system

Abstract

Provide a system. 【Solution means】 A system for assisting in business education for new members, means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding answer, means for notifying the user of the generated answer, means for generating and notifying the user of business-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, A system including means for generating feedback based on the evaluation and notifying the user.

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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Educating new members in the workplace often requires a great deal of effort. Especially in workplaces with a shortage of human resources, there may be a situation where new members are left unattended. As a result, effective education is not carried out, not only does the adaptation of new members lag, but there is also a problem that the overall work efficiency decreases. Therefore, a system for effectively and efficiently educating new members is needed.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides the following means: a system for supporting job training for new members, comprising means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding answer, means for notifying the user of the generated answer, means for generating and notifying the user of job-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, and means for generating and notifying the user of feedback based on the evaluation.

[0006] Furthermore, by incorporating methods for notifying users of instructions in real time using smart devices, and for generating and recommending lecture plans tailored to the specific tasks, more effective training for new employees can be achieved.

[0007] "Voice input" refers to audio data produced by the user's speech.

[0008] "Text data" refers to string data converted from voice input.

[0009] "Analysis" is the process of understanding the content of text data and extracting relevant information.

[0010] "Answer" refers to the response content derived through analysis.

[0011] "Notification" refers to the act of informing the user of generated responses or instructions.

[0012] "Instructions" refer to guidance provided by AI to assist in the progress of tasks.

[0013] "Activity history" refers to a record of a series of activities performed by a user.

[0014] "Evaluation" refers to the measurement of performance based on collected behavioral history and questionnaire responses.

[0015] "Feedback" refers to the areas for improvement and positive comments provided to the user based on the evaluation results.

[0016] "Smart device" refers to a wearable device with an Internet connection function used by the user.

[0017] "Lecture plan" refers to a plan that includes the schedule and content of sequential guidance for a specific task.

Brief Description of Drawings

[0018] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. <0OO0091> [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Modes for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0020] First, the language used in the following description will be explained.

[0021] In the following embodiments, a 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.

[0022] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] 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."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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".

[0039] As an embodiment of this invention, a system to support job training is described below. This system receives voice input from the user, converts it into text data, analyzes the text data to generate an answer, and notifies the user of the answer. It also generates and notifies the user of job-related instructions in real time. Furthermore, it collects the user's behavior history and question content, performs an evaluation, and provides feedback based on the evaluation.

[0040] The user wears a smart device and performs a voice login operation. When the user says, "Login, Username: User123, Password:", the device converts the voice into text data and sends it to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[0041] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0042] When a user encounters a question during their work, they can ask it by voice. For example, if a user asks, "What is the side dish for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and generates an answer, such as, "The side dish for this dish is french fries." The device then notifies the user of the generated answer by voice.

[0043] Furthermore, the user's behavior history and questions are collected and sent to the server. The server evaluates the user based on the collected data and sends the evaluation results to the device. The device receives the evaluation results and provides voice feedback such as, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[0044] As a concrete example, let's consider a new waiter in a restaurant. The user wears a smart device and, if a question arises while taking an order, asks it by voice. For example, if the user asks, "Which wine would go well with this dish?", the device sends this question to a server, which generates an answer. The device then notifies the user by voice of the generated answer, "Red wine would go well with this dish," enabling the user to provide appropriate service.

[0045] This system allows new members to perform their tasks while receiving real-time guidance from AI, significantly improving the effectiveness of training and increasing work efficiency.

[0046] The following describes the processing flow.

[0047] Step 1: User login operation

[0048] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[0049] The device records the audio and converts it into text data using speech recognition software.

[0050] The device sends the text information converted from the speech to the server.

[0051] Step 2: Authentication Process

[0052] The server compares the received username and password with the database to perform authentication.

[0053] The server generates an authentication success or failure result and sends it to the terminal.

[0054] The device receives the authentication result from the server and notifies the user via voice.

[0055] Step 3: Generate and notify the lecture plan

[0056] The server retrieves the job description of the new member user from the database.

[0057] The server generates a lecture plan tailored to the specific tasks.

[0058] The server sends the generated lecture plan to the terminal.

[0059] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[0060] Step 4: Work progress and instructions

[0061] The device monitors the user's location and movements using sensors.

[0062] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[0063] Step 5: Handling the Question

[0064] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[0065] The device records the audio and converts it into text data using speech recognition software.

[0066] The terminal sends the converted question text to the server.

[0067] The server analyzes the question and generates an appropriate answer.

[0068] The server sends the generated response to the terminal.

[0069] The device will notify the user of the answer via voice.

[0070] Step 6: Collecting activity history

[0071] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[0072] The server saves the activity history to a database.

[0073] Step 7: Provide evaluation and feedback

[0074] The server generates a user evaluation report based on the behavioral history it has collected.

[0075] The server sends the evaluation results to the terminal.

[0076] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[0077] This processing flow allows users to receive real-time guidance, evaluation, and feedback while performing their tasks, significantly improving training efficiency and enhancing the quality of work.

[0078] (Example 1)

[0079] 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."

[0080] Providing appropriate guidance and feedback in real time during on-the-job training for new members is considered difficult. Traditional training methods require specialized trainers, which are not only inefficient but also costly. Furthermore, it is difficult to provide standardized training, and the inability to provide flexible guidance tailored to the abilities of new members is a challenge.

[0081] 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.

[0082] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding answer, means for notifying the user of the generated answer, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for the server to retrieve the user's work content from a database and generate a lecture plan according to the work content, means for sending the lecture plan to a terminal and for the terminal to notify the user by voice, means for acquiring the user's question as voice input, converting it into text and sending it to the server, means for the server to analyze the question content, generate a corresponding answer and send it to the terminal, means for generating feedback based on the evaluation and notifying the user, and means for inputting prompt sentences to a generating AI model in order to operate each of the means. This enables efficient and flexible guidance by providing new members with standardized education and feedback in real time.

[0083] "Voice input" refers to the voice data spoken by the user.

[0084] "Text data" refers to a data format obtained by converting voice input into text.

[0085] "Analysis" refers to the process of understanding text data and deriving appropriate processing or responses.

[0086] "Answer" refers to information, including instructions, that are generated based on the analyzed text data.

[0087] "Notification" refers to the act of communicating generated responses or instructions to the user.

[0088] "Instructions related to work" refers to information that includes specific actions and procedures related to the tasks that the user must perform.

[0089] "Activity history" refers to a record of actions taken and questions asked by a user while using the system.

[0090] "Evaluation" refers to the process of determining a user's performance and progress based on collected behavioral history and questionnaire responses.

[0091] "Feedback" refers to improvement instructions and progress reports provided to users based on evaluation results.

[0092] A "lecture plan" refers to a plan of training content and procedures created based on the user's work.

[0093] A "generative AI model" refers to an artificial intelligence model used for tasks such as analyzing text data, generating responses, and creating lecture plans.

[0094] A "prompt statement" refers to an input statement used to instruct a generative AI model on a specific task.

[0095] "Terminal" refers to hardware such as smart devices and computers used by users.

[0096] A "server" refers to a computer system that handles data processing and management for the entire system.

[0097] A "database" refers to a repository of information that stores users' work details and activity history, and is referenced as needed.

[0098] This invention is a system for supporting job training for new members, providing a means to receive user voice input, convert it into text data, and process it appropriately. Specifically, it involves the coordinated operation of a server, a terminal, and the user.

[0099] Hardware and software usage

[0100] The system is primarily implemented using the following hardware and software.

[0101] hardware

[0102] Smart devices: Devices that allow users to input information using voice. Examples include smartphones and wearable devices.

[0103] Server: A computer system used for centralized data processing and management. This includes cloud servers and on-premises servers.

[0104] software

[0105] Speech recognition software: Converts user voice input into text data. An example is Google® Cloud Speech-to-Text API.

[0106] Database systems: Used to store user information and business data. Examples include MySQL (registered trademark) and PostgreSQL.

[0107] Natural language processing engines: These analyze text data and generate responses or instructions. Examples include BERT and GPT-3 (registered trademark).

[0108] Text-to-speech software: Converts text data into speech and notifies the user. An example is the Google Cloud Text-to-Speech API.

[0109] System operation example

[0110] Voice recognition and login

[0111] The user logs in using their voice via a smart device. For example, they might say, "Login, Username: User123, Password: ". The device converts the voice into text data using the Google Cloud Speech-to-Text API and sends it to the server. The server queries the database to verify the username and password and sends the authentication result to the device. The device then notifies the user via voice, "Login successful."

[0112] Lecture plan generation and notification

[0113] The server retrieves the job description of a new member user from the database and uses a natural language generation model (such as GPT-3) to generate a lecture plan tailored to that job. For example, if the user works in the service industry, the server generates a "Basic Waiter's Lecture Plan" and sends it to the terminal. The terminal then notifies the user via voice, "Starting service duties. First, you will learn how to take orders."

[0114] User questions and answers

[0115] If a user has a question during work, they can ask it by voice. For example, they might ask, "What is the side dish for this dish?" The terminal converts the voice into text data and sends it to the server. The server analyzes the question using a natural language processing engine such as BERT and generates the optimal answer, "The side dish for this dish is french fries," using a generative AI model such as GPT-3. This is sent to the terminal, which then notifies the user by voice.

[0116] Collection of behavioral history and feedback

[0117] The device continuously sends the user's activity history and questions to the server. The server analyzes this data and generates a user evaluation. Based on the evaluation, it generates instructions and feedback for the next step and sends them to the device. For example, it might notify the user, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[0118] Examples of prompt statements

[0119] The following are specific examples of prompt statements for a generative AI model.

[0120] Example of a question prompt

[0121] Question: Generate the appropriate answer to the question, "What are the side dishes for this dish?"

[0122] Example of a feedback prompt

[0123] Based on the user's activity history and evaluation results, notify the user that their current work progress is 80% and provide feedback that their next task is to learn how to describe the dessert menu.

[0124] This invention allows new members to receive standardized training and feedback in real time, significantly improving work efficiency and the effectiveness of training.

[0125] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0126] Step 1:

[0127] Accepting voice input

[0128] The user speaks into their smart device saying, "Login, Username: User123, Password:". This voice input is captured by the smart device's microphone. The device passes the captured voice data to the Google Cloud Speech-to-Text API, which converts it into text data. The converted text data is in the format "Login, Username: User123, Password:". This text data is then sent from the device to the server via an HTTPS request.

[0129] Step 2:

[0130] Performing user authentication

[0131] The server analyzes the received text data and extracts the username and password. The extracted username and password are then compared against the authentication information stored in the database (e.g., MySQL). Based on this comparison, the server determines whether authentication was successful or unsuccessful and sends the result back to the terminal. For example, if authentication is successful, the terminal will receive a message such as "Login successful," and if it fails, it will receive a message such as "Login failed." The terminal then uses speech synthesis software to convert the authentication result into speech and notifies the user that "Login successful."

[0132] Step 3:

[0133] Acquisition of job description and generation of lecture plan

[0134] The server retrieves the authenticated user's job description from the database. This job description data includes information about the type of work the user is engaged in and specific tasks. Simultaneously, the server uses a generative AI model (e.g., GPT-3) to generate a lecture plan based on the job description. For example, if the user works in customer service, the generated lecture plan will include a "Basic Waiter Job Lecture Plan." This lecture plan is sent to the terminal. The terminal converts the received lecture plan into speech using speech synthesis software and notifies the user, "Starting customer service work. First, you will learn how to take orders."

[0135] Step 4:

[0136] Receiving and providing answers to user questions.

[0137] A user might have a question during work, for example, "What is the side dish for this dish?" This voice input is captured by the smart device's microphone, and the device converts the voice data into text data. The converted text data is sent to a server. The server receives the text data and analyzes the question using a natural language processing engine (such as BERT). Then, using a generative AI model, it generates an appropriate answer, such as "The side dish for this dish is french fries." This answer is sent to the device, which converts it into speech using speech synthesis software and notifies the user, "The side dish for this dish is french fries."

[0138] Step 5:

[0139] Collection and evaluation of behavioral history

[0140] The terminal continuously transmits the user's activity history and questions to the server. The activity history includes a detailed record of how the user is using the system. The server analyzes the collected activity history data and evaluates the user's performance. Based on this evaluation, it generates instructions and feedback for the next step. For example, it might generate something like, "Your current work progress is 80%. Next, you will learn about the dessert menu," and send this to the terminal. The terminal uses speech synthesis software to convert the evaluation results into speech and notify the user.

[0141] (Application Example 1)

[0142] 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."

[0143] Traditional training systems often suffer from delays in providing guidance and feedback to new members, making it difficult to respond appropriately in environments where immediate responses are required. Furthermore, particularly in factory settings, not only is human training required, but also the efficient operation of robots, necessitating a system that provides real-time guidance and feedback. However, existing systems are inadequate in responding to real-time questions and instructions via voice input, making it difficult to provide immediate guidance to improve the efficiency of robot operations.

[0144] 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.

[0145] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding response, means for notifying the user of the generated response, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for generating and notifying the user of feedback based on the evaluation, means for allowing the robot to ask for instructions by voice when performing a task, means for notifying the robot by voice of the generated response, means for analyzing the robot's operation history and question content and generating feedback, and means for providing guidance to improve the robot's work efficiency based on the feedback. As a result, new members and robots can receive appropriate guidance and feedback in real time, which can significantly improve work efficiency and the effectiveness of training.

[0146] "Voice input means" refers to a device or software that allows a system to receive voice input from a user.

[0147] "Text conversion means" refers to a device or software used to convert received voice input into text data.

[0148] "Response generation means" refers to a device or software that analyzes text data and generates an appropriate response based on its content.

[0149] "Notification means" refers to a device or software that informs the user of generated responses or instructions via voice or text.

[0150] "Real-time instruction generation means" refers to a device or software that instantly generates instructions related to work and transmits them to the user.

[0151] "Means for collecting behavioral history" refers to a device or software for recording and storing a history of a user's actions and operations.

[0152] "Evaluation means" refers to a device or software used to analyze and evaluate collected behavioral history and questionnaire content.

[0153] "Feedback generation means" refers to a device or software that generates appropriate feedback based on evaluations and notifies the user.

[0154] A "robot instruction and questioning means" refers to a device or software that allows a robot to give instructions or ask questions using voice when performing tasks.

[0155] "Robot notification means" refers to a device or software used to notify a robot of its generated response via voice.

[0156] "Action history analysis means" refers to a device or software that analyzes the robot's action history and question content to generate feedback.

[0157] "Efficiency improvement guidance means" refers to a device or software that provides specific guidance to improve the work efficiency of robots based on feedback.

[0158] As an embodiment of this invention, a system for supporting the operational training of robots in a factory will be described. This system provides real-time guidance and answers to questions while the robot is performing its tasks, and provides feedback to improve operational efficiency.

[0159] First, the robot inputs questions and instructions that arise during its work via voice input devices (e.g., smartphones with microphones). For example, it might say, "Please tell me how to attach this part."

[0160] Voice input devices convert the input speech into text data. This is done using speech recognition software such as the Google Speech-to-Text API. This text data is then sent to a server over the internet.

[0161] The server analyzes the received text data using natural language processing software such as the OpenAI® GPT model and generates an appropriate response. For example, it might generate a response like, "To install this part, first set part A in position, and then secure it with screws."

[0162] The generated responses are converted into speech using speech synthesis software (e.g., Amazon Polly) and communicated to the robot via voice. This process allows the robot to receive appropriate guidance in real time.

[0163] Furthermore, the robot's behavior history and question content are continuously collected and stored on a server. The server performs analysis based on the collected data to evaluate the robot's work efficiency. Because this analysis involves handling a large amount of data, a database management system (e.g., MySQL, PostgreSQL) is used.

[0164] Based on the evaluation results, feedback is generated. For example, specific instructions such as "Work progress is 70%. Next, install part B" are generated and notified to the robot. This allows the robot to perform its tasks efficiently.

[0165] As a concrete example, imagine a scenario where a factory robot is assembling parts. If the robot asks, "What is the next task?" via a voice input device, the server immediately generates a response, "Next, attach part B," and notifies the robot by voice. This allows the robot to receive instructions and quickly begin the next task.

[0166] Furthermore, the following are examples of prompt statements that can be input to the generative AI model.

[0167] Question: How do I install this part?

[0168] Answer: To install this part, first set part A in place, and then secure it with screws.

[0169] In this way, robots can perform their tasks while receiving appropriate guidance in real time, significantly improving work efficiency and the effectiveness of training.

[0170] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0171] Step 1:

[0172] The user (robot) inputs questions or instructions through a voice input device. For example, it might say, "Please tell me how to install this part." The input here is voice data.

[0173] Step 2:

[0174] The device (voice input device) converts the input voice data into text data using the Google Speech-to-Text API. This conversion process transforms the voice data into the text "Please tell me how to install this part."

[0175] Step 3:

[0176] The terminal sends the converted text data to the server via the internet. Here, the input is text data, and the output is the data sent to the server.

[0177] Step 4:

[0178] The server analyzes the received text data using an OpenAI GPT model and generates an appropriate response. Specifically, it understands the content of the text data and, based on that, outputs a response such as, "To install this part, first set part A in position, and then secure it with screws."

