System

Abstract

An object of a system according to an embodiment is to quickly and accurately respond to a question from an employee.SOLUTION: A system includes a question understanding unit, an answer generation unit, and a knowledge database. The question understanding unit understands a question from an employee. The answer generation unit generates an answer based on the question understood by the question understanding unit. The knowledge database provides the answer generated by the answer generator.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have had the problem of making it difficult to respond to questions from employees quickly and accurately.

[0005] The system according to the embodiment aims to respond quickly and accurately to questions from employees. [Means for solving the problem]

[0006] The system according to the embodiment includes a question understanding unit, an answer generation unit, and a knowledge database. The question understanding unit understands questions from employees. The answer generation unit generates answers based on the questions understood by the question understanding unit. The knowledge database provides the answers generated by the answer generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly and accurately respond to questions from employees. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices 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), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A responsive application assistant according to an embodiment of the present invention is a system that utilizes generative AI to support the personnel application process. This system responds quickly and accurately to questions or doubts that employees may have when submitting various types of applications. As a result, the responsive application assistant can quickly and accurately respond to employees' questions and doubts, allowing the application process to proceed smoothly.

[0029] A responsive application assistant according to an embodiment includes a question understanding unit, an answer generation unit, and a knowledge database. The question understanding unit understands questions from employees. For example, the question understanding unit analyzes the employee's question using natural language processing technology to understand its intent. The question understanding unit can also identify important parts of the question using keyword extraction technology. For example, if an employee asks, "Please tell me the procedure for applying for vacation," the question understanding unit analyzes the question and extracts information about the vacation application. The answer generation unit generates an answer based on the question understood by the question understanding unit. For example, the answer generation unit uses a rule-based generation method to generate an appropriate answer to the question. The answer generation unit can also use a machine learning model to generate a more advanced answer to the question. For example, if an employee asks, "Please tell me how to apply for paid vacation," the answer generation unit uses the rule-based generation method to explain the specific application procedure. The knowledge database provides the answer generated by the answer generation unit. For example, the knowledge database stores information about a company's human resources policies and procedures and provides accurate answers to questions. The knowledge database is also dynamically updated to always provide the latest information. For example, the knowledge database is automatically updated when a company's personnel policies change, providing answers based on the latest information. This allows the responsive request assistant according to the embodiment to provide quick and accurate answers to employees' questions. For example, if an employee has questions about a vacation request, the responsive request assistant can clarify the question and explain the necessary steps and how to submit documents. This allows the employee to smoothly proceed through the request process.

[0030] The question understanding unit allows the generation AI to provide additional relevant information beyond the context of the question, explaining the background of the question and related procedures. For example, if an employee asks, "Please tell me the procedure for applying for vacation," the generation AI will provide not only the procedure for applying for vacation, but also related information such as the type of vacation, application deadline, and required documents. The question understanding unit also allows the generation AI to explain the background of the question and related procedures. For example, if an employee asks, "Please tell me how to apply for paid vacation," the generation AI will provide not only the procedure for applying for paid vacation, but also background information such as the conditions for taking paid vacation and the application process. This allows the system to provide additional relevant information in response to the employee's question and explain the background of the question and related procedures, thereby deepening the employee's understanding.

[0031] The question understanding unit allows the generation AI to analyze an employee's past question history and behavioral patterns to more deeply understand the intent of the question and generate a personalized answer. For example, if an employee asks, "What is the procedure for applying for vacation?", the generation AI will refer to the employee's past question history and provide a personalized answer, taking into account the employee's previous vacation requests. The question understanding unit can also allow the generation AI to analyze an employee's behavioral patterns and generate answers tailored to the employee's needs. For example, if an employee frequently travels for business, the generation AI will take those behavioral patterns into account and provide information related to business trips. This allows for a deeper understanding of the intent of the employee's question and the provision of personalized answers, thereby improving employee satisfaction.

