technology" and "voice analysis technology" to capture changes in the user's tone and facial expressions in real time. This allows the user's emotional state to be transmitted to the server.

[0494] The server analyzes data from the emotion engine to evaluate user interactions in sales planning. This evaluation includes the accuracy, appropriateness, and quality of user statements. Furthermore, feedback is generated that reflects the user's emotions.

[0495] The device receives feedback from the server and presents it to the user in real time. The feedback includes specific advice on how the user effectively communicated with customers. For example, feedback might be presented such as, "I was able to gain the customer's trust by explaining things in a calm tone."

[0496] As a concrete example, consider a sales training scenario where the user is tasked with "explaining the benefits of an eco-friendly product." The user attempts to provide a clear and emotionally engaging explanation to pique the interest of a virtual customer. An example of a prompt input to the AI ​​model in this scenario would be, "Suggest an effective way to explain the features of an eco-friendly product."

[0497] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0498] Step 1:

[0499] The server retrieves basic customer information such as age, gender, preferences, and consumption history from the database. Using this information as input, a generative AI model generates virtual customer information. The generated customer information is stored in the database and used to build sales plans.

[0500] Step 2:

[0501] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. This plan is output as a user-selectable scenario, using the customer information as input. The user selects the scenario to train from among the displayed options.

[0502] Step 3:

[0503] The user begins role-playing based on a sales scenario selected on the device. The user engages in dialogue, answering customer questions and explaining product features. During this process, the user's words and actions are displayed as the virtual customer's reactions, allowing the user to respond appropriately based on these reactions.

[0504] Step 4:

[0505] The emotion engine analyzes the user's voice and facial expressions in real time. Using voice analysis and facial expression analysis technologies, it identifies the user's emotions. The emotion data obtained through the analysis is sent to a server and used as input for further analysis.

[0506] Step 5:

[0507] The server evaluates user interactions in sales plans by referencing emotional data input from the emotion engine and logs of user conversations. Through data analysis, it assesses the appropriateness of the conversation and the quality of emotional expression, generating feedback based on the results.

[0508] Step 6:

[0509] The terminal receives feedback from the server and presents it to the user in real time. The feedback consists of specific advice on the flow of the conversation and emotional expression, guiding the user to communicate more effectively. An example of such a comment might be, "Your calm explanation increased the customer's sense of security."

[0510] (Application Example 2)

[0511] 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."

[0512] In sales training, when aiming for practical and individualized skill improvement based on virtual sales scenarios, it has traditionally been difficult to consider the user's emotional state in real time. As a result, there was a problem in that users lacked the ability to respond in actual sales situations, and the quality of customer service could not be sufficiently improved.

[0513] 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.

[0514] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario, and means for sentiment analysis for identifying the user's emotional state. This enables the provision of customized feedback to the user in real time and allows for emotion-aware sales training.

[0515] A "virtual customer profile" is data about a hypothetical customer generated based on attribute information such as age, gender, preferences, and purchase history, and forms the basis of sales scenarios.

[0516] A "sales scenario" is a scenario used in sales training that concretely represents a conversational situation built based on a hypothetical customer profile.

[0517] "Means of providing feedback" refers to methods for analyzing user interactions in sales scenarios and using the results of that analysis to provide users with suggestions for improvement and evaluations.

[0518] "Emotional analysis means" refers to technology used to analyze a user's voice tone, facial expressions, and language patterns in order to identify their emotional state in real time.

[0519] "Customized feedback" refers to feedback that provides individually tailored evaluations and advice based on an analysis of the user's emotional state.

[0520] In an embodiment of this invention, the system includes three components: a server, a terminal, and a user. The server generates a virtual customer profile and builds a sales scenario based on it. The generated customer profile includes attribute information such as age, gender, preferences, and purchase history. This information is stored in a database and transmitted to the terminal.

[0521] The terminal has the ability to present sales scenarios on the user interface based on the received customer profile. The user selects a sales scenario and begins a conversation with a virtual customer. During the conversation, the terminal captures the user's voice and facial expressions and identifies emotions in real time using emotion analysis tools. This emotion analysis uses emotion analysis tools (e.g., Amazon Rekognition or Google Cloud Vision).