[0179] Step 5:

[0180] The server converts the generated responses into speech data using text-to-speech software such as Amazon Polly. The input here is the generated text data, and the output is speech data.

[0181] Step 6:

[0182] The server sends the generated audio data to the terminal. The terminal notifies the user (robot) of the transmitted audio data. In this case, the input is the audio data from the server, and the output is the audio notification to the user.

[0183] Step 7:

[0184] The robot continues its task based on the voice instructions it receives. For example, it might execute the instruction, "Set part A and secure it with screws." In this case, the input is the voice instruction, and the output is the corresponding action.

[0185] Step 8:

[0186] The terminal continuously collects the robot's behavior history and question content and sends it to the server. The input here is the robot's behavior history and question content, and the output is the data sent to the server.

[0187] Step 9:

[0188] The server analyzes the collected data and evaluates the robot's operational efficiency. The input here is the collected data, and the output is the evaluation result.

[0189] Step 10:

[0190] The server generates feedback based on the evaluation results and notifies the robot via the terminal. For example, it might generate feedback such as, "Work progress is 70%. Next, install part B." Here, the input is the evaluation result, and the output is the feedback data.

[0191] Step 11:

[0192] The robot improves its operations based on the feedback provided. Here, the input is the feedback data, and the output is the improved operation.

[0193] 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.

[0194] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[0195] Specifically, the system operates using the following steps.

[0196] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the converted text information to the server. The server verifies the received username and password and sends the authentication result to the device. The device notifies the user of the authentication result by voice.

[0197] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0198] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[0199] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0200] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[0201] This system allows users to receive real-time guidance and emotionally responsive support while performing their tasks, significantly improving the effectiveness of training and increasing work efficiency.

[0202] The following describes the processing flow.

[0203] Step 1: User login operation

[0204] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[0205] The device records the audio and converts it into text data using speech recognition software.

[0206] The device sends the text information converted from the speech to the server.

[0207] Step 2: Authentication Process

[0208] The server compares the received username and password with the database to perform authentication.

[0209] The server generates an authentication success or failure result and sends it to the terminal.

[0210] The device receives the authentication result from the server and notifies the user via voice.

[0211] Step 3: Generate and notify the lecture plan

[0212] The server retrieves the job description of the new member user from the database.

[0213] The server generates a lecture plan tailored to the specific tasks.

[0214] The server sends the generated lecture plan to the terminal.

[0215] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[0216] Step 4: Work progress and instructions

[0217] The device monitors the user's location and movements using sensors.

[0218] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[0219] Step 5: Handling the Question

[0220] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[0221] The device records the audio and converts it into text data using speech recognition software.

[0222] The terminal sends the converted question text to the server.

[0223] Step 6: Emotional Analysis

[0224] The server analyzes the question content and uses an emotion recognition engine to analyze the user's emotional state.

[0225] For example, if the server detects that the user is nervous, it will soften the tone of its response.

[0226] Step 7: Generating the answer

[0227] Based on the analysis results, the server generates a response such as, "This dish comes with french fries as a side dish. We can confidently recommend it."

[0228] The server sends the generated response to the terminal.

[0229] Step 8: Notification of response

[0230] The device notifies the user of the generated response via voice.

[0231] Step 9: Collecting activity history

[0232] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[0233] The server saves the activity history to a database.

[0234] Step 10: Provide evaluation and feedback

[0235] The server generates a user evaluation report based on the behavioral history it has collected.

[0236] The server sends the evaluation results to the terminal.

[0237] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[0238] If the server determines, based on analysis by its emotion recognition engine, that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0239] The device notifies the user of that feedback via voice.

[0240] This detailed processing flow allows users to receive real-time guidance and emotionally responsive support while performing their tasks, improving training efficiency and enhancing the quality of work.

[0241] (Example 2)

[0242] 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".

[0243] Current business training support systems struggle to effectively utilize user voice input for training, particularly lacking real-time feedback, instructions, and appropriate support tailored to the user's emotional state. As a result, improvements in training effectiveness and operational efficiency may not be fully achieved.

[0244] 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.

[0245] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for transmitting the converted text data to the server for authentication, means for sending the authentication result to a terminal and notifying the user, means for generating text according to the content of the work, means for converting the generated text into voice data and notifying the user, means for converting the user's question voice into text data, means for transmitting the converted text data to the server and recognizing the user's emotions, means for generating an answer based on the emotion recognition result, means for converting the generated answer from text into voice and notifying the user, means for collecting and evaluating the user's behavior history and question content, and means for generating feedback based on the evaluation and notifying the user. This enables the user to perform their work while receiving appropriate support in real time.

[0246] "Means of accepting voice input" refers to a function that captures the voice spoken by the user.

[0247] "Means of converting to text data" refers to a function that converts audio data into text information.

[0248] "Method of sending to a server for authentication" refers to a function that sends the converted text data to a server via the network to authenticate the user.

[0249] "A means of sending authentication results to the terminal and notifying the user" refers to a function that sends the authentication results from the server to the terminal and informs the user of those results.

[0250] "Means for generating text tailored to the work content" refers to a function that creates text containing necessary information and instructions based on the user's work content.

[0251] "A means of converting generated text into audio data and notifying the user" refers to a function that converts the created text into an audio format and informs the user via voice.

[0252] "Means for converting question audio into text data" refers to a function that converts the audio of a question uttered by a user into text information.

[0253] "Means of recognizing user emotions" refers to a function that analyzes user text data to identify the user's emotional state.

[0254] "Means for generating responses based on emotion recognition results" refers to a function that creates appropriate responses by taking into account the user's emotional state.

[0255] "A means of converting generated responses from text to audio and notifying the user" refers to a function that converts the text of the generated response into an audio format and informs the user of it audibly.

[0256] "Means for collecting and evaluating behavioral history and question content" refers to a function that records user behavior and question content, and analyzes and evaluates that data.

[0257] "A means of generating feedback and notifying users" refers to a function that creates feedback based on evaluation results and informs users of it.

[0258] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects the user's behavior history and question content, and provides feedback based on the evaluation results.

[0259] Hardware and software configuration

[0260] Hardware:

[0261] Smart devices: These are devices that accept voice input, such as smartphones and tablets.

[0262] Server: A device that performs authentication, data analysis, response generation, and evaluation.

[0263] software:

[0264] Speech recognition software: Uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[0265] Text-to-speech software: Use Amazon Polly or Google Cloud Text-to-Speech to convert text data into speech data.

[0266] Emotion recognition engine: Uses IBM Watson® Tone Analyzer to analyze the user's emotional state from text data.

[0267] System operation

[0268] Voice input acceptance and authentication:

[0269] The user puts on a smart device and says "Login, Username: User123, Password: ". The device records the voice and converts it into text data using speech recognition software. The device sends this text data to a server, which performs authentication. Once the authentication result is obtained, the result is sent to the device and notified to the user using speech synthesis software. For example, it might notify the user, "Login successful."

[0270] Generating a business lecture plan:

[0271] After authentication is complete, the server retrieves the user's job description from the database and generates a corresponding lecture plan. For example, if a user starts customer service, the server generates a "Basic Waiter Job Lecture Plan." This plan is sent to the terminal and notified to the user using speech synthesis software. For example, it might notify the user, "Starting customer service. First, you will learn how to take orders."

[0272] Handling questions and answers:

[0273] If a user has a question during work, for example, "What is the side dish for this dish?", they can ask it aloud. The terminal records this question and converts it into text data using speech recognition software. This text data is sent to a server, where the server analyzes the user's emotional state using an emotion recognition engine. For example, if the server analyzes that the user is nervous, it will generate a response in a softer tone. It will generate a response such as, "The side dish for this dish is french fries. I can recommend it with confidence," and convert this back into audio data to notify the user.

[0274] Collecting behavioral history and providing feedback:

[0275] The terminal periodically sends the user's action history (received instructions, question content, work progress) to the server. The server conducts an evaluation based on the collected data and generates feedback. For example, it generates feedback such as "Aren't you a little tired in your recent work? Let's take a break and refresh ourselves", converts this into voice data, and notifies the user.

[0276] Examples of specific operations and prompt texts

[0277] Operation example:

[0278] When the user asks "What should I do? This order can't be processed properly", the terminal records this question and sends it to the server. The server analyzes the user's stress level with an emotion recognition engine and generates a response in a gentle tone, such as "First, let's check the menu. Please proceed without rushing". When this is notified to the user as voice, the user can continue the work with peace of mind.

[0279] Examples of prompt texts:

[0280] Question: "What should I do? This order can't be processed properly"

[0281] User's emotional state: Stress

[0282] Response tone: Gentle

[0283] Answer: "First, let's check the menu. Please proceed without rushing"

[0284] By using this system, the user can receive appropriate support in real time while performing the work. As a result, it is expected that the educational effect will be significantly improved and the work efficiency will also increase.

[0285] The flow of the specific process in Example 2 will be described using FIG. 13.

[0286] Step 1:

[0287] The user performs a voice login operation on the smart device.

[0288] Input: Voice input "Login, Username: User123, Password: "

[0289] Action: The built-in microphone of the terminal records the voice.

[0290] Output: Voice data

[0291] Step 2:

[0292] The terminal collects the voice data and converts it into text data using voice recognition software.

[0293] Input: Voice data

[0294] Action: The terminal uses the Google Cloud Speech-to-Text API to convert the voice data into text data.

[0295] Output: Text data "Login, Username: User123, Password: "

[0296] Step 3:

[0297] The terminal sends the converted text data to the server for authentication.

[0298] Input: Text data "Login, Username: User123, Password: "

[0299] Action: The terminal sends the text data as an HTTP request to the server. The server performs authentication by comparing it with the database.

[0300] Output: Authentication result (success or failure)

[0301] Step 4:

[0302] The server sends the authentication result to the terminal, and the terminal notifies the user of it.

[0303] Input: Authentication result (success or failure)

[0304] Operation: The server returns the authentication result to the terminal in JSON format. The terminal converts this into an audio message using speech synthesis software (such as Amazon Polly) and notifies the user. Specifically, it notifies the user as "Login successful" or "Login failed".

[0305] Output: Audio notification

[0306] Step 5:

[0307] The server generates a lecture plan based on the business content and sends it to the terminal.

[0308] Input: User's business information (obtained from the database)

[0309] Operation: The server obtains the user's business content and generates a lecture plan accordingly. For example, it generates a "Basic lecture plan for waiter business".

[0310] Output: Lecture plan

[0311] Step 6:

[0312] The terminal receives the lecture plan and notifies the user by voice.

[0313] Input: Lecture plan

[0314] Operation: The terminal analyzes the lecture plan and generates an audio message using speech synthesis software. Specifically, it notifies the user as "The customer service business starts. First, learn how to take orders".

[0315] Output: Audio notification

[0316] Step 7:

[0317] During work, the user asks a question, and the terminal converts the question from voice data into text data and sends it to the server.

[0318] Input: Voice input "What side dishes are served with this dish?"

[0319] Operation: The device records the question and converts it into text data using the Google Cloud Speech-to-Text API. The converted text data is then sent to the server as an HTTP request.

[0320] Output: Text data "What side dishes are served with this dish?"

[0321] Step 8:

[0322] The server analyzes the question and the user's emotional state, generates an appropriate answer, and sends it to the terminal.

[0323] Input: Text data "What side dishes are served with this dish?"

[0324] Operation: The server analyzes the question and uses IBM Watson Tone Analyzer to analyze the emotional state. Based on the analysis results, it generates a response in a soft tone. Specifically, it might generate something like, "This dish comes with french fries as a side dish. I can confidently recommend it."

[0325] Output: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[0326] Step 9:

[0327] The device notifies the user of the generated response via voice.

[0328] Input: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[0329] Operation: The terminal converts the received response into a voice message using speech synthesis software and notifies the user.

[0330] Output: Voice notification

[0331] Step 10:

[0332] The device sends the user's activity history to the server, and the server generates evaluations and feedback and sends them back to the device.

[0333] Input: User activity history (instructions received, questions asked, progress of tasks)

[0334] Operation: The device periodically sends its activity history to the server. The server evaluates this and generates feedback. Example: It might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0335] Output: Evaluation results and feedback

[0336] Step 11:

[0337] The device notifies the user of the evaluation results and feedback via voice.

[0338] Input: Evaluation results and feedback "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0339] Operation: The terminal converts the received evaluation results and feedback into a voice message using speech synthesis software and notifies the user.

[0340] Output: Voice notification

[0341] (Application Example 2)

[0342] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0343] Traditionally, training new employees has typically involved using text-based manuals and videos. However, these methods struggle to address individual user emotional states and stress levels, making effective training difficult. Furthermore, they are ineffective at providing real-time support and feedback, highlighting the need for improved training efficiency and quality. In addition, providing appropriate support for employees experiencing tension and anxiety in real-world settings such as physical stores is crucial. To address these challenges, a system is needed that analyzes user emotional states and provides responses and instructions in an appropriate tone.

[0344] 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.

[0345] In this invention, the server includes means for analyzing the user's emotions from voice input and text data, means for generating responses and instructions in an appropriate tone based on the emotion analysis results, means for allowing the user to input login information by voice using a smart device, and means for providing real-time instructions in an appropriate tone according to the user's emotional state. This makes it possible to provide new members with job training that is appropriately customized in real time according to the user's emotional state, including guidance and support.

[0346] "Voice input" refers to voice information spoken by the user.

[0347] "Text data" refers to data obtained by converting audio information into written text.

[0348] "Emotional analysis" is the process of analyzing a user's emotional state from audio and text data.

[0349] "Answer generation" refers to the process by which a system produces appropriate answers to user questions and requests.

[0350] "Instruction generation" refers to the system generating instructions related to the user's work in real time.

[0351] "Activity history" refers to a record of actions taken by a user while using the system.

[0352] "Feedback" refers to a system evaluating a user's behavior and emotional state and notifying the user of the results.

[0353] A "smart device" refers to a device that has functions such as voice input and display, and smart glasses are an example.

[0354] "Login information" refers to authentication data necessary for a user to access the system.

[0355] "Tone" refers to the pitch or atmosphere of a voice, and it is adjusted according to the emotion being conveyed.

[0356] "Real-time instructions" are instructions that are provided instantly to the user while they are performing a task.

[0357] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[0358] Specifically, the system operates in the following steps:

[0359] First, the user puts on a smart device and performs a voice login operation. For example, if the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the text information converted from the voice to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[0360] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user's job is customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0361] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[0362] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0363] The hardware used includes smart devices (e.g., smart glasses), and the software includes a speech recognition library (speech_recognition), a speech synthesis library (pyttsx3), and an emotion recognition engine (a hypothetical emotion_recognition library).

[0364] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[0365] An example of a prompt for a generative AI model is: "When a user asks, 'What comes with this dish?', sentiment analysis will be performed based on the user's voice data. For example, if it is determined that the user is nervous, please generate a response in a gentle tone such as, 'This dish comes with a salad. Please tell us without hesitation.'"

[0366] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0367] Step 1:

[0368] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice. The recorded voice data is converted into text data by speech recognition software. This converted text data is sent to the server. The server compares the received username and password with the database and sends the authentication result (success or failure) to the device. The device notifies the user of the authentication result by voice.

[0369] Input: User's voice data

[0370] Output: Text data, authentication result

[0371] Step 2:

[0372] The server retrieves the job description of the new member user from the database. It generates a lecture plan tailored to the job description and sends it to the terminal. The terminal then notifies the user via voice based on the received lecture plan. The notification might say something like, "We will now begin the basic customer service lecture plan. First, we will learn how to take orders."

[0373] Input: User's job description

[0374] Output: Lecture plan

[0375] Step 3:

[0376] When a user encounters a question during their work, they can ask it by voice. For example, they might say, "What are the side dishes for this dish?" The terminal converts the voice into text and sends it to the server. The server analyzes the question and further analyzes the user's emotional state from the voice data using an emotion recognition engine. Based on the analysis results, the server adjusts the tone of the response, generates an appropriate answer, and sends it to the terminal. The terminal then notifies the user of the generated answer by voice.

[0377] Input: User's question audio data

[0378] Output: Appropriate answer

[0379] Step 4:

[0380] The terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs analysis and evaluation. Based on the evaluation results, it generates feedback and sends it to the terminal. For example, it might provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0381] Input: Behavioral history data

[0382] Output: Feedback

[0383] Step 5:

[0384] If necessary, the user will continue to ask questions or receive new instructions. The device repeatedly records and recognizes voices in response to these situations, sends data to the server, the server processes and generates feedback, and the device sends voice notifications.

[0385] Input: Next question or instruction voice data

[0386] Output: The following appropriate answers and instructions

[0387] 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.

[0388] 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.

[0389] 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.

[0390] [Second Embodiment]

[0391] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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).

[0397] 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.

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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".

[0403] As an embodiment of this invention, a system to support job training is described below. This system receives voice input from the user, converts it into text data, analyzes the text data to generate an answer, and notifies the user of the answer. It also generates and notifies the user of job-related instructions in real time. Furthermore, it collects the user's behavior history and question content, performs an evaluation, and provides feedback based on the evaluation.

[0404] The user wears a smart device and performs a voice login operation. When the user says, "Login, Username: User123, Password:", the device converts the voice into text data and sends it to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[0405] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0406] When a user encounters a question during their work, they can ask it by voice. For example, if a user asks, "What is the side dish for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and generates an answer, such as, "The side dish for this dish is french fries." The device then notifies the user of the generated answer by voice.