[0032] The question understanding department can improve the convenience for employees by diversifying the question input methods and supporting voice input and handwriting input. For example, when an employee asks "Please teach me the procedure for applying for leave" by voice input, the generative AI analyzes the voice and generates an appropriate answer. Also, the question understanding department supports handwriting input. Even when an employee inputs a question in handwriting, the generative AI can analyze the content and provide an answer. For example, when an employee handwrites "Please teach me the method of applying for paid leave" on a tablet, the generative AI analyzes the handwritten characters and generates an appropriate answer. By diversifying the question input methods and supporting voice input and handwriting input, the convenience for employees can be improved.

[0033] The question understanding department can also handle questions in different languages, enabling its use in a global corporate environment. For example, when an employee asks "How do I apply for leave?" in English, the generative AI analyzes the English and generates an appropriate answer. Also, the question understanding department supports other languages. Even when an employee asks a question in Chinese, Spanish, etc., the generative AI can analyze the language and provide an answer. For example, when an employee asks "Please tell me how to apply for leave" in Chinese, the generative AI analyzes the question and generates an appropriate answer. By handling questions in different languages, its use in a global corporate environment can be enabled.

[0034] The knowledge database is updated dynamically and can always provide answers based on the latest policies and procedures. For example, when the company's personnel policy is changed, the generative AI automatically updates the knowledge database and provides answers based on the latest information. Also, the knowledge database can update data regularly and always maintain the latest information. For example, the knowledge database reflects monthly policy changes and provides answers based on the latest procedures. Thus, the knowledge database can be updated dynamically and always provide answers based on the latest policies and procedures.

[0035] Knowledge databases can provide more comprehensive information, including laws, regulations, and industry standards. For example, generative AI can add legal and regulatory information to a knowledge database, and when an employee asks, "What is the procedure for requesting vacation?", the knowledge database can also explain the relevant laws and regulations. Knowledge databases can also provide information based on industry standards. For example, knowledge databases store information based on industry standards such as ISO standards and GDPR, and provide comprehensive answers to employee questions. This allows knowledge databases to provide more comprehensive information, including relevant laws, regulations, and industry standards.

[0036] Knowledge databases can be visualized and provide information in a graphical interface. For example, a generative AI can visualize a knowledge database, and when an employee asks, "What is the procedure for requesting vacation?", the AI ​​can explain the procedure in a graphical interface. Knowledge databases can also provide information visually using graphs and charts. For example, a knowledge database can display the procedure for requesting vacation in a flowchart, making it easier for employees to understand the procedure. This makes it possible to visualize a knowledge database and provide information in a graphical interface.

[0037] Generative AI can simultaneously provide relevant FAQs and guidelines in response to employee questions, promoting self-resolution. For example, when an employee asks, "What is the procedure for requesting vacation?", generative AI can provide relevant FAQs and guidelines in addition to the vacation request procedure. Generative AI can also provide self-help tools and online resources to help employees resolve their own issues. For example, when an employee asks, "How do I request paid vacation?", generative AI can provide a list of frequently asked questions and an operation manual in addition to the specific procedure. This allows generative AI to simultaneously provide relevant FAQs and guidelines in response to employee questions, promoting self-resolution.

[0038] In response to employee questions, the generation AI can refer to similar past cases and provide answers based on specific examples. For example, when an employee asks, "Please tell me the procedure for applying for vacation," the generation AI can refer to similar past cases and provide an answer based on specific examples. The generation AI can also analyze questions and answers previously asked by employees and provide answers based on similar cases. For example, when an employee asks, "Please tell me how to apply for paid vacation," the generation AI can refer to past success stories and failure stories and provide an answer based on specific examples. This makes it possible to refer to similar past cases and provide an answer based on specific examples in response to employee questions.