[0522] The identified sentiment information is sent to a server and analyzed by an AI model (e.g., TensorFlow or PyTorch). Based on this analysis, the server generates customized feedback and sends it to the device. The device immediately displays this feedback to the user to help improve their sales skills.

[0523] For example, when a user asks a virtual customer to "explain the new product," if their tone of voice is too high, feedback will be displayed recommending a calmer tone. This allows the user to learn how to communicate in a way that builds more trust.

[0524] An example of a prompt message is: "Generate the content of the feedback to be provided based on the sentiment analysis results. Virtual customer profile: Age: 45, Gender: Female, Interests: Technology-related; User's emotional state: Anxious."

[0525] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0526] Step 1:

[0527] The server generates virtual customer profiles. The input includes data on the customer's age, gender, preferences, and purchase history. This information is retrieved from the database to generate diverse profiles that can accommodate various sales scenarios. The output is the generated customer profile.

[0528] Step 2:

[0529] The server sends the generated customer profile to the terminal. The terminal receives this information and presents a sales scenario on the user interface. The user then selects the scenario to train. The input is the customer profile sent from the server, and the output is the sales scenario presented to the user.

[0530] Step 3:

[0531] The user initiates an interaction with a virtual customer. The terminal uses a microphone and camera to capture the user's voice and facial expressions. The input for this step is the user's voice and facial expressions, and the output is the captured data. This data is used for subsequent processing.

[0532] Step 4:

[0533] The terminal analyzes the captured data using emotion analysis tools. Here, voice tone, facial expressions, and language patterns are analyzed. The input is the voice and facial expression data obtained in the previous step, and the output is the identified emotional state. This emotional information is obtained as analysis results in real time.

[0534] Step 5:

[0535] The server receives the identified emotional state and analyzes the data using an AI model. The model evaluates the emotional state and the content of the conversation, and generates customized feedback. The input is emotional state data, and the output is specific feedback. It utilizes a generative AI model to respond flexibly.

[0536] Step 6:

[0537] The server sends the generated feedback to the terminal. The terminal immediately displays the feedback to the user. Here, the input is the feedback from the server, and the output is the displayed feedback. This feedback allows the user to improve their sales skills.

[0538] 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.

[0539] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0540] 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.

[0541] [Fourth Embodiment]

[0542] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0543] 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.

[0544] 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).

[0545] 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.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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".

[0555] This invention provides an AI-powered sales training system aimed at improving the sales skills of new employees. The following describes its embodiments in natural language.

[0556] The server first uses an AI algorithm to generate a virtual customer profile. This profile includes attribute information such as age, gender, preferences, and purchase history, and various patterns are provided to ensure diversity in sales scenarios. The generated customer profiles are stored in a database and accessed for each training session.

[0557] The terminal displays sales scenarios on the user interface based on customer profiles received from the server. Multiple sales scenarios are listed on the screen, and new employees can select one to train on.

[0558] For example, the terminal might present a virtual customer profile such as "a male in his 30s who is a sports enthusiast and has frequently purchased outdoor equipment in the past." A new employee selects a sales scenario based on this profile, and then begins a simulated conversation with the customer within that scenario.

[0559] The user (a new employee) interacts with an AI acting as a customer, following a sales scenario presented on the terminal. The user answers customer questions and explains products. During the interaction, the user's responses are analyzed in real time by the server, and feedback is quickly returned to the terminal. Specifically, the quality of the responses is evaluated, such as "The product's benefits were clearly explained" or "The price explanation was unclear."

[0560] This training system allows new employees to efficiently acquire the skills to handle various virtual customers. Receiving immediate feedback allows them to identify areas for improvement on the spot and utilize this information in subsequent role-playing exercises. In this way, it promotes the immediate deployment of sales skills and contributes to the uniformity and quality of training.

[0561] The following describes the processing flow.

[0562] Step 1:

[0563] The server utilizes AI algorithms to generate virtual customer profiles. These profiles include attributes such as age, gender, preferences, and purchase history, creating a diverse set of profiles that can handle various sales scenarios. The generated profiles are stored in a database and accessed in later steps.

[0564] Step 2:

[0565] The terminal receives customer profile data from the server. Based on the received data, it displays a list of sales scenarios on the user interface. Multiple scenarios are presented on the screen so that the user (new employee) can make a selection.