[0407] Furthermore, the user's behavior history and questions are collected and sent to the server. The server evaluates the user based on the collected data and sends the evaluation results to the device. The device receives the evaluation results and provides voice feedback such as, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[0408] As a concrete example, let's consider a new waiter in a restaurant. The user wears a smart device and, if a question arises while taking an order, asks it by voice. For example, if the user asks, "Which wine would go well with this dish?", the device sends this question to a server, which generates an answer. The device then notifies the user by voice of the generated answer, "Red wine would go well with this dish," enabling the user to provide appropriate service.

[0409] This system allows new members to perform their tasks while receiving real-time guidance from AI, significantly improving the effectiveness of training and increasing work efficiency.

[0410] The following describes the processing flow.

[0411] Step 1: User login operation

[0412] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[0413] The device records the audio and converts it into text data using speech recognition software.

[0414] The device sends the text information converted from the speech to the server.

[0415] Step 2: Authentication Process

[0416] The server compares the received username and password with the database to perform authentication.

[0417] The server generates an authentication success or failure result and sends it to the terminal.

[0418] The device receives the authentication result from the server and notifies the user via voice.

[0419] Step 3: Generate and notify the lecture plan

[0420] The server retrieves the job description of the new member user from the database.

[0421] The server generates a lecture plan tailored to the specific tasks.

[0422] The server sends the generated lecture plan to the terminal.

[0423] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[0424] Step 4: Work progress and instructions

[0425] The device monitors the user's location and movements using sensors.

[0426] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[0427] Step 5: Handling the Question

[0428] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[0429] The device records the audio and converts it into text data using speech recognition software.

[0430] The terminal sends the converted question text to the server.

[0431] The server analyzes the question and generates an appropriate answer.

[0432] The server sends the generated response to the terminal.

[0433] The device will notify the user of the answer via voice.

[0434] Step 6: Collecting activity history

[0435] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[0436] The server saves the activity history to a database.

[0437] Step 7: Provide evaluation and feedback

[0438] The server generates a user evaluation report based on the behavioral history it has collected.

[0439] The server sends the evaluation results to the terminal.

[0440] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[0441] This processing flow allows users to receive real-time guidance, evaluation, and feedback while performing their tasks, significantly improving training efficiency and enhancing the quality of work.

[0442] (Example 1)

[0443] 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."

[0444] Providing appropriate guidance and feedback in real time during on-the-job training for new members is considered difficult. Traditional training methods require specialized trainers, which are not only inefficient but also costly. Furthermore, it is difficult to provide standardized training, and the inability to provide flexible guidance tailored to the abilities of new members is a challenge.

[0445] 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.

[0446] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding answer, means for notifying the user of the generated answer, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for the server to retrieve the user's work content from a database and generate a lecture plan according to the work content, means for sending the lecture plan to a terminal and for the terminal to notify the user by voice, means for acquiring the user's question as voice input, converting it into text and sending it to the server, means for the server to analyze the question content, generate a corresponding answer and send it to the terminal, means for generating feedback based on the evaluation and notifying the user, and means for inputting prompt sentences to a generating AI model in order to operate each of the means. This enables efficient and flexible guidance by providing new members with standardized education and feedback in real time.

[0447] "Voice input" refers to the voice data spoken by the user.

[0448] "Text data" refers to a data format obtained by converting voice input into text.

[0449] "Analysis" refers to the process of understanding text data and deriving appropriate processing or responses.

[0450] "Answer" refers to information, including instructions, that are generated based on the analyzed text data.

[0451] "Notification" refers to the act of communicating generated responses or instructions to the user.

[0452] "Instructions related to work" refers to information that includes specific actions and procedures related to the tasks that the user must perform.

[0453] "Activity history" refers to a record of actions taken and questions asked by a user while using the system.

[0454] "Evaluation" refers to the process of determining a user's performance and progress based on collected behavioral history and questionnaire responses.

[0455] "Feedback" refers to improvement instructions and progress reports provided to users based on evaluation results.

[0456] A "lecture plan" refers to a plan of training content and procedures created based on the user's work.

[0457] A "generative AI model" refers to an artificial intelligence model used for tasks such as analyzing text data, generating responses, and creating lecture plans.

[0458] A "prompt statement" refers to an input statement used to instruct a generative AI model on a specific task.

[0459] "Terminal" refers to hardware such as smart devices and computers used by users.

[0460] A "server" refers to a computer system that handles data processing and management for the entire system.

[0461] A "database" refers to a repository of information that stores users' work details and activity history, and is referenced as needed.

[0462] This invention is a system for supporting job training for new members, providing a means to receive user voice input, convert it into text data, and process it appropriately. Specifically, it involves the coordinated operation of a server, a terminal, and the user.

[0463] Hardware and software usage

[0464] The system is primarily implemented using the following hardware and software.

[0465] hardware

[0466] Smart devices: Devices that allow users to input information using voice. Examples include smartphones and wearable devices.

[0467] Server: A computer system used for centralized data processing and management. This includes cloud servers and on-premises servers.

[0468] software

[0469] Speech recognition software: Converts user voice input into text data. An example is the Google Cloud Speech-to-Text API.

[0470] Database systems: Used to store user information and business data. Examples include MySQL and PostgreSQL.

[0471] Natural language processing engines: These analyze text data and generate responses or instructions. Examples include BERT and GPT-3.

[0472] Text-to-speech software: Converts text data into speech and notifies the user. An example is the Google Cloud Text-to-Speech API.

[0473] System operation example

[0474] Voice recognition and login

[0475] The user logs in using their voice via a smart device. For example, they might say, "Login, Username: User123, Password: ". The device converts the voice into text data using the Google Cloud Speech-to-Text API and sends it to the server. The server queries the database to verify the username and password and sends the authentication result to the device. The device then notifies the user via voice, "Login successful."

[0476] Lecture plan generation and notification

[0477] The server retrieves the job description of a new member user from the database and uses a natural language generation model (such as GPT-3) to generate a lecture plan tailored to that job. For example, if the user works in the service industry, the server generates a "Basic Waiter's Lecture Plan" and sends it to the terminal. The terminal then notifies the user via voice, "Starting service duties. First, you will learn how to take orders."

[0478] User questions and answers

[0479] If a user has a question during work, they can ask it by voice. For example, they might ask, "What is the side dish for this dish?" The terminal converts the voice into text data and sends it to the server. The server analyzes the question using a natural language processing engine such as BERT and generates the optimal answer, "The side dish for this dish is french fries," using a generative AI model such as GPT-3. This is sent to the terminal, which then notifies the user by voice.

[0480] Collection of behavioral history and feedback

[0481] The device continuously sends the user's activity history and questions to the server. The server analyzes this data and generates a user evaluation. Based on the evaluation, it generates instructions and feedback for the next step and sends them to the device. For example, it might notify the user, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[0482] Examples of prompt statements

[0483] The following are specific examples of prompt statements for a generative AI model.

[0484] Example of a question prompt

[0485] Question: Generate the appropriate answer to the question, "What are the side dishes for this dish?"

[0486] Example of a feedback prompt

[0487] Based on the user's activity history and evaluation results, notify the user that their current work progress is 80% and provide feedback that their next task is to learn how to describe the dessert menu.

[0488] This invention allows new members to receive standardized training and feedback in real time, significantly improving work efficiency and the effectiveness of training.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] Accepting voice input

[0492] The user speaks into their smart device saying, "Login, Username: User123, Password:". This voice input is captured by the smart device's microphone. The device passes the captured voice data to the Google Cloud Speech-to-Text API, which converts it into text data. The converted text data is in the format "Login, Username: User123, Password:". This text data is then sent from the device to the server via an HTTPS request.

[0493] Step 2:

[0494] Performing user authentication

[0495] The server analyzes the received text data and extracts the username and password. The extracted username and password are then compared against the authentication information stored in the database (e.g., MySQL). Based on this comparison, the server determines whether authentication was successful or unsuccessful and sends the result back to the terminal. For example, if authentication is successful, the terminal will receive a message such as "Login successful," and if it fails, it will receive a message such as "Login failed." The terminal then uses speech synthesis software to convert the authentication result into speech and notifies the user that "Login successful."

[0496] Step 3:

[0497] Acquisition of job description and generation of lecture plan

[0498] The server retrieves the authenticated user's job description from the database. This job description data includes information about the type of work the user is engaged in and specific tasks. Simultaneously, the server uses a generative AI model (e.g., GPT-3) to generate a lecture plan based on the job description. For example, if the user works in customer service, the generated lecture plan will include a "Basic Waiter Job Lecture Plan." This lecture plan is sent to the terminal. The terminal converts the received lecture plan into speech using speech synthesis software and notifies the user, "Starting customer service work. First, you will learn how to take orders."

[0499] Step 4:

[0500] Receiving and providing answers to user questions.

[0501] A user might have a question during work, for example, "What is the side dish for this dish?" This voice input is captured by the smart device's microphone, and the device converts the voice data into text data. The converted text data is sent to a server. The server receives the text data and analyzes the question using a natural language processing engine (such as BERT). Then, using a generative AI model, it generates an appropriate answer, such as "The side dish for this dish is french fries." This answer is sent to the device, which converts it into speech using speech synthesis software and notifies the user, "The side dish for this dish is french fries."

[0502] Step 5:

[0503] Collection and evaluation of behavioral history

[0504] The terminal continuously transmits the user's activity history and questions to the server. The activity history includes a detailed record of how the user is using the system. The server analyzes the collected activity history data and evaluates the user's performance. Based on this evaluation, it generates instructions and feedback for the next step. For example, it might generate something like, "Your current work progress is 80%. Next, you will learn about the dessert menu," and send this to the terminal. The terminal uses speech synthesis software to convert the evaluation results into speech and notify the user.

[0505] (Application Example 1)

[0506] 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."

[0507] Traditional training systems often suffer from delays in providing guidance and feedback to new members, making it difficult to respond appropriately in environments where immediate responses are required. Furthermore, particularly in factory settings, not only is human training required, but also the efficient operation of robots, necessitating a system that provides real-time guidance and feedback. However, existing systems are inadequate in responding to real-time questions and instructions via voice input, making it difficult to provide immediate guidance to improve the efficiency of robot operations.

[0508] 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.

[0509] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding response, means for notifying the user of the generated response, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for generating and notifying the user of feedback based on the evaluation, means for allowing the robot to ask for instructions by voice when performing a task, means for notifying the robot by voice of the generated response, means for analyzing the robot's operation history and question content and generating feedback, and means for providing guidance to improve the robot's work efficiency based on the feedback. As a result, new members and robots can receive appropriate guidance and feedback in real time, which can significantly improve work efficiency and the effectiveness of training.

[0510] "Voice input means" refers to a device or software that allows a system to receive voice input from a user.

[0511] "Text conversion means" refers to a device or software used to convert received voice input into text data.

[0512] "Response generation means" refers to a device or software that analyzes text data and generates an appropriate response based on its content.

[0513] "Notification means" refers to a device or software that informs the user of generated responses or instructions via voice or text.

[0514] "Real-time instruction generation means" refers to a device or software that instantly generates instructions related to work and transmits them to the user.

[0515] "Means for collecting behavioral history" refers to a device or software for recording and storing a history of a user's actions and operations.

[0516] "Evaluation means" refers to a device or software used to analyze and evaluate collected behavioral history and questionnaire content.

[0517] "Feedback generation means" refers to a device or software that generates appropriate feedback based on evaluations and notifies the user.

[0518] A "robot instruction and questioning means" refers to a device or software that allows a robot to give instructions or ask questions using voice when performing tasks.

[0519] "Robot notification means" refers to a device or software used to notify a robot of its generated response via voice.

[0520] "Action history analysis means" refers to a device or software that analyzes the robot's action history and question content to generate feedback.

[0521] "Efficiency improvement guidance means" refers to a device or software that provides specific guidance to improve the work efficiency of robots based on feedback.

[0522] As an embodiment of this invention, a system for supporting the operational training of robots in a factory will be described. This system provides real-time guidance and answers to questions while the robot is performing its tasks, and provides feedback to improve operational efficiency.

[0523] First, the robot inputs questions and instructions that arise during its work via voice input devices (e.g., smartphones with microphones). For example, it might say, "Please tell me how to attach this part."

[0524] Voice input devices convert the input speech into text data. This is done using speech recognition software such as the Google Speech-to-Text API. This text data is then sent to a server over the internet.

[0525] The server analyzes the received text data using natural language processing software such as the OpenAI GPT model and generates an appropriate response. For example, it might generate a response like, "To install this part, first set part A in position, and then secure it with screws."

[0526] The generated responses are converted into speech using speech synthesis software (e.g., Amazon Polly) and communicated to the robot via voice. This process allows the robot to receive appropriate guidance in real time.

[0527] Furthermore, the robot's behavior history and question content are continuously collected and stored on a server. The server performs analysis based on the collected data to evaluate the robot's work efficiency. Because this analysis involves handling a large amount of data, a database management system (e.g., MySQL, PostgreSQL) is used.

[0528] Based on the evaluation results, feedback is generated. For example, specific instructions such as "Work progress is 70%. Next, install part B" are generated and notified to the robot. This allows the robot to perform its tasks efficiently.

[0529] As a concrete example, imagine a scenario where a factory robot is assembling parts. If the robot asks, "What is the next task?" via a voice input device, the server immediately generates a response, "Next, attach part B," and notifies the robot by voice. This allows the robot to receive instructions and quickly begin the next task.

[0530] Furthermore, the following are examples of prompt statements that can be input to the generative AI model.

[0531] Question: How do I install this part?

[0532] Answer: To install this part, first set part A in place, and then secure it with screws.

[0533] In this way, robots can perform their tasks while receiving appropriate guidance in real time, significantly improving work efficiency and the effectiveness of training.

[0534] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0535] Step 1:

[0536] The user (robot) inputs questions or instructions through a voice input device. For example, it might say, "Please tell me how to install this part." The input here is voice data.

[0537] Step 2:

[0538] The device (voice input device) converts the input voice data into text data using the Google Speech-to-Text API. This conversion process transforms the voice data into the text "Please tell me how to install this part."

[0539] Step 3:

[0540] The terminal sends the converted text data to the server via the internet. Here, the input is text data, and the output is the data sent to the server.

[0541] Step 4:

[0542] The server analyzes the received text data using an OpenAI GPT model and generates an appropriate response. Specifically, it understands the content of the text data and, based on that, outputs a response such as, "To install this part, first set part A in position, and then secure it with screws."

[0543] Step 5:

[0544] The server converts the generated responses into speech data using text-to-speech software such as Amazon Polly. The input here is the generated text data, and the output is speech data.

[0545] Step 6:

[0546] The server sends the generated audio data to the terminal. The terminal notifies the user (robot) of the transmitted audio data. In this case, the input is the audio data from the server, and the output is the audio notification to the user.

[0547] Step 7:

[0548] The robot continues its task based on the voice instructions it receives. For example, it might execute the instruction, "Set part A and secure it with screws." In this case, the input is the voice instruction, and the output is the corresponding action.

[0549] Step 8:

[0550] The terminal continuously collects the robot's behavior history and question content and sends it to the server. The input here is the robot's behavior history and question content, and the output is the data sent to the server.

[0551] Step 9:

[0552] The server analyzes the collected data and evaluates the robot's operational efficiency. The input here is the collected data, and the output is the evaluation result.

[0553] Step 10:

[0554] The server generates feedback based on the evaluation results and notifies the robot via the terminal. For example, it might generate feedback such as, "Work progress is 70%. Next, install part B." Here, the input is the evaluation result, and the output is the feedback data.

[0555] Step 11:

[0556] The robot improves its operations based on the feedback provided. Here, the input is the feedback data, and the output is the improved operation.

[0557] 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.

[0558] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[0559] Specifically, the system operates using the following steps.

[0560] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the converted text information to the server. The server verifies the received username and password and sends the authentication result to the device. The device notifies the user of the authentication result by voice.

[0561] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0562] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[0563] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0564] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[0565] This system allows users to receive real-time guidance and emotionally responsive support while performing their tasks, significantly improving the effectiveness of training and increasing work efficiency.

[0566] The following describes the processing flow.

[0567] Step 1: User login operation

[0568] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[0569] The device records the audio and converts it into text data using speech recognition software.

[0570] The device sends the text information converted from the speech to the server.

[0571] Step 2: Authentication Process

[0572] The server compares the received username and password with the database to perform authentication.

[0573] The server generates an authentication success or failure result and sends it to the terminal.

[0574] The device receives the authentication result from the server and notifies the user via voice.

[0575] Step 3: Generate and notify the lecture plan

[0576] The server retrieves the job description of the new member user from the database.

[0577] The server generates a lecture plan tailored to the specific tasks.

[0578] The server sends the generated lecture plan to the terminal.

[0579] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[0580] Step 4: Work progress and instructions

[0581] The device monitors the user's location and movements using sensors.

[0582] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[0583] Step 5: Handling the Question

[0584] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[0585] The device records the audio and converts it into text data using speech recognition software.

[0586] The terminal sends the converted question text to the server.