[0039] User support can diversify channels and provide support in multiple ways, such as through chatbots, email, and telephone. For example, if an employee asks a question through a chatbot, such as "How do I apply for vacation?", the generation AI provides an answer through the chatbot. User support can also provide support through email and telephone. For example, if an employee sends a question by email, the generation AI replies with an appropriate answer via email. User support can also respond to employee questions via telephone. For example, if an employee calls and asks, "How do I apply for paid vacation?", the generation AI provides an appropriate answer to the question. This allows user support channels to diversify and provide support in multiple ways, such as through chatbots, email, and telephone.

[0040] User support can automatically log the content so that it can be referenced later. For example, when an employee asks, "How do I apply for vacation?", the generation AI automatically logs the interaction so that it can be referenced later. User support can also log questions that employees have previously asked and their answers, so that it can be referenced as needed. For example, when an employee asks, "How do I apply for paid vacation?", the generation AI logs the interaction so that it can be referenced later if another employee asks the same question. This allows the content of user support to be automatically logged so that it can be referenced later.

[0041] Generative AI can analyze past question and answer data, extract trends and patterns, and provide more accurate answers. For example, generative AI can analyze past question and answer data to extract trends and patterns related to vacation requests, and provide more accurate answers. Generative AI can also use data mining and time series analysis to improve the quality of answers to employee questions. For example, generative AI can analyze past question data to identify topics and patterns frequently asked by employees and provide answers based on those. This allows generative AI to analyze past question and answer data to extract trends and patterns and provide more accurate answers.

[0042] Generative AI can collect employee feedback and continuously improve the quality of responses based on that feedback. For example, generative AI can collect employee feedback and continuously improve the quality of responses regarding vacation requests. Generative AI can also utilize surveys and user reviews to improve the quality of responses based on feedback. For example, generative AI can collect employee feedback about how they felt about the responses and improve the quality of responses based on the results. This allows generative AI to collect employee feedback and continuously improve the quality of responses based on that feedback.

[0043] The learning function can automatically generate training programs to help employees improve their skills and knowledge. For example, the generation AI uses the learning function to automatically generate a training program to help employees improve their skills and knowledge regarding vacation requests. The learning function can also analyze an employee's past learning history and skill level to provide an individualized training program. For example, the learning function automatically generates a new training program based on training programs that the employee has previously taken. In this way, the learning function can be used to automatically generate training programs to help employees improve their skills and knowledge.

[0044] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0045] The question understanding unit can also provide relevant video tutorials and interactive guides in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generation AI can provide a video tutorial explaining the procedure for requesting vacation. The question understanding unit can also use interactive guides to help employees go through the procedure step by step. For example, if an employee asks, "How do I request paid vacation?", the generation AI can provide an interactive guide, allowing employees to receive real-time support as they go through the procedure. This allows the system to deepen employees' understanding by providing relevant video tutorials and interactive guides in response to their questions.

[0046] The question understanding unit can also provide relevant legal advice and compliance information in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generation AI can provide legal requirements and compliance information related to vacation requests. The question understanding unit can also provide relevant legal advice when an employee asks about a specific legal issue. For example, if an employee asks, "What should I do if my paid vacation request is denied?", the generation AI can provide legal advice tailored to the situation. This allows the system to deepen employees' understanding by providing them with relevant legal advice and compliance information in response to their questions.

[0047] The question understanding unit can also provide relevant industry best practices and success stories in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generation AI will provide industry best practices and success stories. The question understanding unit can also provide relevant success stories when an employee asks about a specific business process. For example, if an employee asks, "How do I request paid vacation?", the generation AI can provide success stories from other companies so that the employee can refer to those procedures. This allows employees to deepen their understanding by providing relevant industry best practices and success stories in response to their questions.

[0048] The knowledge database can also provide relevant external resources and links in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generative AI will provide links to official external websites and related online resources. The knowledge database can also provide relevant external resources when an employee asks a question about a specific topic. For example, if an employee asks, "How do I request paid vacation?", the generative AI will provide links to relevant legal information and guidelines. This allows the system to provide relevant external resources and links in response to employee questions, thereby deepening employees' understanding.