[0566] Step 3:

[0567] The user selects the scenario they want to train on from the displayed list of scenarios. Based on the selected scenario, a specific sales scenario related to the customer profile is set up.

[0568] Step 4:

[0569] The device initiates a role-playing scenario with a virtual customer controlled by AI, according to the selected scenario. Questions and lines from the customer are displayed on the device, and the user responds to them.

[0570] Step 5:

[0571] Users respond appropriately to questions from a virtual customer during role-playing, using their own knowledge and skills. In doing so, they explain the product's features and benefits, attempting to engage in a conversation that convinces the customer.

[0572] Step 6:

[0573] The server analyzes user responses in real time and evaluates their content. Natural language processing technology is used for the analysis, evaluating the accuracy of the content and the appropriateness of the expression.

[0574] Step 7:

[0575] The terminal immediately displays feedback to the user regarding the server's response. This feedback includes both positive aspects of the response and areas for improvement, encouraging user understanding and improvement.

[0576] (Example 1)

[0577] 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".

[0578] Training new employees in sales presents a problem: the quality and efficiency of training vary due to individual differences in ability and lack of experience. In particular, developing effective communication skills in a practical setting requires experience dealing with a wide variety of customers, but this is difficult to achieve through conventional training methods.

[0579] 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.

[0580] In this invention, the server includes means for generating virtual attribute information, means for constructing a sales scenario based on the attribute information, and means for analyzing the content of the dialogue in the sales scenario and providing feedback. This enables sales training that anticipates various customer attributes, allowing users to efficiently acquire the ability to respond promptly to diverse situations.

[0581] "Virtual attribute information" refers to a data set that simulates customer characteristics and preferences, and includes information such as age, gender, hobbies, and purchase history.

[0582] A "sales scenario" is a scenario built based on virtual customer attributes, and is a simulation environment used by the user.

[0583] "Dialogue content analysis" is a process that analyzes the content of simulated conversations between users and AI in real time and evaluates how effective the conversations were.

[0584] The "means of providing feedback" refer to a system that, based on an analysis of the conversation content, immediately provides users with specific advice and evaluations to help them improve their sales skills.

[0585] A "user interface" is an interactive display method on a device screen that allows users to experience and interact with a story.

[0586] "Immediate analysis of dialogue records" refers to a process where the content of a conversation between the user and the AI ​​is analyzed immediately after it takes place, and the results are immediately fed back to the user.

[0587] This invention is an AI-powered sales training system aimed at improving the sales skills of new employees. The system consists of three components: a server, a terminal, and a user, each playing a specific role.

[0588] The server first generates virtual attribute information using an AI algorithm. This process utilizes a deep learning model. This virtual attribute information includes the customer's age, gender, preferences, and purchase history. This data serves as the foundation for providing diverse sales scenarios and is stored in a database. A specific example scenario might be "a 30-year-old male who enjoys sports and has frequently purchased outdoor equipment in the past."

[0589] The terminal presents sales scenarios via a user interface based on attribute information provided by the server. Here, a Python GUI library is used to display a list of sales scenarios. New employees can select a scenario of interest and begin an interaction according to that scenario. Depending on the selected scenario, detailed information and related product data are displayed on the screen.

[0590] Users interact with an AI acting as a customer, following a sales scenario presented on their device. A generative AI model is used, allowing the AI ​​to play the role of the customer. By answering questions about product benefits and pricing, users can hone their skills in a realistic setting. Feedback generated during the interaction is presented to the user in real time, allowing them to immediately identify areas for improvement.

[0591] A concrete example of a prompt message would be, "In this scenario, please provide an approach for selling outdoor equipment to a sports enthusiast in their 30s." In this way, sales skills can be improved in a more practical and efficient manner.

[0592] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0593] Step 1:

[0594] The server generates virtual attribute information. Past purchase data and general market trend data are used as input. AI algorithms, particularly deep learning models, are used to generate diverse customer profiles from this data. The output is virtual attribute information including age, gender, preferences, and purchase history, and is stored in a database in JSON format.