[0587] Step 6: Emotional Analysis

[0588] The server analyzes the question content and uses an emotion recognition engine to analyze the user's emotional state.

[0589] For example, if the server detects that the user is nervous, it will soften the tone of its response.

[0590] Step 7: Generating the answer

[0591] Based on the analysis results, the server generates a response such as, "This dish comes with french fries as a side dish. We can confidently recommend it."

[0592] The server sends the generated response to the terminal.

[0593] Step 8: Notification of response

[0594] The device notifies the user of the generated response via voice.

[0595] Step 9: Collecting activity history

[0596] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[0597] The server saves the activity history to a database.

[0598] Step 10: Provide evaluation and feedback

[0599] The server generates a user evaluation report based on the behavioral history it has collected.

[0600] The server sends the evaluation results to the terminal.

[0601] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[0602] If the server determines, based on analysis by its emotion recognition engine, that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0603] The device notifies the user of that feedback via voice.

[0604] This detailed processing flow allows users to receive real-time guidance and emotionally responsive support while performing their tasks, improving training efficiency and enhancing the quality of work.

[0605] (Example 2)

[0606] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0607] Current business training support systems struggle to effectively utilize user voice input for training, particularly lacking real-time feedback, instructions, and appropriate support tailored to the user's emotional state. As a result, improvements in training effectiveness and operational efficiency may not be fully achieved.

[0608] 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.

[0609] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for transmitting the converted text data to the server for authentication, means for sending the authentication result to a terminal and notifying the user, means for generating text according to the content of the work, means for converting the generated text into voice data and notifying the user, means for converting the user's question voice into text data, means for transmitting the converted text data to the server and recognizing the user's emotions, means for generating an answer based on the emotion recognition result, means for converting the generated answer from text into voice and notifying the user, means for collecting and evaluating the user's behavior history and question content, and means for generating feedback based on the evaluation and notifying the user. This enables the user to perform their work while receiving appropriate support in real time.

[0610] "Means of accepting voice input" refers to a function that captures the voice spoken by the user.

[0611] "Means of converting to text data" refers to a function that converts audio data into text information.

[0612] "Method of sending to a server for authentication" refers to a function that sends the converted text data to a server via the network to authenticate the user.

[0613] "A means of sending authentication results to the terminal and notifying the user" refers to a function that sends the authentication results from the server to the terminal and informs the user of those results.

[0614] "Means for generating text tailored to the work content" refers to a function that creates text containing necessary information and instructions based on the user's work content.

[0615] "A means of converting generated text into audio data and notifying the user" refers to a function that converts the created text into an audio format and informs the user via voice.

[0616] "Means for converting question audio into text data" refers to a function that converts the audio of a question uttered by a user into text information.

[0617] "Means of recognizing user emotions" refers to a function that analyzes user text data to identify the user's emotional state.

[0618] "Means for generating responses based on emotion recognition results" refers to a function that creates appropriate responses by taking into account the user's emotional state.

[0619] "A means of converting generated responses from text to audio and notifying the user" refers to a function that converts the text of the generated response into an audio format and informs the user of it audibly.

[0620] "Means for collecting and evaluating behavioral history and question content" refers to a function that records user behavior and question content, and analyzes and evaluates that data.

[0621] "A means of generating feedback and notifying users" refers to a function that creates feedback based on evaluation results and informs users of it.

[0622] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects the user's behavior history and question content, and provides feedback based on the evaluation results.

[0623] Hardware and software configuration

[0624] Hardware:

[0625] Smart devices: These are devices that accept voice input, such as smartphones and tablets.

[0626] Server: A device that performs authentication, data analysis, response generation, and evaluation.

[0627] software:

[0628] Speech recognition software: Uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[0629] Text-to-speech software: Use Amazon Polly or Google Cloud Text-to-Speech to convert text data into speech data.

[0630] Emotion recognition engine: Uses IBM Watson Tone Analyzer to analyze the user's emotional state from text data.

[0631] System operation

[0632] Voice input acceptance and authentication:

[0633] The user puts on a smart device and says "Login, Username: User123, Password: ". The device records the voice and converts it into text data using speech recognition software. The device sends this text data to a server, which performs authentication. Once the authentication result is obtained, the result is sent to the device and notified to the user using speech synthesis software. For example, it might notify the user, "Login successful."

[0634] Generating a business lecture plan:

[0635] After authentication is complete, the server retrieves the user's job description from the database and generates a corresponding lecture plan. For example, if a user starts customer service, the server generates a "Basic Waiter Job Lecture Plan." This plan is sent to the terminal and notified to the user using speech synthesis software. For example, it might notify the user, "Starting customer service. First, you will learn how to take orders."

[0636] Handling questions and answers:

[0637] If a user has a question during work, for example, "What is the side dish for this dish?", they can ask it aloud. The terminal records this question and converts it into text data using speech recognition software. This text data is sent to a server, where the server analyzes the user's emotional state using an emotion recognition engine. For example, if the server analyzes that the user is nervous, it will generate a response in a softer tone. It will generate a response such as, "The side dish for this dish is french fries. I can recommend it with confidence," and convert this back into audio data to notify the user.

[0638] Collecting behavioral history and providing feedback:

[0639] The terminal periodically sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server evaluates the collected data and generates feedback. For example, it might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself," and then convert this into audio data to notify the user.

[0640] Examples of specific actions and prompt statements.

[0641] Example of operation:

[0642] If a user asks, "What should I do? I can't take this order properly," the terminal records the question and sends it to the server. The server uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone, such as, "First, let's check the menu. Please proceed without rushing." When this is communicated to the user as an audio message, they can continue their work with peace of mind.

[0643] Example of a prompt:

[0644] Question: "What should I do? I can't seem to get this order."

[0645] User's emotional state: Tension

[0646] Response tone: Gentle

[0647] Answer: "First, let's check the menu. Take your time and don't rush."

[0648] This system allows users to receive appropriate support in real time while performing their tasks. This is expected to significantly improve the effectiveness of training and increase work efficiency.

[0649] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0650] Step 1:

[0651] Users log in to their smart devices using voice commands.

[0652] Input: Voice input "Login, Username: User123, Password:"

[0653] Operation: The device's built-in microphone records the audio.

[0654] Output: Audio data

[0655] Step 2:

[0656] The device collects voice data and converts it into text data using speech recognition software.

[0657] Input: Audio data

[0658] Operation: The device uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[0659] Output: Text data "Login, Username: User123, Password: "

[0660] Step 3:

[0661] The terminal sends the converted text data to the server for authentication.

[0662] Input: Text data "Login, Username: User123, Password: "

[0663] Operation: The terminal sends text data to the server as an HTTP request. The server performs authentication by matching it with the database.

[0664] Output: Authentication result (success or failure)

[0665] Step 4:

[0666] The server sends the authentication result to the terminal, and the terminal notifies the user of it.

[0667] Input: Authentication result (success or failure)

[0668] Operation: The server returns the authentication result to the terminal in JSON format. The terminal converts this into a voice message using speech synthesis software (such as Amazon Polly) and notifies the user. Specifically, it notifies the user of either "Login successful" or "Login failed."

[0669] Output: Voice notification

[0670] Step 5:

[0671] The server generates a lecture plan based on the work content and sends it to the terminal.

[0672] Input: User's business information (obtained from database)

[0673] Operation: The server retrieves the user's job description and generates a corresponding lecture plan. As an example, it generates a "Basic Lecture Plan for Waiter Duties."

[0674] Output: Lecture plan

[0675] Step 6:

[0676] The device receives the lecture plan and notifies the user via voice.

[0677] Input: Lecture plan

[0678] Operation: The terminal analyzes the lecture plan and generates a voice message using speech synthesis software. Specifically, it notifies the user with "Starting customer service duties. First, we will learn how to take orders."

[0679] Output: Voice notification

[0680] Step 7:

[0681] During work, the user asks a question, and the terminal converts the question from voice data into text data and sends it to the server.

[0682] Input: Voice input "What side dishes are served with this dish?"

[0683] Operation: The device records the question and converts it into text data using the Google Cloud Speech-to-Text API. The converted text data is then sent to the server as an HTTP request.

[0684] Output: Text data "What side dishes are served with this dish?"

[0685] Step 8:

[0686] The server analyzes the question and the user's emotional state, generates an appropriate answer, and sends it to the terminal.

[0687] Input: Text data "What side dishes are served with this dish?"

[0688] Operation: The server analyzes the question and uses IBM Watson Tone Analyzer to analyze the emotional state. Based on the analysis results, it generates a response in a soft tone. Specifically, it might generate something like, "This dish comes with french fries as a side dish. I can confidently recommend it."

[0689] Output: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[0690] Step 9:

[0691] The device notifies the user of the generated response via voice.

[0692] Input: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[0693] Operation: The terminal converts the received response into a voice message using speech synthesis software and notifies the user.

[0694] Output: Voice notification

[0695] Step 10:

[0696] The device sends the user's activity history to the server, and the server generates evaluations and feedback and sends them back to the device.

[0697] Input: User activity history (instructions received, questions asked, progress of tasks)

[0698] Operation: The device periodically sends its activity history to the server. The server evaluates this and generates feedback. Example: It might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0699] Output: Evaluation results and feedback

[0700] Step 11:

[0701] The device notifies the user of the evaluation results and feedback via voice.

[0702] Input: Evaluation results and feedback "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0703] Operation: The terminal converts the received evaluation results and feedback into a voice message using speech synthesis software and notifies the user.

[0704] Output: Voice notification

[0705] (Application Example 2)

[0706] 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."

[0707] Traditionally, training new employees has typically involved using text-based manuals and videos. However, these methods struggle to address individual user emotional states and stress levels, making effective training difficult. Furthermore, they are ineffective at providing real-time support and feedback, highlighting the need for improved training efficiency and quality. In addition, providing appropriate support for employees experiencing tension and anxiety in real-world settings such as physical stores is crucial. To address these challenges, a system is needed that analyzes user emotional states and provides responses and instructions in an appropriate tone.

[0708] 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.

[0709] In this invention, the server includes means for analyzing the user's emotions from voice input and text data, means for generating responses and instructions in an appropriate tone based on the emotion analysis results, means for allowing the user to input login information by voice using a smart device, and means for providing real-time instructions in an appropriate tone according to the user's emotional state. This makes it possible to provide new members with job training that is appropriately customized in real time according to the user's emotional state, including guidance and support.

[0710] "Voice input" refers to voice information spoken by the user.

[0711] "Text data" refers to data obtained by converting audio information into written text.

[0712] "Emotional analysis" is the process of analyzing a user's emotional state from audio and text data.

[0713] "Answer generation" refers to the process by which a system produces appropriate answers to user questions and requests.

[0714] "Instruction generation" refers to the system generating instructions related to the user's work in real time.

[0715] "Activity history" refers to a record of actions taken by a user while using the system.

[0716] "Feedback" refers to a system evaluating a user's behavior and emotional state and notifying the user of the results.

[0717] A "smart device" refers to a device that has functions such as voice input and display, and smart glasses are an example.

[0718] "Login information" refers to authentication data necessary for a user to access the system.

[0719] "Tone" refers to the pitch or atmosphere of a voice, and it is adjusted according to the emotion being conveyed.

[0720] "Real-time instructions" are instructions that are provided instantly to the user while they are performing a task.

[0721] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[0722] Specifically, the system operates in the following steps:

[0723] First, the user puts on a smart device and performs a voice login operation. For example, if the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the text information converted from the voice to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[0724] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user's job is customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0725] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[0726] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0727] The hardware used includes smart devices (e.g., smart glasses), and the software includes a speech recognition library (speech_recognition), a speech synthesis library (pyttsx3), and an emotion recognition engine (a hypothetical emotion_recognition library).

[0728] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[0729] An example of a prompt for a generative AI model is: "When a user asks, 'What comes with this dish?', sentiment analysis will be performed based on the user's voice data. For example, if it is determined that the user is nervous, please generate a response in a gentle tone such as, 'This dish comes with a salad. Please tell us without hesitation.'"

[0730] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0731] Step 1:

[0732] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice. The recorded voice data is converted into text data by speech recognition software. This converted text data is sent to the server. The server compares the received username and password with the database and sends the authentication result (success or failure) to the device. The device notifies the user of the authentication result by voice.

[0733] Input: User's voice data

[0734] Output: Text data, authentication result

[0735] Step 2:

[0736] The server retrieves the job description of the new member user from the database. It generates a lecture plan tailored to the job description and sends it to the terminal. The terminal then notifies the user via voice based on the received lecture plan. The notification might say something like, "We will now begin the basic customer service lecture plan. First, we will learn how to take orders."

[0737] Input: User's job description

[0738] Output: Lecture plan

[0739] Step 3:

[0740] When a user encounters a question during their work, they can ask it by voice. For example, they might say, "What are the side dishes for this dish?" The terminal converts the voice into text and sends it to the server. The server analyzes the question and further analyzes the user's emotional state from the voice data using an emotion recognition engine. Based on the analysis results, the server adjusts the tone of the response, generates an appropriate answer, and sends it to the terminal. The terminal then notifies the user of the generated answer by voice.

[0741] Input: User's question audio data

[0742] Output: Appropriate answer

[0743] Step 4:

[0744] The terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs analysis and evaluation. Based on the evaluation results, it generates feedback and sends it to the terminal. For example, it might provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0745] Input: Behavioral history data

[0746] Output: Feedback

[0747] Step 5:

[0748] If necessary, the user will continue to ask questions or receive new instructions. The device repeatedly records and recognizes voices in response to these situations, sends data to the server, the server processes and generates feedback, and the device sends voice notifications.

[0749] Input: Next question or instruction voice data

[0750] Output: The following appropriate answers and instructions

[0751] 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.

[0752] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0753] 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.

[0754] [Third Embodiment]

[0755] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0756] 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.

[0757] 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).

[0758] 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.

[0759] 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.

[0760] 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).

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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".

[0767] As an embodiment of this invention, a system to support job training is described below. This system receives voice input from the user, converts it into text data, analyzes the text data to generate an answer, and notifies the user of the answer. It also generates and notifies the user of job-related instructions in real time. Furthermore, it collects the user's behavior history and question content, performs an evaluation, and provides feedback based on the evaluation.

[0768] The user wears a smart device and performs a voice login operation. When the user says, "Login, Username: User123, Password:", the device converts the voice into text data and sends it to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[0769] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0770] When a user encounters a question during their work, they can ask it by voice. For example, if a user asks, "What is the side dish for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and generates an answer, such as, "The side dish for this dish is french fries." The device then notifies the user of the generated answer by voice.

[0771] Furthermore, the user's behavior history and questions are collected and sent to the server. The server evaluates the user based on the collected data and sends the evaluation results to the device. The device receives the evaluation results and provides voice feedback such as, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[0772] As a concrete example, let's consider a new waiter in a restaurant. The user wears a smart device and, if a question arises while taking an order, asks it by voice. For example, if the user asks, "Which wine would go well with this dish?", the device sends this question to a server, which generates an answer. The device then notifies the user by voice of the generated answer, "Red wine would go well with this dish," enabling the user to provide appropriate service.

[0773] This system allows new members to perform their tasks while receiving real-time guidance from AI, significantly improving the effectiveness of training and increasing work efficiency.

[0774] The following describes the processing flow.

[0775] Step 1: User login operation

[0776] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[0777] The device records the audio and converts it into text data using speech recognition software.

[0778] The device sends the text information converted from the speech to the server.

[0779] Step 2: Authentication Process

[0780] The server compares the received username and password with the database to perform authentication.

[0781] The server generates an authentication success or failure result and sends it to the terminal.

[0782] The device receives the authentication result from the server and notifies the user via voice.

[0783] Step 3: Generate and notify the lecture plan

[0784] The server retrieves the job description of the new member user from the database.

[0785] The server generates a lecture plan tailored to the specific tasks.

[0786] The server sends the generated lecture plan to the terminal.

[0787] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[0788] Step 4: Work progress and instructions

[0789] The device monitors the user's location and movements using sensors.

[0790] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[0791] Step 5: Handling the Question

[0792] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[0793] The device records the audio and converts it into text data using speech recognition software.

[0794] The terminal sends the converted question text to the server.

[0795] The server analyzes the question and generates an appropriate answer.

[0796] The server sends the generated response to the terminal.

[0797] The device will notify the user of the answer via voice.

[0798] Step 6: Collecting activity history

[0799] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[0800] The server saves the activity history to a database.

[0801] Step 7: Provide evaluation and feedback

[0802] The server generates a user evaluation report based on the behavioral history it has collected.

[0803] The server sends the evaluation results to the terminal.

[0804] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[0805] This processing flow allows users to receive real-time guidance, evaluation, and feedback while performing their tasks, significantly improving training efficiency and enhancing the quality of work.

[0806] (Example 1)

[0807] 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."

[0808] Providing appropriate guidance and feedback in real time during on-the-job training for new members is considered difficult. Traditional training methods require specialized trainers, which are not only inefficient but also costly. Furthermore, it is difficult to provide standardized training, and the inability to provide flexible guidance tailored to the abilities of new members is a challenge.

[0809] 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.