[0049] The knowledge database can also provide relevant statistical data and analytical results in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generative AI will provide statistical data and analytical results related to vacation requests. The knowledge database can also provide relevant statistical data and analytical results when an employee asks a question about a specific topic. For example, if an employee asks, "How do I request paid vacation?", the generative AI will provide statistical data on the usage of paid vacation and the success rate of requests. This allows employees to deepen their understanding by providing relevant statistical data and analytical results in response to their questions.

[0050] The knowledge database can also provide relevant case studies and examples in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generative AI will provide case studies and examples related to vacation requests. The knowledge database can also provide relevant case studies and examples when an employee asks a question about a specific topic. For example, if an employee asks, "How do I request paid vacation?", the generative AI will provide success stories and failure stories from other employees. This allows employees to deepen their understanding by providing relevant case studies and examples in response to their questions.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The question understanding unit understands the question from the employee. For example, the question understanding unit uses natural language processing technology to analyze the employee's question and understand its intent. The question understanding unit can also identify important parts of the question using keyword extraction technology. For example, if an employee asks, "Please tell me the procedure for applying for vacation," the question is analyzed and information about vacation applications is extracted. Step 2: The answer generation unit generates an answer based on the question understood by the question understanding unit. For example, the answer generation unit uses a rule-based generation method to generate an appropriate answer to the question. The answer generation unit can also use a machine learning model to generate a more advanced answer to the question. For example, if an employee asks, "How do I apply for paid leave?", the answer generation unit uses a rule-based generation method to explain the specific application procedure. Step 3: The knowledge database provides the answer generated by the answer generator. For example, the knowledge database may contain information about a company's human resources policies and procedures, and provide accurate answers to questions. The knowledge database is also dynamically updated, allowing it to always provide the latest information. For example, the knowledge database is automatically updated when a company's human resources policies change, providing answers based on the latest information.

[0053] (Example 2) A responsive application assistant according to an embodiment of the present invention is a system that utilizes generative AI to support the personnel application process. This system responds quickly and accurately to questions or doubts that employees may have when submitting various types of applications. As a result, the responsive application assistant can quickly and accurately respond to employees' questions and doubts, allowing the application process to proceed smoothly.

[0054] A responsive application assistant according to an embodiment includes a question understanding unit, an answer generation unit, and a knowledge database. The question understanding unit understands questions from employees. For example, the question understanding unit analyzes the employee's question using natural language processing technology to understand its intent. The question understanding unit can also identify important parts of the question using keyword extraction technology. For example, if an employee asks, "Please tell me the procedure for applying for vacation," the question understanding unit analyzes the question and extracts information about the vacation application. The answer generation unit generates an answer based on the question understood by the question understanding unit. For example, the answer generation unit uses a rule-based generation method to generate an appropriate answer to the question. The answer generation unit can also use a machine learning model to generate a more advanced answer to the question. For example, if an employee asks, "Please tell me how to apply for paid vacation," the answer generation unit uses the rule-based generation method to explain the specific application procedure. The knowledge database provides the answer generated by the answer generation unit. For example, the knowledge database stores information about a company's human resources policies and procedures and provides accurate answers to questions. The knowledge database is also dynamically updated to always provide the latest information. For example, the knowledge database is automatically updated when a company's personnel policies change, providing answers based on the latest information. This allows the responsive request assistant according to the embodiment to provide quick and accurate answers to employees' questions. For example, if an employee has questions about a vacation request, the responsive request assistant can clarify the question and explain the necessary steps and how to submit documents. This allows the employee to smoothly proceed through the request process.

[0055] The question understanding unit allows the generation AI to provide additional relevant information beyond the context of the question, explaining the background of the question and related procedures. For example, if an employee asks, "Please tell me the procedure for applying for vacation," the generation AI will provide not only the procedure for applying for vacation, but also related information such as the type of vacation, application deadline, and required documents. The question understanding unit also allows the generation AI to explain the background of the question and related procedures. For example, if an employee asks, "Please tell me how to apply for paid vacation," the generation AI will provide not only the procedure for applying for paid vacation, but also background information such as the conditions for taking paid vacation and the application process. This allows the system to provide additional relevant information in response to the employee's question and explain the background of the question and related procedures, thereby deepening the employee's understanding.