[0595] Step 2:

[0596] The terminal presents a sales scenario. It uses virtual attribute information received from the server as input. A Python GUI library is used to visually list multiple sales scenarios on the user interface. The user can select the scenario they are interested in. The output displays detailed information and related products based on the user's selected scenario.

[0597] Step 3:

[0598] The user initiates a dialogue based on a scenario. The input is a sales scenario displayed on the terminal. The user uses a generated AI model to interact with the customer-role AI, explaining product features and pricing based on the information presented. The output consists of the dialogue history and response data, which are sent to the server.

[0599] Step 4:

[0600] The server analyzes the user's responses. The input is the history of the user-AI interaction. A machine learning algorithm is used to evaluate the effectiveness and areas for improvement of the responses. The output is feedback data, which includes specific advice such as "The product features were explained appropriately" or "The price explanation is unclear." The feedback is generated in real time and sent to the terminal.

[0601] Step 5:

[0602] The device displays feedback to the user. It uses feedback data received from the server as input. The analyzed evaluation and advice are immediately displayed in the user interface. The output is information that encourages user performance improvement and can be used to improve future training sessions.

[0603] (Application Example 1)

[0604] 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".

[0605] Traditional sales training systems make it difficult to effectively acquire skills relevant to actual sales work in a short period of time. Furthermore, they have the problem of not being able to grasp training progress and challenges in real time and make immediate improvements. To enable in-store sales staff to perform their duties quickly and accurately on the job, these challenges need to be addressed.

[0606] 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.

[0607] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario based on the customer profile, and means for selecting a training scenario and initiating a virtual dialogue through a user interface operating on a portable electronic device. This enables users to conduct scenario-based training directly related to their daily sales activities on a mobile device and receive real-time feedback.

[0608] A "virtual customer profile" is fictional customer data generated based on attribute information such as age, gender, preferences, and purchase history, and is used to create diverse sales scenarios.

[0609] A "sales scenario" refers to a sales situation or scenario set up based on a hypothetical customer profile, and serves as the foundation for building a specific dialogue flow in sales training.

[0610] "Means of providing feedback" refers to a function that analyzes user responses and dialogue content in sales scenarios, evaluates their quality, and then presents users with areas for improvement in their training.

[0611] A "portable electronic device" refers to a portable electronic device, such as a smartphone or tablet, that presents training scenarios and provides an interface for conducting virtual dialogues.

[0612] "Methods for real-time analysis" refers to technologies that enable a rapid learning cycle by instantly analyzing the content of conversations and displaying feedback and progress records to the user each time.

[0613] The system for carrying out this invention includes a server, a portable electronic device (terminal), and a user. The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history. This allows for the preparation of diverse sales scenarios and enables the user to train in various situations.

[0614] The portable electronic device presents sales scenarios based on customer profiles received from a server. The user interface is developed using React Native, allowing users to select scenarios and engage in virtual dialogues. The device also sends the content of the dialogue to the server in real time, where it is analyzed using a natural language processing model (e.g., BERT) powered by TensorFlow.

[0615] The server analyzes user responses and provides immediate feedback. This allows users to understand their challenges and areas for improvement during training and apply that knowledge to future interactions. Real-time feedback helps users learn quickly and improve their sales skills.

[0616] As a concrete example, a user might select a virtual customer profile targeting an "outdoorsy woman in her 40s" and choose a scenario where this customer is looking for sunglasses. In this scenario, the user can explain the features and benefits of the product and receive feedback from the AI ​​such as, "Please explain the benefits of this product in more detail." This entire process allows the user to enhance their face-to-face customer service skills.

[0617] An example of a prompt to a generating AI might be: "The customer is looking for sunglasses. His preference is casual, and he intends to use them mainly for outdoor activities. How should we approach him?" By using this prompt, the AI ​​can be trained to construct conversations and learn more effective customer service methods.

[0618] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0619] Step 1:

[0620] The server uses an AI algorithm to generate virtual customer profiles. It receives data such as age, gender, preferences, and purchase history as input, and uses this information to construct profiles with diverse customer attributes. The output is the data of the generated customer profiles. This allows for a variety of sales scenarios.

[0621] Step 2:

[0622] The server transmits the generated customer profile to a portable electronic device (terminal). The input is the customer profile data on the server, which is output to the terminal via data transfer. The terminal uses the received data to display a list of sales scenarios on the user interface.