[0810] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding answer, means for notifying the user of the generated answer, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for the server to retrieve the user's work content from a database and generate a lecture plan according to the work content, means for sending the lecture plan to a terminal and for the terminal to notify the user by voice, means for acquiring the user's question as voice input, converting it into text and sending it to the server, means for the server to analyze the question content, generate a corresponding answer and send it to the terminal, means for generating feedback based on the evaluation and notifying the user, and means for inputting prompt sentences to a generating AI model in order to operate each of the means. This enables efficient and flexible guidance by providing new members with standardized education and feedback in real time.

[0811] "Voice input" refers to the voice data spoken by the user.

[0812] "Text data" refers to a data format obtained by converting voice input into text.

[0813] "Analysis" refers to the process of understanding text data and deriving appropriate processing or responses.

[0814] "Answer" refers to information, including instructions, that are generated based on the analyzed text data.

[0815] "Notification" refers to the act of communicating generated responses or instructions to the user.

[0816] "Instructions related to work" refers to information that includes specific actions and procedures related to the tasks that the user must perform.

[0817] "Activity history" refers to a record of actions taken and questions asked by a user while using the system.

[0818] "Evaluation" refers to the process of determining a user's performance and progress based on collected behavioral history and questionnaire responses.

[0819] "Feedback" refers to improvement instructions and progress reports provided to users based on evaluation results.

[0820] A "lecture plan" refers to a plan of training content and procedures created based on the user's work.

[0821] A "generative AI model" refers to an artificial intelligence model used for tasks such as analyzing text data, generating responses, and creating lecture plans.

[0822] A "prompt statement" refers to an input statement used to instruct a generative AI model on a specific task.

[0823] "Terminal" refers to hardware such as smart devices and computers used by users.

[0824] A "server" refers to a computer system that handles data processing and management for the entire system.

[0825] A "database" refers to a repository of information that stores users' work details and activity history, and is referenced as needed.

[0826] This invention is a system for supporting job training for new members, providing a means to receive user voice input, convert it into text data, and process it appropriately. Specifically, it involves the coordinated operation of a server, a terminal, and the user.

[0827] Hardware and software usage

[0828] The system is primarily implemented using the following hardware and software.

[0829] hardware

[0830] Smart devices: Devices that allow users to input information using voice. Examples include smartphones and wearable devices.

[0831] Server: A computer system used for centralized data processing and management. This includes cloud servers and on-premises servers.

[0832] software

[0833] Speech recognition software: Converts user voice input into text data. An example is the Google Cloud Speech-to-Text API.

[0834] Database systems: Used to store user information and business data. Examples include MySQL and PostgreSQL.

[0835] Natural language processing engines: These analyze text data and generate responses or instructions. Examples include BERT and GPT-3.

[0836] Text-to-speech software: Converts text data into speech and notifies the user. An example is the Google Cloud Text-to-Speech API.

[0837] System operation example

[0838] Voice recognition and login

[0839] The user logs in using their voice via a smart device. For example, they might say, "Login, Username: User123, Password: ". The device converts the voice into text data using the Google Cloud Speech-to-Text API and sends it to the server. The server queries the database to verify the username and password and sends the authentication result to the device. The device then notifies the user via voice, "Login successful."

[0840] Lecture plan generation and notification

[0841] The server retrieves the job description of a new member user from the database and uses a natural language generation model (such as GPT-3) to generate a lecture plan tailored to that job. For example, if the user works in the service industry, the server generates a "Basic Waiter's Lecture Plan" and sends it to the terminal. The terminal then notifies the user via voice, "Starting service duties. First, you will learn how to take orders."

[0842] User questions and answers

[0843] If a user has a question during work, they can ask it by voice. For example, they might ask, "What is the side dish for this dish?" The terminal converts the voice into text data and sends it to the server. The server analyzes the question using a natural language processing engine such as BERT and generates the optimal answer, "The side dish for this dish is french fries," using a generative AI model such as GPT-3. This is sent to the terminal, which then notifies the user by voice.

[0844] Collection of behavioral history and feedback

[0845] The device continuously sends the user's activity history and questions to the server. The server analyzes this data and generates a user evaluation. Based on the evaluation, it generates instructions and feedback for the next step and sends them to the device. For example, it might notify the user, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[0846] Examples of prompt statements

[0847] The following are specific examples of prompt statements for a generative AI model.

[0848] Example of a question prompt

[0849] Question: Generate the appropriate answer to the question, "What are the side dishes for this dish?"

[0850] Example of a feedback prompt

[0851] Based on the user's activity history and evaluation results, notify the user that their current work progress is 80% and provide feedback that their next task is to learn how to describe the dessert menu.

[0852] This invention allows new members to receive standardized training and feedback in real time, significantly improving work efficiency and the effectiveness of training.

[0853] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0854] Step 1:

[0855] Accepting voice input

[0856] The user speaks into their smart device saying, "Login, Username: User123, Password:". This voice input is captured by the smart device's microphone. The device passes the captured voice data to the Google Cloud Speech-to-Text API, which converts it into text data. The converted text data is in the format "Login, Username: User123, Password:". This text data is then sent from the device to the server via an HTTPS request.

[0857] Step 2:

[0858] Performing user authentication

[0859] The server analyzes the received text data and extracts the username and password. The extracted username and password are then compared against the authentication information stored in the database (e.g., MySQL). Based on this comparison, the server determines whether authentication was successful or unsuccessful and sends the result back to the terminal. For example, if authentication is successful, the terminal will receive a message such as "Login successful," and if it fails, it will receive a message such as "Login failed." The terminal then uses speech synthesis software to convert the authentication result into speech and notifies the user that "Login successful."

[0860] Step 3:

[0861] Acquisition of job description and generation of lecture plan

[0862] The server retrieves the authenticated user's job description from the database. This job description data includes information about the type of work the user is engaged in and specific tasks. Simultaneously, the server uses a generative AI model (e.g., GPT-3) to generate a lecture plan based on the job description. For example, if the user works in customer service, the generated lecture plan will include a "Basic Waiter Job Lecture Plan." This lecture plan is sent to the terminal. The terminal converts the received lecture plan into speech using speech synthesis software and notifies the user, "Starting customer service work. First, you will learn how to take orders."

[0863] Step 4:

[0864] Receiving and providing answers to user questions.

[0865] A user might have a question during work, for example, "What is the side dish for this dish?" This voice input is captured by the smart device's microphone, and the device converts the voice data into text data. The converted text data is sent to a server. The server receives the text data and analyzes the question using a natural language processing engine (such as BERT). Then, using a generative AI model, it generates an appropriate answer, such as "The side dish for this dish is french fries." This answer is sent to the device, which converts it into speech using speech synthesis software and notifies the user, "The side dish for this dish is french fries."

[0866] Step 5:

[0867] Collection and evaluation of behavioral history

[0868] The terminal continuously transmits the user's activity history and questions to the server. The activity history includes a detailed record of how the user is using the system. The server analyzes the collected activity history data and evaluates the user's performance. Based on this evaluation, it generates instructions and feedback for the next step. For example, it might generate something like, "Your current work progress is 80%. Next, you will learn about the dessert menu," and send this to the terminal. The terminal uses speech synthesis software to convert the evaluation results into speech and notify the user.

[0869] (Application Example 1)

[0870] 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."

[0871] Traditional training systems often suffer from delays in providing guidance and feedback to new members, making it difficult to respond appropriately in environments where immediate responses are required. Furthermore, particularly in factory settings, not only is human training required, but also the efficient operation of robots, necessitating a system that provides real-time guidance and feedback. However, existing systems are inadequate in responding to real-time questions and instructions via voice input, making it difficult to provide immediate guidance to improve the efficiency of robot operations.

[0872] 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.

[0873] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding response, means for notifying the user of the generated response, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for generating and notifying the user of feedback based on the evaluation, means for allowing the robot to ask for instructions by voice when performing a task, means for notifying the robot by voice of the generated response, means for analyzing the robot's operation history and question content and generating feedback, and means for providing guidance to improve the robot's work efficiency based on the feedback. As a result, new members and robots can receive appropriate guidance and feedback in real time, which can significantly improve work efficiency and the effectiveness of training.

[0874] "Voice input means" refers to a device or software that allows a system to receive voice input from a user.

[0875] "Text conversion means" refers to a device or software used to convert received voice input into text data.

[0876] "Response generation means" refers to a device or software that analyzes text data and generates an appropriate response based on its content.

[0877] "Notification means" refers to a device or software that informs the user of generated responses or instructions via voice or text.

[0878] "Real-time instruction generation means" refers to a device or software that instantly generates instructions related to work and transmits them to the user.

[0879] "Means for collecting behavioral history" refers to a device or software for recording and storing a history of a user's actions and operations.

[0880] "Evaluation means" refers to a device or software used to analyze and evaluate collected behavioral history and questionnaire content.

[0881] "Feedback generation means" refers to a device or software that generates appropriate feedback based on evaluations and notifies the user.

[0882] A "robot instruction and questioning means" refers to a device or software that allows a robot to give instructions or ask questions using voice when performing tasks.

[0883] "Robot notification means" refers to a device or software used to notify a robot of its generated response via voice.

[0884] "Action history analysis means" refers to a device or software that analyzes the robot's action history and question content to generate feedback.

[0885] "Efficiency improvement guidance means" refers to a device or software that provides specific guidance to improve the work efficiency of robots based on feedback.

[0886] As an embodiment of this invention, a system for supporting the operational training of robots in a factory will be described. This system provides real-time guidance and answers to questions while the robot is performing its tasks, and provides feedback to improve operational efficiency.

[0887] First, the robot inputs questions and instructions that arise during its work via voice input devices (e.g., smartphones with microphones). For example, it might say, "Please tell me how to attach this part."

[0888] Voice input devices convert the input speech into text data. This is done using speech recognition software such as the Google Speech-to-Text API. This text data is then sent to a server over the internet.

[0889] The server analyzes the received text data using natural language processing software such as the OpenAI GPT model and generates an appropriate response. For example, it might generate a response like, "To install this part, first set part A in position, and then secure it with screws."

[0890] The generated responses are converted into speech using speech synthesis software (e.g., Amazon Polly) and communicated to the robot via voice. This process allows the robot to receive appropriate guidance in real time.

[0891] Furthermore, the robot's behavior history and question content are continuously collected and stored on a server. The server performs analysis based on the collected data to evaluate the robot's work efficiency. Because this analysis involves handling a large amount of data, a database management system (e.g., MySQL, PostgreSQL) is used.

[0892] Based on the evaluation results, feedback is generated. For example, specific instructions such as "Work progress is 70%. Next, install part B" are generated and notified to the robot. This allows the robot to perform its tasks efficiently.

[0893] As a concrete example, imagine a scenario where a factory robot is assembling parts. If the robot asks, "What is the next task?" via a voice input device, the server immediately generates a response, "Next, attach part B," and notifies the robot by voice. This allows the robot to receive instructions and quickly begin the next task.

[0894] Furthermore, the following are examples of prompt statements that can be input to the generative AI model.

[0895] Question: How do I install this part?

[0896] Answer: To install this part, first set part A in place, and then secure it with screws.

[0897] In this way, robots can perform their tasks while receiving appropriate guidance in real time, significantly improving work efficiency and the effectiveness of training.

[0898] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0899] Step 1:

[0900] The user (robot) inputs questions or instructions through a voice input device. For example, it might say, "Please tell me how to install this part." The input here is voice data.

[0901] Step 2:

[0902] The device (voice input device) converts the input voice data into text data using the Google Speech-to-Text API. This conversion process transforms the voice data into the text "Please tell me how to install this part."

[0903] Step 3:

[0904] The terminal sends the converted text data to the server via the internet. Here, the input is text data, and the output is the data sent to the server.

[0905] Step 4:

[0906] The server analyzes the received text data using an OpenAI GPT model and generates an appropriate response. Specifically, it understands the content of the text data and, based on that, outputs a response such as, "To install this part, first set part A in position, and then secure it with screws."

[0907] Step 5:

[0908] The server converts the generated responses into speech data using text-to-speech software such as Amazon Polly. The input here is the generated text data, and the output is speech data.

[0909] Step 6:

[0910] The server sends the generated audio data to the terminal. The terminal notifies the user (robot) of the transmitted audio data. In this case, the input is the audio data from the server, and the output is the audio notification to the user.

[0911] Step 7:

[0912] The robot continues its task based on the voice instructions it receives. For example, it might execute the instruction, "Set part A and secure it with screws." In this case, the input is the voice instruction, and the output is the corresponding action.

[0913] Step 8:

[0914] The terminal continuously collects the robot's behavior history and question content and sends it to the server. The input here is the robot's behavior history and question content, and the output is the data sent to the server.

[0915] Step 9:

[0916] The server analyzes the collected data and evaluates the robot's operational efficiency. The input here is the collected data, and the output is the evaluation result.

[0917] Step 10:

[0918] The server generates feedback based on the evaluation results and notifies the robot via the terminal. For example, it might generate feedback such as, "Work progress is 70%. Next, install part B." Here, the input is the evaluation result, and the output is the feedback data.

[0919] Step 11:

[0920] The robot improves its operations based on the feedback provided. Here, the input is the feedback data, and the output is the improved operation.

[0921] 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.

[0922] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[0923] Specifically, the system operates using the following steps.

[0924] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the converted text information to the server. The server verifies the received username and password and sends the authentication result to the device. The device notifies the user of the authentication result by voice.

[0925] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[0926] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[0927] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[0928] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[0929] This system allows users to receive real-time guidance and emotionally responsive support while performing their tasks, significantly improving the effectiveness of training and increasing work efficiency.

[0930] The following describes the processing flow.

[0931] Step 1: User login operation

[0932] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[0933] The device records the audio and converts it into text data using speech recognition software.

[0934] The device sends the text information converted from the speech to the server.

[0935] Step 2: Authentication Process

[0936] The server compares the received username and password with the database to perform authentication.

[0937] The server generates an authentication success or failure result and sends it to the terminal.

[0938] The device receives the authentication result from the server and notifies the user via voice.

[0939] Step 3: Generate and notify the lecture plan

[0940] The server retrieves the job description of the new member user from the database.

[0941] The server generates a lecture plan tailored to the specific tasks.

[0942] The server sends the generated lecture plan to the terminal.

[0943] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[0944] Step 4: Work progress and instructions

[0945] The device monitors the user's location and movements using sensors.

[0946] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[0947] Step 5: Handling the Question

[0948] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[0949] The device records the audio and converts it into text data using speech recognition software.

[0950] The terminal sends the converted question text to the server.

[0951] Step 6: Emotional Analysis

[0952] The server analyzes the question content and uses an emotion recognition engine to analyze the user's emotional state.

[0953] For example, if the server detects that the user is nervous, it will soften the tone of its response.

[0954] Step 7: Generating the answer

[0955] Based on the analysis results, the server generates a response such as, "This dish comes with french fries as a side dish. We can confidently recommend it."

[0956] The server sends the generated response to the terminal.

[0957] Step 8: Notification of response

[0958] The device notifies the user of the generated response via voice.

[0959] Step 9: Collecting activity history

[0960] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[0961] The server saves the activity history to a database.

[0962] Step 10: Provide evaluation and feedback

[0963] The server generates a user evaluation report based on the behavioral history it has collected.

[0964] The server sends the evaluation results to the terminal.

[0965] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[0966] If the server determines, based on analysis by its emotion recognition engine, that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[0967] The device notifies the user of that feedback via voice.

[0968] This detailed processing flow allows users to receive real-time guidance and emotionally responsive support while performing their tasks, improving training efficiency and enhancing the quality of work.

[0969] (Example 2)

[0970] 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."

[0971] Current business training support systems struggle to effectively utilize user voice input for training, particularly lacking real-time feedback, instructions, and appropriate support tailored to the user's emotional state. As a result, improvements in training effectiveness and operational efficiency may not be fully achieved.

[0972] 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.

[0973] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for transmitting the converted text data to the server for authentication, means for sending the authentication result to a terminal and notifying the user, means for generating text according to the content of the work, means for converting the generated text into voice data and notifying the user, means for converting the user's question voice into text data, means for transmitting the converted text data to the server and recognizing the user's emotions, means for generating an answer based on the emotion recognition result, means for converting the generated answer from text into voice and notifying the user, means for collecting and evaluating the user's behavior history and question content, and means for generating feedback based on the evaluation and notifying the user. This enables the user to perform their work while receiving appropriate support in real time.

[0974] "Means of accepting voice input" refers to a function that captures the voice spoken by the user.

[0975] "Means of converting to text data" refers to a function that converts audio data into text information.

[0976] "Method of sending to a server for authentication" refers to a function that sends the converted text data to a server via the network to authenticate the user.

[0977] "A means of sending authentication results to the terminal and notifying the user" refers to a function that sends the authentication results from the server to the terminal and informs the user of those results.

[0978] "Means for generating text tailored to the work content" refers to a function that creates text containing necessary information and instructions based on the user's work content.

[0979] "A means of converting generated text into audio data and notifying the user" refers to a function that converts the created text into an audio format and informs the user via voice.

[0980] "Means for converting question audio into text data" refers to a function that converts the audio of a question uttered by a user into text information.

[0981] "Means of recognizing user emotions" refers to a function that analyzes user text data to identify the user's emotional state.

[0982] "Means for generating responses based on emotion recognition results" refers to a function that creates appropriate responses by taking into account the user's emotional state.