[0056] The question understanding unit allows the generation AI to analyze an employee's past question history and behavioral patterns to more deeply understand the intent of the question and generate a personalized answer. For example, if an employee asks, "What is the procedure for applying for vacation?", the generation AI will refer to the employee's past question history and provide a personalized answer, taking into account the employee's previous vacation requests. The question understanding unit can also allow the generation AI to analyze an employee's behavioral patterns and generate answers tailored to the employee's needs. For example, if an employee frequently travels for business, the generation AI will take those behavioral patterns into account and provide information related to business trips. This allows for a deeper understanding of the intent of the employee's question and the provision of personalized answers, thereby improving employee satisfaction.

[0057] The question understanding unit uses emotion estimation to analyze the emotions expressed when an employee asks a question and generates answers that correspond to those emotions, thereby improving employee satisfaction. For example, when an employee asks, "Please tell me how to apply for vacation," the generation AI analyzes the employee's emotions and, if the employee is feeling stressed, responds in a gentle manner that helps them relax. The question understanding unit can also provide answers that reassure employees if they are feeling anxious. For example, when an employee asks, "What should I do if my paid vacation application is delayed?" the generation AI analyzes the employee's anxiety and gently explains specific ways to deal with the situation. This allows the system to analyze the emotions expressed when an employee asks a question and provide answers that correspond to those emotions, thereby improving employee satisfaction.

[0058] The question understanding unit diversifies question input methods, supporting voice and handwriting input, thereby improving employee convenience. For example, if an employee voice-inputs a question such as "Please tell me how to apply for vacation," the generation AI analyzes the voice and generates an appropriate answer. The question understanding unit also supports handwriting input, so even if an employee inputs a question by hand, the generation AI can analyze the content and provide an answer. For example, if an employee handwrites a question on a tablet, such as "Please tell me how to apply for paid vacation," the generation AI analyzes the handwriting and generates an appropriate answer. This diversifies question input methods, supporting voice and handwriting input, thereby improving employee convenience.

[0059] The question understanding department can handle questions in different languages, enabling it to be used in a global corporate environment. For example, when an employee asks "How do I apply for leave?" in English, the generative AI analyzes the English and generates an appropriate answer. The question understanding department also supports other languages. When an employee asks a question in Chinese, Spanish, etc., the generative AI can analyze the language and provide an answer. For example, when an employee asks "?告?我如何申?休假" in Chinese, the generative AI analyzes the question and generates an appropriate answer. This enables handling questions in different languages and makes it possible to use in a global corporate environment.

[0060] The question understanding department can use an emotion estimation function to analyze the emotion of employees in real time when they input questions and make suggestions to elicit positive emotions. For example, when an employee inputs "Please teach me the procedure for applying for leave", the generative AI analyzes the employee's emotion in real time and displays an encouraging message to elicit positive emotions. Also, when an employee is feeling stressed, the question understanding department can make suggestions for relaxation. For example, when an employee inputs "What should I do if my application for paid leave is delayed?", the generative AI analyzes the employee's emotion and provides advice for relaxation. By analyzing the emotion of employees in real time when they input questions and making suggestions to elicit positive emotions, the satisfaction of employees can be improved.

[0061] The knowledge database is dynamically updated, making it possible to always provide answers based on the latest policies and procedures. For example, when a company's personnel policy changes, the generative AI automatically updates the knowledge database to provide answers based on the latest information. The knowledge database also updates its data regularly, making it possible to always keep the information up to date. For example, the knowledge database reflects monthly policy changes and provides answers based on the latest procedures. This allows the knowledge database to be dynamically updated, making it possible to always provide answers based on the latest policies and procedures.