[0623] Step 3:

[0624] The user selects their desired sales scenario through the terminal interface. The input is a list of sales scenarios displayed on the terminal, and the user's selection triggers the output of specific scenario data. This output is the scenario data necessary for subsequent training.

[0625] Step 4:

[0626] The terminal initiates a virtual dialogue based on the selected sales scenario. The input is the user's selected scenario data, and a generative AI model is used to generate dialogue text based on this data. The output is presented to the user as the content of the dialogue with a virtual customer. In the dialogue generation process, prompt sentences are input to the AI ​​model, and dialogue appropriate to the scenario is generated.

[0627] Step 5:

[0628] The server analyzes user interactions in real time and generates evaluation feedback. The input is user interaction data. This data is analyzed using natural language processing techniques (TensorFlow and BERT model) to evaluate the quality of the response. The evaluation results are output as feedback data and sent to the terminal.

[0629] Step 6:

[0630] The terminal immediately displays feedback received from the server to the user. The input is feedback data from the server. The output is information presented to the user interface as areas for improvement and evaluation. This allows the user to understand the accuracy of their responses and use that information in future interactions.

[0631] 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.

[0632] This invention provides a sales training system utilizing AI that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training. The following is a detailed description of an embodiment of this system.

[0633] The server generates a virtual customer profile using an AI algorithm. This profile includes attribute information such as age, gender, preferences, and purchase history, and is created in a way that can accommodate diverse sales scenarios. This information is stored in a database and used in subsequent training sessions.

[0634] The terminal presents sales scenarios on the user interface based on customer profiles received from the server. New employees can select training content from multiple scenarios. The selected scenario is prepared to initiate an interaction with a virtual customer as part of role-playing.

[0635] As a concrete example, a virtual customer, described as a "middle-aged woman with anxieties about a new product," is displayed on the device. The user communicates with this virtual customer by answering her questions and concerns within a sales scenario tailored to this profile.

[0636] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns to identify emotions in real time. This identification result is transmitted to the server for analysis.

[0637] The server analyzes the user's dialogue in more depth based on the emotional information reported by the emotion engine. This analysis takes into account not only the accuracy and appropriateness of the user's statements, but also an evaluation based on their emotional state.

[0638] The terminal immediately displays analysis results and feedback from the server to the user. The feedback includes an evaluation of the overall interaction, as well as a customized evaluation based on the user's emotional state. For example, feedback might include, "I was able to gain the trust of an anxious customer by explaining things calmly."

[0639] This system allows users to improve the skills necessary for real-world sales situations in a more comprehensive and human-centered way, and to enhance their ability to provide customer service that takes emotions and communication into consideration.

[0640] The following describes the processing flow.

[0641] Step 1:

[0642] The server uses an AI algorithm to generate a virtual customer profile. This profile reflects user attribute information such as age, gender, preferences, and purchase history, and is prepared as a diverse dataset capable of handling various sales scenarios.

[0643] Step 2:

[0644] The terminal displays sales scenarios on the user interface based on customer profiles retrieved from the server. Users can select a scenario they wish to train on from a list of multiple scenarios on this terminal.

[0645] Step 3:

[0646] The user selects a sales scenario of interest from the displayed list of scenarios and initiates a specific customer interaction based on the chosen scenario. This interaction takes place on the device, with a virtual customer posing questions and concerns to the user.

[0647] Step 4:

[0648] The emotion engine analyzes the user's voice tone, facial expressions, and language patterns in real time during a conversation to identify the user's emotions. This analysis information is sent to a server and used for dialogue analysis.

[0649] Step 5:

[0650] The server analyzes the conversation in detail based on user responses and emotional information obtained from the emotion engine. It evaluates not only the accuracy and appropriateness of the user's statements, but also the emotional state related to their manner of speaking and attitude.

[0651] Step 6:

[0652] The device immediately displays feedback to the user based on analysis results from the server. This feedback includes an overall evaluation of the user's response, as well as suggestions for improvement and enhancements tailored to the detected emotions.

[0653] Step 7:

[0654] Users improve their sales skills and customer service abilities by receiving feedback on their devices and using it to inform future interactions. This feedback also promotes emotional awareness, enabling more effective learning.