[0983] "A means of converting generated responses from text to audio and notifying the user" refers to a function that converts the text of the generated response into an audio format and informs the user of it audibly.

[0984] "Means for collecting and evaluating behavioral history and question content" refers to a function that records user behavior and question content, and analyzes and evaluates that data.

[0985] "A means of generating feedback and notifying users" refers to a function that creates feedback based on evaluation results and informs users of it.

[0986] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects the user's behavior history and question content, and provides feedback based on the evaluation results.

[0987] Hardware and software configuration

[0988] Hardware:

[0989] Smart devices: These are devices that accept voice input, such as smartphones and tablets.

[0990] Server: A device that performs authentication, data analysis, response generation, and evaluation.

[0991] software:

[0992] Speech recognition software: Uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[0993] Text-to-speech software: Use Amazon Polly or Google Cloud Text-to-Speech to convert text data into speech data.

[0994] Emotion recognition engine: Uses IBM Watson Tone Analyzer to analyze the user's emotional state from text data.

[0995] System operation

[0996] Voice input acceptance and authentication:

[0997] The user puts on a smart device and says "Login, Username: User123, Password: ". The device records the voice and converts it into text data using speech recognition software. The device sends this text data to a server, which performs authentication. Once the authentication result is obtained, the result is sent to the device and notified to the user using speech synthesis software. For example, it might notify the user, "Login successful."

[0998] Generating a business lecture plan:

[0999] After authentication is complete, the server retrieves the user's job description from the database and generates a corresponding lecture plan. For example, if a user starts customer service, the server generates a "Basic Waiter Job Lecture Plan." This plan is sent to the terminal and notified to the user using speech synthesis software. For example, it might notify the user, "Starting customer service. First, you will learn how to take orders."

[1000] Handling questions and answers:

[1001] If a user has a question during work, for example, "What is the side dish for this dish?", they can ask it aloud. The terminal records this question and converts it into text data using speech recognition software. This text data is sent to a server, where the server analyzes the user's emotional state using an emotion recognition engine. For example, if the server analyzes that the user is nervous, it will generate a response in a softer tone. It will generate a response such as, "The side dish for this dish is french fries. I can recommend it with confidence," and convert this back into audio data to notify the user.

[1002] Collecting behavioral history and providing feedback:

[1003] The terminal periodically sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server evaluates the collected data and generates feedback. For example, it might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself," and then convert this into audio data to notify the user.

[1004] Examples of specific actions and prompt statements.

[1005] Example of operation:

[1006] If a user asks, "What should I do? I can't take this order properly," the terminal records the question and sends it to the server. The server uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone, such as, "First, let's check the menu. Please proceed without rushing." When this is communicated to the user as an audio message, they can continue their work with peace of mind.

[1007] Example of a prompt:

[1008] Question: "What should I do? I can't seem to get this order."

[1009] User's emotional state: Tension

[1010] Response tone: Gentle

[1011] Answer: "First, let's check the menu. Take your time and don't rush."

[1012] This system allows users to receive appropriate support in real time while performing their tasks. This is expected to significantly improve the effectiveness of training and increase work efficiency.

[1013] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1014] Step 1:

[1015] Users log in to their smart devices using voice commands.

[1016] Input: Voice input "Login, Username: User123, Password:"

[1017] Operation: The device's built-in microphone records the audio.

[1018] Output: Audio data

[1019] Step 2:

[1020] The device collects voice data and converts it into text data using speech recognition software.

[1021] Input: Audio data

[1022] Operation: The device uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[1023] Output: Text data "Login, Username: User123, Password: "

[1024] Step 3:

[1025] The terminal sends the converted text data to the server for authentication.

[1026] Input: Text data "Login, Username: User123, Password: "

[1027] Operation: The terminal sends text data to the server as an HTTP request. The server performs authentication by matching it with the database.

[1028] Output: Authentication result (success or failure)

[1029] Step 4:

[1030] The server sends the authentication result to the terminal, and the terminal notifies the user of it.

[1031] Input: Authentication result (success or failure)

[1032] Operation: The server returns the authentication result to the terminal in JSON format. The terminal converts this into a voice message using speech synthesis software (such as Amazon Polly) and notifies the user. Specifically, it notifies the user of either "Login successful" or "Login failed."

[1033] Output: Voice notification

[1034] Step 5:

[1035] The server generates a lecture plan based on the work content and sends it to the terminal.

[1036] Input: User's business information (obtained from database)

[1037] Operation: The server retrieves the user's job description and generates a corresponding lecture plan. As an example, it generates a "Basic Lecture Plan for Waiter Duties."

[1038] Output: Lecture plan

[1039] Step 6:

[1040] The device receives the lecture plan and notifies the user via voice.

[1041] Input: Lecture plan

[1042] Operation: The terminal analyzes the lecture plan and generates a voice message using speech synthesis software. Specifically, it notifies the user with "Starting customer service duties. First, we will learn how to take orders."

[1043] Output: Voice notification

[1044] Step 7:

[1045] During work, the user asks a question, and the terminal converts the question from voice data into text data and sends it to the server.

[1046] Input: Voice input "What side dishes are served with this dish?"

[1047] Operation: The device records the question and converts it into text data using the Google Cloud Speech-to-Text API. The converted text data is then sent to the server as an HTTP request.

[1048] Output: Text data "What side dishes are served with this dish?"

[1049] Step 8:

[1050] The server analyzes the question and the user's emotional state, generates an appropriate answer, and sends it to the terminal.

[1051] Input: Text data "What side dishes are served with this dish?"

[1052] Operation: The server analyzes the question and uses IBM Watson Tone Analyzer to analyze the emotional state. Based on the analysis results, it generates a response in a soft tone. Specifically, it might generate something like, "This dish comes with french fries as a side dish. I can confidently recommend it."

[1053] Output: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[1054] Step 9:

[1055] The device notifies the user of the generated response via voice.

[1056] Input: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[1057] Operation: The terminal converts the received response into a voice message using speech synthesis software and notifies the user.

[1058] Output: Voice notification

[1059] Step 10:

[1060] The device sends the user's activity history to the server, and the server generates evaluations and feedback and sends them back to the device.

[1061] Input: User activity history (instructions received, questions asked, progress of tasks)

[1062] Operation: The device periodically sends its activity history to the server. The server evaluates this and generates feedback. Example: It might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[1063] Output: Evaluation results and feedback

[1064] Step 11:

[1065] The device notifies the user of the evaluation results and feedback via voice.

[1066] Input: Evaluation results and feedback "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[1067] Operation: The terminal converts the received evaluation results and feedback into a voice message using speech synthesis software and notifies the user.

[1068] Output: Voice notification

[1069] (Application Example 2)

[1070] 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."

[1071] Traditionally, training new employees has typically involved using text-based manuals and videos. However, these methods struggle to address individual user emotional states and stress levels, making effective training difficult. Furthermore, they are ineffective at providing real-time support and feedback, highlighting the need for improved training efficiency and quality. In addition, providing appropriate support for employees experiencing tension and anxiety in real-world settings such as physical stores is crucial. To address these challenges, a system is needed that analyzes user emotional states and provides responses and instructions in an appropriate tone.

[1072] 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.

[1073] In this invention, the server includes means for analyzing the user's emotions from voice input and text data, means for generating responses and instructions in an appropriate tone based on the emotion analysis results, means for allowing the user to input login information by voice using a smart device, and means for providing real-time instructions in an appropriate tone according to the user's emotional state. This makes it possible to provide new members with job training that is appropriately customized in real time according to the user's emotional state, including guidance and support.

[1074] "Voice input" refers to voice information spoken by the user.

[1075] "Text data" refers to data obtained by converting audio information into written text.

[1076] "Emotional analysis" is the process of analyzing a user's emotional state from audio and text data.

[1077] "Answer generation" refers to the process by which a system produces appropriate answers to user questions and requests.

[1078] "Instruction generation" refers to the system generating instructions related to the user's work in real time.

[1079] "Activity history" refers to a record of actions taken by a user while using the system.

[1080] "Feedback" refers to a system evaluating a user's behavior and emotional state and notifying the user of the results.

[1081] A "smart device" refers to a device that has functions such as voice input and display, and smart glasses are an example.

[1082] "Login information" refers to authentication data necessary for a user to access the system.

[1083] "Tone" refers to the pitch or atmosphere of a voice, and it is adjusted according to the emotion being conveyed.

[1084] "Real-time instructions" are instructions that are provided instantly to the user while they are performing a task.

[1085] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[1086] Specifically, the system operates in the following steps:

[1087] First, the user puts on a smart device and performs a voice login operation. For example, if the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the text information converted from the voice to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[1088] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user's job is customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[1089] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[1090] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[1091] The hardware used includes smart devices (e.g., smart glasses), and the software includes a speech recognition library (speech_recognition), a speech synthesis library (pyttsx3), and an emotion recognition engine (a hypothetical emotion_recognition library).

[1092] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[1093] An example of a prompt for a generative AI model is: "When a user asks, 'What comes with this dish?', sentiment analysis will be performed based on the user's voice data. For example, if it is determined that the user is nervous, please generate a response in a gentle tone such as, 'This dish comes with a salad. Please tell us without hesitation.'"

[1094] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1095] Step 1:

[1096] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice. The recorded voice data is converted into text data by speech recognition software. This converted text data is sent to the server. The server compares the received username and password with the database and sends the authentication result (success or failure) to the device. The device notifies the user of the authentication result by voice.

[1097] Input: User's voice data

[1098] Output: Text data, authentication result

[1099] Step 2:

[1100] The server retrieves the job description of the new member user from the database. It generates a lecture plan tailored to the job description and sends it to the terminal. The terminal then notifies the user via voice based on the received lecture plan. The notification might say something like, "We will now begin the basic customer service lecture plan. First, we will learn how to take orders."

[1101] Input: User's job description

[1102] Output: Lecture plan

[1103] Step 3:

[1104] When a user encounters a question during their work, they can ask it by voice. For example, they might say, "What are the side dishes for this dish?" The terminal converts the voice into text and sends it to the server. The server analyzes the question and further analyzes the user's emotional state from the voice data using an emotion recognition engine. Based on the analysis results, the server adjusts the tone of the response, generates an appropriate answer, and sends it to the terminal. The terminal then notifies the user of the generated answer by voice.

[1105] Input: User's question audio data

[1106] Output: Appropriate answer

[1107] Step 4:

[1108] The terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs analysis and evaluation. Based on the evaluation results, it generates feedback and sends it to the terminal. For example, it might provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[1109] Input: Behavioral history data

[1110] Output: Feedback

[1111] Step 5:

[1112] If necessary, the user will continue to ask questions or receive new instructions. The device repeatedly records and recognizes voices in response to these situations, sends data to the server, the server processes and generates feedback, and the device sends voice notifications.

[1113] Input: Next question or instruction voice data

[1114] Output: The following appropriate answers and instructions

[1115] 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.

[1116] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1117] 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.

[1118] [Fourth Embodiment]

[1119] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1120] 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.

[1121] 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).

[1122] 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.

[1123] 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.

[1124] 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).

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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".

[1132] As an embodiment of this invention, a system to support job training is described below. This system receives voice input from the user, converts it into text data, analyzes the text data to generate an answer, and notifies the user of the answer. It also generates and notifies the user of job-related instructions in real time. Furthermore, it collects the user's behavior history and question content, performs an evaluation, and provides feedback based on the evaluation.

[1133] The user wears a smart device and performs a voice login operation. When the user says, "Login, Username: User123, Password:", the device converts the voice into text data and sends it to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[1134] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[1135] When a user encounters a question during their work, they can ask it by voice. For example, if a user asks, "What is the side dish for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and generates an answer, such as, "The side dish for this dish is french fries." The device then notifies the user of the generated answer by voice.

[1136] Furthermore, the user's behavior history and questions are collected and sent to the server. The server evaluates the user based on the collected data and sends the evaluation results to the device. The device receives the evaluation results and provides voice feedback such as, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[1137] As a concrete example, let's consider a new waiter in a restaurant. The user wears a smart device and, if a question arises while taking an order, asks it by voice. For example, if the user asks, "Which wine would go well with this dish?", the device sends this question to a server, which generates an answer. The device then notifies the user by voice of the generated answer, "Red wine would go well with this dish," enabling the user to provide appropriate service.

[1138] This system allows new members to perform their tasks while receiving real-time guidance from AI, significantly improving the effectiveness of training and increasing work efficiency.

[1139] The following describes the processing flow.

[1140] Step 1: User login operation

[1141] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[1142] The device records the audio and converts it into text data using speech recognition software.

[1143] The device sends the text information converted from the speech to the server.

[1144] Step 2: Authentication Process

[1145] The server compares the received username and password with the database to perform authentication.

[1146] The server generates an authentication success or failure result and sends it to the terminal.

[1147] The device receives the authentication result from the server and notifies the user via voice.

[1148] Step 3: Generate and notify the lecture plan

[1149] The server retrieves the job description of the new member user from the database.

[1150] The server generates a lecture plan tailored to the specific tasks.

[1151] The server sends the generated lecture plan to the terminal.

[1152] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[1153] Step 4: Work progress and instructions

[1154] The device monitors the user's location and movements using sensors.

[1155] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[1156] Step 5: Handling the Question

[1157] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[1158] The device records the audio and converts it into text data using speech recognition software.

[1159] The terminal sends the converted question text to the server.

[1160] The server analyzes the question and generates an appropriate answer.

[1161] The server sends the generated response to the terminal.

[1162] The device will notify the user of the answer via voice.

[1163] Step 6: Collecting activity history

[1164] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[1165] The server saves the activity history to a database.

[1166] Step 7: Provide evaluation and feedback

[1167] The server generates a user evaluation report based on the behavioral history it has collected.

[1168] The server sends the evaluation results to the terminal.

[1169] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[1170] This processing flow allows users to receive real-time guidance, evaluation, and feedback while performing their tasks, significantly improving training efficiency and enhancing the quality of work.

[1171] (Example 1)

[1172] 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".

[1173] Providing appropriate guidance and feedback in real time during on-the-job training for new members is considered difficult. Traditional training methods require specialized trainers, which are not only inefficient but also costly. Furthermore, it is difficult to provide standardized training, and the inability to provide flexible guidance tailored to the abilities of new members is a challenge.

[1174] 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.

[1175] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding answer, means for notifying the user of the generated answer, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for the server to retrieve the user's work content from a database and generate a lecture plan according to the work content, means for sending the lecture plan to a terminal and for the terminal to notify the user by voice, means for acquiring the user's question as voice input, converting it into text and sending it to the server, means for the server to analyze the question content, generate a corresponding answer and send it to the terminal, means for generating feedback based on the evaluation and notifying the user, and means for inputting prompt sentences to a generating AI model in order to operate each of the means. This enables efficient and flexible guidance by providing new members with standardized education and feedback in real time.

[1176] "Voice input" refers to the voice data spoken by the user.

[1177] "Text data" refers to a data format obtained by converting voice input into text.

[1178] "Analysis" refers to the process of understanding text data and deriving appropriate processing or responses.

[1179] "Answer" refers to information, including instructions, that are generated based on the analyzed text data.

[1180] "Notification" refers to the act of communicating generated responses or instructions to the user.

[1181] "Instructions related to work" refers to information that includes specific actions and procedures related to the tasks that the user must perform.

[1182] "Activity history" refers to a record of actions taken and questions asked by a user while using the system.

[1183] "Evaluation" refers to the process of determining a user's performance and progress based on collected behavioral history and questionnaire responses.

[1184] "Feedback" refers to improvement instructions and progress reports provided to users based on evaluation results.

[1185] A "lecture plan" refers to a plan of training content and procedures created based on the user's work.

[1186] A "generative AI model" refers to an artificial intelligence model used for tasks such as analyzing text data, generating responses, and creating lecture plans.

[1187] A "prompt statement" refers to an input statement used to instruct a generative AI model on a specific task.

[1188] "Terminal" refers to hardware such as smart devices and computers used by users.

[1189] A "server" refers to a computer system that handles data processing and management for the entire system.

[1190] A "database" refers to a repository of information that stores users' work details and activity history, and is referenced as needed.

[1191] This invention is a system for supporting job training for new members, providing a means to receive user voice input, convert it into text data, and process it appropriately. Specifically, it involves the coordinated operation of a server, a terminal, and the user.

[1192] Hardware and software usage

[1193] The system is primarily implemented using the following hardware and software.

[1194] hardware

[1195] Smart devices: Devices that allow users to input information using voice. Examples include smartphones and wearable devices.

[1196] Server: A computer system used for centralized data processing and management. This includes cloud servers and on-premises servers.

[1197] software

[1198] Speech recognition software: Converts user voice input into text data. An example is the Google Cloud Speech-to-Text API.

[1199] Database systems: Used to store user information and business data. Examples include MySQL and PostgreSQL.

[1200] Natural language processing engines: These analyze text data and generate responses or instructions. Examples include BERT and GPT-3.

[1201] Text-to-speech software: Converts text data into speech and notifies the user. An example is the Google Cloud Text-to-Speech API.