[0655] (Example 2)

[0656] 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".

[0657] Traditional sales training has faced challenges in providing feedback that aligns with users' emotions, resulting in limitations in improving communication skills. In particular, it is difficult to learn how to respond appropriately and quickly when users encounter a variety of emotional states.

[0658] 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.

[0659] In this invention, the server includes an element for generating virtual customer information, an element for constructing a sales plan based on the customer information, and an element for analyzing voice and video to identify the user's emotions. This enables real-time feedback that responds to the user's emotional state.

[0660] "Virtual customer information" refers to attribute information about customers that do not actually exist but are generated for sales training purposes, including age, gender, preferences, and purchase history.

[0661] A "sales plan" is a sales scenario or strategy built on hypothetical customer information, intended for training in handling diverse customer interactions.

[0662] "Emotional identification" is a process of analyzing a user's voice and video to understand their emotional state at any given time. This process enables analysis based on the user's emotions.

[0663] "Real-time feedback" refers to evaluations and advice provided instantly to users during their interactions with virtual customers, and is a crucial element for improving the quality of those interactions.

[0664] This invention is an AI-powered sales training system that identifies user emotions and provides corresponding feedback, thereby achieving more practical and personalized training.

[0665] The server uses a "virtual customer generation algorithm" to generate virtual customer information. This algorithm constructs diverse virtual customers based on information such as age, gender, preferences, and consumption history obtained from the database. The generated customer information is stored in the database, and sales plans are formulated based on it.

[0666] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. The user selects a scenario from the presented sales plan and improves their sales skills through role-playing with a virtual customer. In this process, the terminal provides the user with a real-time, interactive experience.

[0667] During interactions with virtual customers, users need to adjust their communication as needed based on the customer's reactions. For example, when answering questions about a proposed product, they should provide explanations that address any concerns the customer may have.

[0668] The emotion engine identifies emotions by analyzing the user's facial expressions and voice. This engine utilizes "facial expression analysis technology" and "voice analysis technology" to capture changes in the user's tone and facial expressions in real time. This allows the user's emotional state to be transmitted to the server.

[0669] The server analyzes data from the emotion engine to evaluate user interactions in sales planning. This evaluation includes the accuracy, appropriateness, and quality of user statements. Furthermore, feedback is generated that reflects the user's emotions.

[0670] The device receives feedback from the server and presents it to the user in real time. The feedback includes specific advice on how the user effectively communicated with customers. For example, feedback might be presented such as, "I was able to gain the customer's trust by explaining things in a calm tone."

[0671] As a concrete example, consider a sales training scenario where the user is tasked with "explaining the benefits of an eco-friendly product." The user attempts to provide a clear and emotionally engaging explanation to pique the interest of a virtual customer. An example of a prompt input to the AI ​​model in this scenario would be, "Suggest an effective way to explain the features of an eco-friendly product."

[0672] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0673] Step 1:

[0674] The server retrieves basic customer information such as age, gender, preferences, and consumption history from the database. Using this information as input, a generative AI model generates virtual customer information. The generated customer information is stored in the database and used to build sales plans.

[0675] Step 2:

[0676] The terminal displays a sales plan on the user interface based on virtual customer information received from the server. This plan is output as a user-selectable scenario, using the customer information as input. The user selects the scenario to train from among the displayed options.

[0677] Step 3:

[0678] The user begins role-playing based on a sales scenario selected on the device. The user engages in dialogue, answering customer questions and explaining product features. During this process, the user's words and actions are displayed as the virtual customer's reactions, allowing the user to respond appropriately based on these reactions.

[0679] Step 4:

[0680] The emotion engine analyzes the user's voice and facial expressions in real time. Using voice analysis and facial expression analysis technologies, it identifies the user's emotions. The emotion data obtained through the analysis is sent to a server and used as input for further analysis.

[0681] Step 5:

[0682] The server evaluates user interactions in sales plans by referencing emotional data input from the emotion engine and logs of user conversations. Through data analysis, it assesses the appropriateness of the conversation and the quality of emotional expression, generating feedback based on the results.

[0683] Step 6:

[0684] The terminal receives feedback from the server and presents it to the user in real time. The feedback consists of specific advice on the flow of the conversation and emotional expression, guiding the user to communicate more effectively. An example of such a comment might be, "Your calm explanation increased the customer's sense of security."