[1202] System operation example

[1203] Voice recognition and login

[1204] The user logs in using their voice via a smart device. For example, they might say, "Login, Username: User123, Password: ". The device converts the voice into text data using the Google Cloud Speech-to-Text API and sends it to the server. The server queries the database to verify the username and password and sends the authentication result to the device. The device then notifies the user via voice, "Login successful."

[1205] Lecture plan generation and notification

[1206] The server retrieves the job description of a new member user from the database and uses a natural language generation model (such as GPT-3) to generate a lecture plan tailored to that job. For example, if the user works in the service industry, the server generates a "Basic Waiter's Lecture Plan" and sends it to the terminal. The terminal then notifies the user via voice, "Starting service duties. First, you will learn how to take orders."

[1207] User questions and answers

[1208] If a user has a question during work, they can ask it by voice. For example, they might ask, "What is the side dish for this dish?" The terminal converts the voice into text data and sends it to the server. The server analyzes the question using a natural language processing engine such as BERT and generates the optimal answer, "The side dish for this dish is french fries," using a generative AI model such as GPT-3. This is sent to the terminal, which then notifies the user by voice.

[1209] Collection of behavioral history and feedback

[1210] The device continuously sends the user's activity history and questions to the server. The server analyzes this data and generates a user evaluation. Based on the evaluation, it generates instructions and feedback for the next step and sends them to the device. For example, it might notify the user, "Your current work progress is 80%. Next, you will learn about the dessert menu."

[1211] Examples of prompt statements

[1212] The following are specific examples of prompt statements for a generative AI model.

[1213] Example of a question prompt

[1214] Question: Generate the appropriate answer to the question, "What are the side dishes for this dish?"

[1215] Example of a feedback prompt

[1216] Based on the user's activity history and evaluation results, notify the user that their current work progress is 80% and provide feedback that their next task is to learn how to describe the dessert menu.

[1217] This invention allows new members to receive standardized training and feedback in real time, significantly improving work efficiency and the effectiveness of training.

[1218] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1219] Step 1:

[1220] Accepting voice input

[1221] The user speaks into their smart device saying, "Login, Username: User123, Password:". This voice input is captured by the smart device's microphone. The device passes the captured voice data to the Google Cloud Speech-to-Text API, which converts it into text data. The converted text data is in the format "Login, Username: User123, Password:". This text data is then sent from the device to the server via an HTTPS request.

[1222] Step 2:

[1223] Performing user authentication

[1224] The server analyzes the received text data and extracts the username and password. The extracted username and password are then compared against the authentication information stored in the database (e.g., MySQL). Based on this comparison, the server determines whether authentication was successful or unsuccessful and sends the result back to the terminal. For example, if authentication is successful, the terminal will receive a message such as "Login successful," and if it fails, it will receive a message such as "Login failed." The terminal then uses speech synthesis software to convert the authentication result into speech and notifies the user that "Login successful."

[1225] Step 3:

[1226] Acquisition of job description and generation of lecture plan

[1227] The server retrieves the authenticated user's job description from the database. This job description data includes information about the type of work the user is engaged in and specific tasks. Simultaneously, the server uses a generative AI model (e.g., GPT-3) to generate a lecture plan based on the job description. For example, if the user works in customer service, the generated lecture plan will include a "Basic Waiter Job Lecture Plan." This lecture plan is sent to the terminal. The terminal converts the received lecture plan into speech using speech synthesis software and notifies the user, "Starting customer service work. First, you will learn how to take orders."

[1228] Step 4:

[1229] Receiving and providing answers to user questions.

[1230] A user might have a question during work, for example, "What is the side dish for this dish?" This voice input is captured by the smart device's microphone, and the device converts the voice data into text data. The converted text data is sent to a server. The server receives the text data and analyzes the question using a natural language processing engine (such as BERT). Then, using a generative AI model, it generates an appropriate answer, such as "The side dish for this dish is french fries." This answer is sent to the device, which converts it into speech using speech synthesis software and notifies the user, "The side dish for this dish is french fries."

[1231] Step 5:

[1232] Collection and evaluation of behavioral history

[1233] The terminal continuously transmits the user's activity history and questions to the server. The activity history includes a detailed record of how the user is using the system. The server analyzes the collected activity history data and evaluates the user's performance. Based on this evaluation, it generates instructions and feedback for the next step. For example, it might generate something like, "Your current work progress is 80%. Next, you will learn about the dessert menu," and send this to the terminal. The terminal uses speech synthesis software to convert the evaluation results into speech and notify the user.

[1234] (Application Example 1)

[1235] 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".

[1236] Traditional training systems often suffer from delays in providing guidance and feedback to new members, making it difficult to respond appropriately in environments where immediate responses are required. Furthermore, particularly in factory settings, not only is human training required, but also the efficient operation of robots, necessitating a system that provides real-time guidance and feedback. However, existing systems are inadequate in responding to real-time questions and instructions via voice input, making it difficult to provide immediate guidance to improve the efficiency of robot operations.

[1237] 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.

[1238] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for analyzing the text data and generating a corresponding response, means for notifying the user of the generated response, means for generating and notifying the user of work-related instructions in real time, means for collecting and evaluating the user's behavior history and question content, means for generating and notifying the user of feedback based on the evaluation, means for allowing the robot to ask for instructions by voice when performing a task, means for notifying the robot by voice of the generated response, means for analyzing the robot's operation history and question content and generating feedback, and means for providing guidance to improve the robot's work efficiency based on the feedback. As a result, new members and robots can receive appropriate guidance and feedback in real time, which can significantly improve work efficiency and the effectiveness of training.

[1239] "Voice input means" refers to a device or software that allows a system to receive voice input from a user.

[1240] "Text conversion means" refers to a device or software used to convert received voice input into text data.

[1241] "Response generation means" refers to a device or software that analyzes text data and generates an appropriate response based on its content.

[1242] "Notification means" refers to a device or software that informs the user of generated responses or instructions via voice or text.

[1243] "Real-time instruction generation means" refers to a device or software that instantly generates instructions related to work and transmits them to the user.

[1244] "Means for collecting behavioral history" refers to a device or software for recording and storing a history of a user's actions and operations.

[1245] "Evaluation means" refers to a device or software used to analyze and evaluate collected behavioral history and questionnaire content.

[1246] "Feedback generation means" refers to a device or software that generates appropriate feedback based on evaluations and notifies the user.

[1247] A "robot instruction and questioning means" refers to a device or software that allows a robot to give instructions or ask questions using voice when performing tasks.

[1248] "Robot notification means" refers to a device or software used to notify a robot of its generated response via voice.

[1249] "Action history analysis means" refers to a device or software that analyzes the robot's action history and question content to generate feedback.

[1250] "Efficiency improvement guidance means" refers to a device or software that provides specific guidance to improve the work efficiency of robots based on feedback.

[1251] As an embodiment of this invention, a system for supporting the operational training of robots in a factory will be described. This system provides real-time guidance and answers to questions while the robot is performing its tasks, and provides feedback to improve operational efficiency.

[1252] First, the robot inputs questions and instructions that arise during its work via voice input devices (e.g., smartphones with microphones). For example, it might say, "Please tell me how to attach this part."

[1253] Voice input devices convert the input speech into text data. This is done using speech recognition software such as the Google Speech-to-Text API. This text data is then sent to a server over the internet.

[1254] The server analyzes the received text data using natural language processing software such as the OpenAI GPT model and generates an appropriate response. For example, it might generate a response like, "To install this part, first set part A in position, and then secure it with screws."

[1255] The generated responses are converted into speech using speech synthesis software (e.g., Amazon Polly) and communicated to the robot via voice. This process allows the robot to receive appropriate guidance in real time.

[1256] Furthermore, the robot's behavior history and question content are continuously collected and stored on a server. The server performs analysis based on the collected data to evaluate the robot's work efficiency. Because this analysis involves handling a large amount of data, a database management system (e.g., MySQL, PostgreSQL) is used.

[1257] Based on the evaluation results, feedback is generated. For example, specific instructions such as "Work progress is 70%. Next, install part B" are generated and notified to the robot. This allows the robot to perform its tasks efficiently.

[1258] As a concrete example, imagine a scenario where a factory robot is assembling parts. If the robot asks, "What is the next task?" via a voice input device, the server immediately generates a response, "Next, attach part B," and notifies the robot by voice. This allows the robot to receive instructions and quickly begin the next task.

[1259] Furthermore, the following are examples of prompt statements that can be input to the generative AI model.

[1260] Question: How do I install this part?

[1261] Answer: To install this part, first set part A in place, and then secure it with screws.

[1262] In this way, robots can perform their tasks while receiving appropriate guidance in real time, significantly improving work efficiency and the effectiveness of training.

[1263] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1264] Step 1:

[1265] The user (robot) inputs questions or instructions through a voice input device. For example, it might say, "Please tell me how to install this part." The input here is voice data.

[1266] Step 2:

[1267] The device (voice input device) converts the input voice data into text data using the Google Speech-to-Text API. This conversion process transforms the voice data into the text "Please tell me how to install this part."

[1268] Step 3:

[1269] The terminal sends the converted text data to the server via the internet. Here, the input is text data, and the output is the data sent to the server.

[1270] Step 4:

[1271] The server analyzes the received text data using an OpenAI GPT model and generates an appropriate response. Specifically, it understands the content of the text data and, based on that, outputs a response such as, "To install this part, first set part A in position, and then secure it with screws."

[1272] Step 5:

[1273] The server converts the generated responses into speech data using text-to-speech software such as Amazon Polly. The input here is the generated text data, and the output is speech data.

[1274] Step 6:

[1275] The server sends the generated audio data to the terminal. The terminal notifies the user (robot) of the transmitted audio data. In this case, the input is the audio data from the server, and the output is the audio notification to the user.

[1276] Step 7:

[1277] The robot continues its task based on the voice instructions it receives. For example, it might execute the instruction, "Set part A and secure it with screws." In this case, the input is the voice instruction, and the output is the corresponding action.

[1278] Step 8:

[1279] The terminal continuously collects the robot's behavior history and question content and sends it to the server. The input here is the robot's behavior history and question content, and the output is the data sent to the server.

[1280] Step 9:

[1281] The server analyzes the collected data and evaluates the robot's operational efficiency. The input here is the collected data, and the output is the evaluation result.

[1282] Step 10:

[1283] The server generates feedback based on the evaluation results and notifies the robot via the terminal. For example, it might generate feedback such as, "Work progress is 70%. Next, install part B." Here, the input is the evaluation result, and the output is the feedback data.

[1284] Step 11:

[1285] The robot improves its operations based on the feedback provided. Here, the input is the feedback data, and the output is the improved operation.

[1286] 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.

[1287] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[1288] Specifically, the system operates using the following steps.

[1289] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the converted text information to the server. The server verifies the received username and password and sends the authentication result to the device. The device notifies the user of the authentication result by voice.

[1290] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user works in customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[1291] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[1292] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[1293] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[1294] This system allows users to receive real-time guidance and emotionally responsive support while performing their tasks, significantly improving the effectiveness of training and increasing work efficiency.

[1295] The following describes the processing flow.

[1296] Step 1: User login operation

[1297] The user puts on a smart device and gives voice commands such as, "Log in, Username: User123, Password:".

[1298] The device records the audio and converts it into text data using speech recognition software.

[1299] The device sends the text information converted from the speech to the server.

[1300] Step 2: Authentication Process

[1301] The server compares the received username and password with the database to perform authentication.

[1302] The server generates an authentication success or failure result and sends it to the terminal.

[1303] The device receives the authentication result from the server and notifies the user via voice.

[1304] Step 3: Generate and notify the lecture plan

[1305] The server retrieves the job description of the new member user from the database.

[1306] The server generates a lecture plan tailored to the specific tasks.

[1307] The server sends the generated lecture plan to the terminal.

[1308] The terminal receives the lecture plan and notifies the user via voice message, "Starting customer service duties. First, you will learn how to take orders."

[1309] Step 4: Work progress and instructions

[1310] The device monitors the user's location and movements using sensors.

[1311] The terminal generates necessary instructions related to the user's work in real time and notifies the user via voice.

[1312] Step 5: Handling the Question

[1313] A user may have a question during work and ask it by voice, "What side dish is served with this dish?"

[1314] The device records the audio and converts it into text data using speech recognition software.

[1315] The terminal sends the converted question text to the server.

[1316] Step 6: Emotional Analysis

[1317] The server analyzes the question content and uses an emotion recognition engine to analyze the user's emotional state.

[1318] For example, if the server detects that the user is nervous, it will soften the tone of its response.

[1319] Step 7: Generating the answer

[1320] Based on the analysis results, the server generates a response such as, "This dish comes with french fries as a side dish. We can confidently recommend it."

[1321] The server sends the generated response to the terminal.

[1322] Step 8: Notification of response

[1323] The device notifies the user of the generated response via voice.

[1324] Step 9: Collecting activity history

[1325] The terminal sends the user's activity history (instructions received, questions asked, and progress of tasks) to the server.

[1326] The server saves the activity history to a database.

[1327] Step 10: Provide evaluation and feedback

[1328] The server generates a user evaluation report based on the behavioral history it has collected.

[1329] The server sends the evaluation results to the terminal.

[1330] The device notifies the user of the evaluation results via voice. For example, it might say, "Your current work progress is 80%. Next, you will learn how to describe the dessert menu."

[1331] If the server determines, based on analysis by its emotion recognition engine, that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[1332] The device notifies the user of that feedback via voice.

[1333] This detailed processing flow allows users to receive real-time guidance and emotionally responsive support while performing their tasks, improving training efficiency and enhancing the quality of work.

[1334] (Example 2)

[1335] 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".

[1336] Current business training support systems struggle to effectively utilize user voice input for training, particularly lacking real-time feedback, instructions, and appropriate support tailored to the user's emotional state. As a result, improvements in training effectiveness and operational efficiency may not be fully achieved.

[1337] 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.

[1338] In this invention, the server includes means for receiving voice input from a user, means for converting the received voice input into text data, means for transmitting the converted text data to the server for authentication, means for sending the authentication result to a terminal and notifying the user, means for generating text according to the content of the work, means for converting the generated text into voice data and notifying the user, means for converting the user's question voice into text data, means for transmitting the converted text data to the server and recognizing the user's emotions, means for generating an answer based on the emotion recognition result, means for converting the generated answer from text into voice and notifying the user, means for collecting and evaluating the user's behavior history and question content, and means for generating feedback based on the evaluation and notifying the user. This enables the user to perform their work while receiving appropriate support in real time.

[1339] "Means of accepting voice input" refers to a function that captures the voice spoken by the user.

[1340] "Means of converting to text data" refers to a function that converts audio data into text information.

[1341] "Method of sending to a server for authentication" refers to a function that sends the converted text data to a server via the network to authenticate the user.

[1342] "A means of sending authentication results to the terminal and notifying the user" refers to a function that sends the authentication results from the server to the terminal and informs the user of those results.

[1343] "Means for generating text tailored to the work content" refers to a function that creates text containing necessary information and instructions based on the user's work content.

[1344] "A means of converting generated text into audio data and notifying the user" refers to a function that converts the created text into an audio format and informs the user via voice.

[1345] "Means for converting question audio into text data" refers to a function that converts the audio of a question uttered by a user into text information.

[1346] "Means of recognizing user emotions" refers to a function that analyzes user text data to identify the user's emotional state.

[1347] "Means for generating responses based on emotion recognition results" refers to a function that creates appropriate responses by taking into account the user's emotional state.

[1348] "A means of converting generated responses from text to audio and notifying the user" refers to a function that converts the text of the generated response into an audio format and informs the user of it audibly.

[1349] "Means for collecting and evaluating behavioral history and question content" refers to a function that records user behavior and question content, and analyzes and evaluates that data.

[1350] "A means of generating feedback and notifying users" refers to a function that creates feedback based on evaluation results and informs users of it.

[1351] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects the user's behavior history and question content, and provides feedback based on the evaluation results.

[1352] Hardware and software configuration

[1353] Hardware:

[1354] Smart devices: These are devices that accept voice input, such as smartphones and tablets.

[1355] Server: A device that performs authentication, data analysis, response generation, and evaluation.

[1356] software:

[1357] Speech recognition software: Uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[1358] Text-to-speech software: Use Amazon Polly or Google Cloud Text-to-Speech to convert text data into speech data.

[1359] Emotion recognition engine: Uses IBM Watson Tone Analyzer to analyze the user's emotional state from text data.

[1360] System operation

[1361] Voice input acceptance and authentication:

[1362] The user puts on a smart device and says "Login, Username: User123, Password: ". The device records the voice and converts it into text data using speech recognition software. The device sends this text data to a server, which performs authentication. Once the authentication result is obtained, the result is sent to the device and notified to the user using speech synthesis software. For example, it might notify the user, "Login successful."

[1363] Generating a business lecture plan:

[1364] After authentication is complete, the server retrieves the user's job description from the database and generates a corresponding lecture plan. For example, if a user starts customer service, the server generates a "Basic Waiter Job Lecture Plan." This plan is sent to the terminal and notified to the user using speech synthesis software. For example, it might notify the user, "Starting customer service. First, you will learn how to take orders."

[1365] Handling questions and answers:

[1366] If a user has a question during work, for example, "What is the side dish for this dish?", they can ask it aloud. The terminal records this question and converts it into text data using speech recognition software. This text data is sent to a server, where the server analyzes the user's emotional state using an emotion recognition engine. For example, if the server analyzes that the user is nervous, it will generate a response in a softer tone. It will generate a response such as, "The side dish for this dish is french fries. I can recommend it with confidence," and convert this back into audio data to notify the user.