[0685] (Application Example 2)

[0686] 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".

[0687] In sales training, when aiming for practical and individualized skill improvement based on virtual sales scenarios, it has traditionally been difficult to consider the user's emotional state in real time. As a result, there was a problem in that users lacked the ability to respond in actual sales situations, and the quality of customer service could not be sufficiently improved.

[0688] 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.

[0689] In this invention, the server includes means for generating a virtual customer profile, means for constructing a sales scenario, and means for sentiment analysis for identifying the user's emotional state. This enables the provision of customized feedback to the user in real time and allows for emotion-aware sales training.

[0690] A "virtual customer profile" is data about a hypothetical customer generated based on attribute information such as age, gender, preferences, and purchase history, and forms the basis of sales scenarios.

[0691] A "sales scenario" is a scenario used in sales training that concretely represents a conversational situation built based on a hypothetical customer profile.

[0692] "Means of providing feedback" refers to methods for analyzing user interactions in sales scenarios and using the results of that analysis to provide users with suggestions for improvement and evaluations.

[0693] "Emotional analysis means" refers to technology used to analyze a user's voice tone, facial expressions, and language patterns in order to identify their emotional state in real time.

[0694] "Customized feedback" refers to feedback that provides individually tailored evaluations and advice based on an analysis of the user's emotional state.

[0695] In an embodiment of this invention, the system includes three components: a server, a terminal, and a user. The server generates a virtual customer profile and builds a sales scenario based on it. The generated customer profile includes attribute information such as age, gender, preferences, and purchase history. This information is stored in a database and transmitted to the terminal.

[0696] The terminal has the ability to present sales scenarios on the user interface based on the received customer profile. The user selects a sales scenario and begins a conversation with a virtual customer. During the conversation, the terminal captures the user's voice and facial expressions and identifies emotions in real time using emotion analysis tools. This emotion analysis uses emotion analysis tools (e.g., Amazon Rekognition or Google Cloud Vision).

[0697] The identified sentiment information is sent to a server and analyzed by an AI model (e.g., TensorFlow or PyTorch). Based on this analysis, the server generates customized feedback and sends it to the device. The device immediately displays this feedback to the user to help improve their sales skills.

[0698] For example, when a user asks a virtual customer to "explain the new product," if their tone of voice is too high, feedback will be displayed recommending a calmer tone. This allows the user to learn how to communicate in a way that builds more trust.

[0699] An example of a prompt message is: "Generate the content of the feedback to be provided based on the sentiment analysis results. Virtual customer profile: Age: 45, Gender: Female, Interests: Technology-related; User's emotional state: Anxious."

[0700] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0701] Step 1:

[0702] The server generates virtual customer profiles. The input includes data on the customer's age, gender, preferences, and purchase history. This information is retrieved from the database to generate diverse profiles that can accommodate various sales scenarios. The output is the generated customer profile.

[0703] Step 2:

[0704] The server sends the generated customer profile to the terminal. The terminal receives this information and presents a sales scenario on the user interface. The user then selects the scenario to train. The input is the customer profile sent from the server, and the output is the sales scenario presented to the user.

[0705] Step 3:

[0706] The user initiates an interaction with a virtual customer. The terminal uses a microphone and camera to capture the user's voice and facial expressions. The input for this step is the user's voice and facial expressions, and the output is the captured data. This data is used for subsequent processing.

[0707] Step 4:

[0708] The terminal analyzes the captured data using emotion analysis tools. Here, voice tone, facial expressions, and language patterns are analyzed. The input is the voice and facial expression data obtained in the previous step, and the output is the identified emotional state. This emotional information is obtained as analysis results in real time.

[0709] Step 5:

[0710] The server receives the identified emotional state and analyzes the data using an AI model. The model evaluates the emotional state and the content of the conversation, and generates customized feedback. The input is emotional state data, and the output is specific feedback. It utilizes a generative AI model to respond flexibly.

[0711] Step 6:

[0712] The server sends the generated feedback to the terminal. The terminal immediately displays the feedback to the user. Here, the input is the feedback from the server, and the output is the displayed feedback. This feedback allows the user to improve their sales skills.