[1367] Collecting behavioral history and providing feedback:

[1368] The terminal periodically sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server evaluates the collected data and generates feedback. For example, it might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself," and then convert this into audio data to notify the user.

[1369] Examples of specific actions and prompt statements.

[1370] Example of operation:

[1371] If a user asks, "What should I do? I can't take this order properly," the terminal records the question and sends it to the server. The server uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone, such as, "First, let's check the menu. Please proceed without rushing." When this is communicated to the user as an audio message, they can continue their work with peace of mind.

[1372] Example of a prompt:

[1373] Question: "What should I do? I can't seem to get this order."

[1374] User's emotional state: Tension

[1375] Response tone: Gentle

[1376] Answer: "First, let's check the menu. Take your time and don't rush."

[1377] This system allows users to receive appropriate support in real time while performing their tasks. This is expected to significantly improve the effectiveness of training and increase work efficiency.

[1378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1379] Step 1:

[1380] Users log in to their smart devices using voice commands.

[1381] Input: Voice input "Login, Username: User123, Password:"

[1382] Operation: The device's built-in microphone records the audio.

[1383] Output: Audio data

[1384] Step 2:

[1385] The device collects voice data and converts it into text data using speech recognition software.

[1386] Input: Audio data

[1387] Operation: The device uses the Google Cloud Speech-to-Text API to convert speech data into text data.

[1388] Output: Text data "Login, Username: User123, Password: "

[1389] Step 3:

[1390] The terminal sends the converted text data to the server for authentication.

[1391] Input: Text data "Login, Username: User123, Password: "

[1392] Operation: The terminal sends text data to the server as an HTTP request. The server performs authentication by matching it with the database.

[1393] Output: Authentication result (success or failure)

[1394] Step 4:

[1395] The server sends the authentication result to the terminal, and the terminal notifies the user of it.

[1396] Input: Authentication result (success or failure)

[1397] Operation: The server returns the authentication result to the terminal in JSON format. The terminal converts this into a voice message using speech synthesis software (such as Amazon Polly) and notifies the user. Specifically, it notifies the user of either "Login successful" or "Login failed."

[1398] Output: Voice notification

[1399] Step 5:

[1400] The server generates a lecture plan based on the work content and sends it to the terminal.

[1401] Input: User's business information (obtained from database)

[1402] Operation: The server retrieves the user's job description and generates a corresponding lecture plan. As an example, it generates a "Basic Lecture Plan for Waiter Duties."

[1403] Output: Lecture plan

[1404] Step 6:

[1405] The device receives the lecture plan and notifies the user via voice.

[1406] Input: Lecture plan

[1407] Operation: The terminal analyzes the lecture plan and generates a voice message using speech synthesis software. Specifically, it notifies the user with "Starting customer service duties. First, we will learn how to take orders."

[1408] Output: Voice notification

[1409] Step 7:

[1410] During work, the user asks a question, and the terminal converts the question from voice data into text data and sends it to the server.

[1411] Input: Voice input "What side dishes are served with this dish?"

[1412] Operation: The device records the question and converts it into text data using the Google Cloud Speech-to-Text API. The converted text data is then sent to the server as an HTTP request.

[1413] Output: Text data "What side dishes are served with this dish?"

[1414] Step 8:

[1415] The server analyzes the question and the user's emotional state, generates an appropriate answer, and sends it to the terminal.

[1416] Input: Text data "What side dishes are served with this dish?"

[1417] Operation: The server analyzes the question and uses IBM Watson Tone Analyzer to analyze the emotional state. Based on the analysis results, it generates a response in a soft tone. Specifically, it might generate something like, "This dish comes with french fries as a side dish. I can confidently recommend it."

[1418] Output: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[1419] Step 9:

[1420] The device notifies the user of the generated response via voice.

[1421] Input: Generated answer: "This dish comes with french fries as a side dish. I can confidently recommend it."

[1422] Operation: The terminal converts the received response into a voice message using speech synthesis software and notifies the user.

[1423] Output: Voice notification

[1424] Step 10:

[1425] The device sends the user's activity history to the server, and the server generates evaluations and feedback and sends them back to the device.

[1426] Input: User activity history (instructions received, questions asked, progress of tasks)

[1427] Operation: The device periodically sends its activity history to the server. The server evaluates this and generates feedback. Example: It might generate feedback such as, "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[1428] Output: Evaluation results and feedback

[1429] Step 11:

[1430] The device notifies the user of the evaluation results and feedback via voice.

[1431] Input: Evaluation results and feedback "Are you feeling a little tired from your recent work? Take a break and refresh yourself."

[1432] Operation: The terminal converts the received evaluation results and feedback into a voice message using speech synthesis software and notifies the user.

[1433] Output: Voice notification

[1434] (Application Example 2)

[1435] 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".

[1436] Traditionally, training new employees has typically involved using text-based manuals and videos. However, these methods struggle to address individual user emotional states and stress levels, making effective training difficult. Furthermore, they are ineffective at providing real-time support and feedback, highlighting the need for improved training efficiency and quality. In addition, providing appropriate support for employees experiencing tension and anxiety in real-world settings such as physical stores is crucial. To address these challenges, a system is needed that analyzes user emotional states and provides responses and instructions in an appropriate tone.

[1437] 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.

[1438] In this invention, the server includes means for analyzing the user's emotions from voice input and text data, means for generating responses and instructions in an appropriate tone based on the emotion analysis results, means for allowing the user to input login information by voice using a smart device, and means for providing real-time instructions in an appropriate tone according to the user's emotional state. This makes it possible to provide new members with job training that is appropriately customized in real time according to the user's emotional state, including guidance and support.

[1439] "Voice input" refers to voice information spoken by the user.

[1440] "Text data" refers to data obtained by converting audio information into written text.

[1441] "Emotional analysis" is the process of analyzing a user's emotional state from audio and text data.

[1442] "Answer generation" refers to the process by which a system produces appropriate answers to user questions and requests.

[1443] "Instruction generation" refers to the system generating instructions related to the user's work in real time.

[1444] "Activity history" refers to a record of actions taken by a user while using the system.

[1445] "Feedback" refers to a system evaluating a user's behavior and emotional state and notifying the user of the results.

[1446] A "smart device" refers to a device that has functions such as voice input and display, and smart glasses are an example.

[1447] "Login information" refers to authentication data necessary for a user to access the system.

[1448] "Tone" refers to the pitch or atmosphere of a voice, and it is adjusted according to the emotion being conveyed.

[1449] "Real-time instructions" are instructions that are provided instantly to the user while they are performing a task.

[1450] As an embodiment of this invention, a business training support system incorporating an emotion engine is described below. This system receives voice input from the user, converts it into text data, and analyzes the user's emotions from the text data and voice. Based on the analysis results, it generates answers and instructions and notifies the user. It also collects and evaluates the user's behavior history and question content, and provides feedback based on the evaluation results.

[1451] Specifically, the system operates in the following steps:

[1452] First, the user puts on a smart device and performs a voice login operation. For example, if the user says "Login, Username: User123, Password:", the device records the voice and converts it into text data using speech recognition software. The device sends the text information converted from the voice to the server. The server verifies the received username and password and sends the authentication result to the device. The device then notifies the user of the authentication result by voice.

[1453] Next, the server retrieves the new user's job description from the database and generates a lecture plan tailored to that job. For example, if the user's job is customer service, the server generates a "Basic Waiter Job Lecture Plan" and sends it to the terminal. The terminal receives the lecture plan and notifies the user via voice, "Starting customer service. First, you will learn how to take orders."

[1454] As users work, if they encounter any questions in specific situations, they can ask them by voice. For example, if a user asks, "What are the side dishes for this dish?", the device converts the voice into text and sends it to the server. The server analyzes the question and uses an emotion recognition engine to analyze the user's emotional state. For example, if the server determines that the user is nervous, it will soften the tone of the response and generate something like, "The side dish for this dish is french fries. I can recommend it with confidence." The device then notifies the user of the generated response by voice.

[1455] Furthermore, the terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs an evaluation. Based on the evaluation results, the server generates feedback and sends it to the terminal. For example, if the server determines that the user's stress level is high, it will provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[1456] The hardware used includes smart devices (e.g., smart glasses), and the software includes a speech recognition library (speech_recognition), a speech synthesis library (pyttsx3), and an emotion recognition engine (a hypothetical emotion_recognition library).

[1457] As a concrete example, if a user feels nervous when a customer places a complex order while performing customer service duties, the user might ask, "What should I do? I can't take this order properly." The terminal sends this question to the server, which uses an emotion recognition engine to analyze the user's state of tension and generates a response in a gentle tone: "First, let's check the menu. Take your time." The terminal then notifies the user of this response verbally, allowing the user to continue their work with peace of mind.

[1458] An example of a prompt for a generative AI model is: "When a user asks, 'What comes with this dish?', sentiment analysis will be performed based on the user's voice data. For example, if it is determined that the user is nervous, please generate a response in a gentle tone such as, 'This dish comes with a salad. Please tell us without hesitation.'"

[1459] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1460] Step 1:

[1461] The user wears a smart device and performs a voice login operation. When the user says "Login, Username: User123, Password:", the device records the voice. The recorded voice data is converted into text data by speech recognition software. This converted text data is sent to the server. The server compares the received username and password with the database and sends the authentication result (success or failure) to the device. The device notifies the user of the authentication result by voice.

[1462] Input: User's voice data

[1463] Output: Text data, authentication result

[1464] Step 2:

[1465] The server retrieves the job description of the new member user from the database. It generates a lecture plan tailored to the job description and sends it to the terminal. The terminal then notifies the user via voice based on the received lecture plan. The notification might say something like, "We will now begin the basic customer service lecture plan. First, we will learn how to take orders."

[1466] Input: User's job description

[1467] Output: Lecture plan

[1468] Step 3:

[1469] When a user encounters a question during their work, they can ask it by voice. For example, they might say, "What are the side dishes for this dish?" The terminal converts the voice into text and sends it to the server. The server analyzes the question and further analyzes the user's emotional state from the voice data using an emotion recognition engine. Based on the analysis results, the server adjusts the tone of the response, generates an appropriate answer, and sends it to the terminal. The terminal then notifies the user of the generated answer by voice.

[1470] Input: User's question audio data

[1471] Output: Appropriate answer

[1472] Step 4:

[1473] The terminal sends the user's activity history (instructions received, questions asked, and work progress) to the server. The server stores the collected data in a database and performs analysis and evaluation. Based on the evaluation results, it generates feedback and sends it to the terminal. For example, it might provide feedback such as, "Are you feeling a little tired from your recent work? Let's take a break and refresh yourself." The terminal notifies the user of the evaluation results and feedback via voice.

[1474] Input: Behavioral history data

[1475] Output: Feedback

[1476] Step 5:

[1477] If necessary, the user will continue to ask questions or receive new instructions. The device repeatedly records and recognizes voices in response to these situations, sends data to the server, the server processes and generates feedback, and the device sends voice notifications.

[1478] Input: Next question or instruction voice data

[1479] Output: The following appropriate answers and instructions

[1480] 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.

[1481] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1482] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1483] 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.

[1484] 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.

[1485] 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.

[1486] 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.

[1487] 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.

[1488] 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."

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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.

[1496] 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.

[1497] 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.

[1498] 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.

[1499] 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.

[1500] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1501] The following is further disclosed regarding the embodiments described above.

[1502] (Claim 1)

[1503] This is a system to support job training for new members.

[1504] A means of receiving user voice input,

[1505] A means of converting received voice input into text data,

[1506] A means for analyzing text data and generating corresponding answers,

[1507] A means of notifying the user of the generated response,

[1508] A means of generating and notifying users of work-related instructions in real time,

[1509] A means of collecting and evaluating user behavior history and question content,

[1510] A system including means for generating feedback based on the aforementioned evaluation and notifying the user.

[1511] (Claim 2)

[1512] The system according to claim 1, comprising means for notifying a user of instructions in real time using a smart device.

[1513] (Claim 3)

[1514] The system according to claim 1, comprising means for generating a lecture plan tailored to the content of work and recommending it to the user.

[1515]

[1516] "Example 1"

[1517] (Claim 1)

[1518] A means of receiving user voice input,

[1519] A means of converting received voice input into text data,

[1520] A means for analyzing text data and generating corresponding answers,

[1521] A means of notifying the user of the generated response,

[1522] A means of generating and notifying users of work-related instructions in real time,

[1523] A means of collecting and evaluating user behavior history and question content,

[1524] A means by which the server retrieves the user's work details from the database and generates a lecture plan according to those details,

[1525] A method for sending a lecture plan to a device and having the device notify the user via voice,

[1526] A means of acquiring user questions as voice input, converting them to text, and sending them to the server,

[1527] A means by which the server analyzes the question content, generates a corresponding answer, and sends it to the terminal,

[1528] A means for generating feedback based on the aforementioned evaluation and notifying the user,

[1529] A system including means for inputting prompt statements to a generated AI model in order to operate each of the aforementioned means.

[1530] (Claim 2)

[1531] The system according to claim 1, comprising means for notifying a user of instructions in real time using a smart device.

[1532] (Claim 3)

[1533] The system according to claim 1, comprising means for generating a lecture plan tailored to the content of work and recommending it to the user.

[1534] "Application Example 1"

[1535] (Claim 1)

[1536] This is a system to support job training for new members.

[1537] A means of receiving user voice input,

[1538] A means of converting received voice input into text data,

[1539] A means for analyzing text data and generating corresponding answers,

[1540] A means of notifying the user of the generated response,

[1541] A means of generating and notifying users of work-related instructions in real time,

[1542] A means of collecting and evaluating user behavior history and question content,

[1543] A means for generating feedback based on the aforementioned evaluation and notifying the user,

[1544] A means by which robots can ask questions and receive instructions by voice when performing tasks,

[1545] A means of notifying the robot of the generated response by voice,

[1546] A means for analyzing the robot's operation history and question content to generate feedback,

[1547] A system including means for providing guidance to improve the operational efficiency of a robot based on the aforementioned feedback.

[1548] (Claim 2)

[1549] The system according to claim 1, further comprising means for notifying a robot of instructions in real time using a smart device.

[1550] (Claim 3)

[1551] The system according to claim 1, comprising means for generating a lecture plan according to the content of the work and recommending it to the robot.

[1552] "Example 2 of combining an emotion engine"

[1553] (Claim 1)

[1554] A means of receiving user voice input,

[1555] A means of converting received voice input into text data,

[1556] A means of sending the converted text data to a server for authentication,

[1557] A means of sending the authentication result to the device and notifying the user,

[1558] A means of generating text according to the content of the work,

[1559] A means of converting the generated text into audio data and notifying the user,

[1560] A means of converting the user's question audio into text data,

[1561] The converted text data is sent to a server, and a means of recognizing the user's emotions is provided.

[1562] A means for generating a response based on the emotion recognition result,

[1563] A means of converting the generated response from text to speech and notifying the user,

[1564] A means of collecting and evaluating user behavior history and question content,

[1565] A system including means for generating feedback based on the aforementioned evaluation and notifying the user.

[1566] (Claim 2)

[1567] The system according to claim 1, comprising means for analyzing the user's emotional state and generating a response.

[1568] (Claim 3)

[1569] The system according to claim 1, comprising means for generating a lecture plan tailored to the content of work and recommending it to the user.

[1570] "Application example 2 when combining with an emotional engine"

[1571] (Claim 1)

[1572] This is a system to support job training for new members.

[1573] A means of receiving user voice input,

[1574] A means of converting received voice input into text data,

[1575] A means for analyzing text data and generating corresponding answers,

[1576] A means of notifying the user of the generated response,

[1577] A means of generating and notifying users of work-related instructions in real time,

[1578] A means of collecting and evaluating user behavior history and question content,

[1579] A means for generating feedback based on the aforementioned evaluation and notifying the user,

[1580] A means of analyzing user emotions from voice input and text data,

[1581] A means of generating responses and instructions in an appropriate tone based on the results of emotion analysis,

[1582] A method for allowing users to input login information by voice using a smart device,

[1583] A means of providing real-time instructions in an appropriate tone according to the user's emotional state.

[1584] A system that includes this.

[1585] (Claim 2)

[1586] The system according to claim 1, comprising means for notifying the user of instructions in real time using smart glasses.

[1587] (Claim 3)

[1588] The system according to claim 1, comprising means for generating a lecture plan according to the content of the work and recommending it to the user in an appropriate tone based on emotion recognition. [Explanation of Symbols]

[1589] 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. This is a system to support job training for new members. A means of receiving user voice input, A means of converting received voice input into text data, A means for analyzing text data and generating corresponding answers, A means of notifying the user of the generated response, A means of generating and notifying users of work-related instructions in real time, A means of collecting and evaluating user behavior history and question content, A system including means for generating feedback based on the aforementioned evaluation and notifying the user.

2. The system according to claim 1, further comprising means for notifying a user of instructions in real time using a smart device.

3. The system according to claim 1, comprising means for generating a lecture plan tailored to the content of the work and recommending it to the user.

Images