[0713] 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.

[0714] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0715] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0716] 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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."

[0722] 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.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] The following is further disclosed regarding the embodiments described above.

[0735] (Claim 1)

[0736] A means of generating a virtual customer profile,

[0737] Means for constructing a sales scenario based on the aforementioned customer profile,

[0738] A means of analyzing the content of the dialogue in the aforementioned sales scenario and providing feedback,

[0739] A system that includes this.

[0740] (Claim 2)

[0741] The system according to claim 1, wherein the customer profile has attribute information including age, gender, preferences, and purchase history.

[0742] (Claim 3)

[0743] The system according to claim 1, wherein the feedback is configured to be displayed on the terminal immediately.

[0744] "Example 1"

[0745] (Claim 1)

[0746] A means for generating virtual attribute information,

[0747] A means for constructing a sales scenario based on the aforementioned attribute information,

[0748] A means for analyzing the content of the dialogue in the aforementioned sales situation and providing opinions,

[0749] A means of providing a dialogue scenario through a user interface,

[0750] A means of instantly analyzing the record of the conversation and returning the opinion to the terminal,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, wherein the attribute information includes type, numerical value, preference, and history information.

[0754] (Claim 3)

[0755] The system according to claim 1, wherein the aforementioned opinion is configured to be immediately visible to the terminal.

[0756] "Application Example 1"

[0757] (Claim 1)

[0758] A means of generating a virtual customer profile,

[0759] Means for constructing a sales scenario based on the aforementioned customer profile,

[0760] A means of analyzing the content of the dialogue in the aforementioned sales scenario and providing feedback,

[0761] A means of selecting a training scenario and initiating a virtual dialogue through a user interface operating on a portable electronic device,

[0762] A means for analyzing the aforementioned dialogue content in real time, recording and displaying the progress,

[0763] A system that includes this.

[0764] (Claim 2)

[0765] The system according to claim 1, wherein the customer profile has attribute information including age, gender, preferences, and purchase history, and is further configured to support the improvement of sales capabilities by accumulating the history of individual scenarios.

[0766] (Claim 3)

[0767] The system according to claim 1, wherein the feedback is immediately displayed on a portable electronic device and configured to allow the user to easily reflect it in the next interaction.

[0768] "Example 2 of combining an emotion engine"

[0769] (Claim 1)

[0770] Elements that generate virtual customer information,

[0771] Elements for constructing a sales plan based on the aforementioned customer information,

[0772] Elements that analyze audio and video to identify the user's emotions,

[0773] The content of the dialogue in the aforementioned sales plan is analyzed, and elements are included to provide feedback according to the emotional state,

[0774] A system that includes this.

[0775] (Claim 2)

[0776] The system according to claim 1, wherein the customer information includes attribute information such as age, gender, preferences, and consumption history.

[0777] (Claim 3)

[0778] The system according to claim 1, wherein the feedback is configured to be presented to the terminal in real time.

[0779] "Application example 2 when combining with an emotional engine"

[0780] (Claim 1)

[0781] A means of generating a virtual customer profile,

[0782] Means for constructing a sales scenario based on the aforementioned customer profile,

[0783] A means of analyzing the content of the dialogue in the aforementioned sales scenario and providing feedback,

[0784] A means for analyzing the emotional state of a user,

[0785] A means for providing customized feedback in real time based on the aforementioned emotion analysis results,

[0786] A system that includes this.

[0787] (Claim 2)

[0788] The system according to claim 1, wherein the customer profile has attribute information including age, gender, preferences, and purchase history, and further includes an element that provides a scenario for in-store sales staff training.

[0789] (Claim 3)

[0790] The system according to claim 1, wherein the feedback, including an evaluation based on emotional state, is configured to be displayed immediately on the terminal. [Explanation of Symbols]

[0791] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of generating a virtual customer profile, Means for constructing a sales scenario based on the aforementioned customer profile, A means of analyzing the content of the dialogue in the aforementioned sales scenario and providing feedback, A system that includes this.

2. The system according to claim 1, wherein the customer profile has attribute information including age, gender, preferences, and purchase history.

3. The system according to claim 1, wherein the feedback is configured to be displayed on the terminal immediately.

Images