[0062] Knowledge databases can provide more comprehensive information, including laws, regulations, and industry standards. For example, generative AI can add legal and regulatory information to a knowledge database, and when an employee asks, "What is the procedure for requesting vacation?", the knowledge database can also explain the relevant laws and regulations. Knowledge databases can also provide information based on industry standards. For example, knowledge databases store information based on industry standards such as ISO standards and GDPR, and provide comprehensive answers to employee questions. This allows knowledge databases to provide more comprehensive information, including relevant laws, regulations, and industry standards.

[0063] The knowledge database can use an emotion estimation function to analyze the emotions of employees when they refer to the knowledge database and provide an interface to reduce stress. For example, when an employee refers to the knowledge database, the generation AI analyzes the employee's emotions and provides an interface that helps them relax if they are feeling stressed. The knowledge database can also provide an interface that gives employees a sense of security if they are feeling anxious. For example, when an employee asks, "How do I apply for paid leave?" the generation AI analyzes the employee's emotions and provides an interface that helps them relax. In this way, it is possible to analyze the emotions of employees when they refer to the knowledge database and provide an interface that helps them reduce stress.

[0064] Knowledge databases can be visualized and provide information in a graphical interface. For example, a generative AI can visualize a knowledge database, and when an employee asks, "What is the procedure for requesting vacation?", the AI ​​can explain the procedure in a graphical interface. Knowledge databases can also provide information visually using graphs and charts. For example, a knowledge database can display the procedure for requesting vacation in a flowchart, making it easier for employees to understand the procedure. This makes it possible to visualize a knowledge database and provide information in a graphical interface.

[0065] The knowledge database uses an emotion estimation function to monitor the emotions of employees when they use the knowledge database in real time and make suggestions to elicit positive emotions. For example, when an employee uses the knowledge database, the generative AI monitors the employee's emotions in real time and displays encouraging messages to elicit positive emotions. The knowledge database can also make suggestions to help employees relax if they are feeling stressed. For example, when an employee asks, "How do I apply for paid leave?" the generative AI analyzes the employee's emotions and provides advice to help them relax. This makes it possible to improve employee satisfaction by monitoring the emotions of employees when they use the knowledge database in real time and making suggestions to elicit positive emotions.

[0066] Generative AI can simultaneously provide relevant FAQs and guidelines in response to employee questions, promoting self-resolution. For example, when an employee asks, "What is the procedure for requesting vacation?", generative AI can provide relevant FAQs and guidelines in addition to the vacation request procedure. Generative AI can also provide self-help tools and online resources to help employees resolve their own issues. For example, when an employee asks, "How do I request paid vacation?", generative AI can provide a list of frequently asked questions and an operation manual in addition to the specific procedure. This allows generative AI to simultaneously provide relevant FAQs and guidelines in response to employee questions, promoting self-resolution.

[0067] In response to employee questions, the generation AI can refer to similar past cases and provide answers based on specific examples. For example, when an employee asks, "Please tell me the procedure for applying for vacation," the generation AI can refer to similar past cases and provide an answer based on specific examples. The generation AI can also analyze questions and answers previously asked by employees and provide answers based on similar cases. For example, when an employee asks, "Please tell me how to apply for paid vacation," the generation AI can refer to past success stories and failure stories and provide an answer based on specific examples. This makes it possible to refer to similar past cases and provide an answer based on specific examples in response to employee questions.

[0068] Generative AI uses its emotion estimation function to analyze the emotions of employees when they ask questions and provides support appropriate to their emotions, thereby improving employee satisfaction. For example, when an employee asks, "How do I apply for vacation?", generative AI analyzes the employee's emotions and, if they are feeling stressed, responds in a gentle manner to help them relax. Generative AI can also provide support that gives employees a sense of security if they are feeling anxious. For example, when an employee asks, "What should I do if my paid vacation application is delayed?", generative AI analyzes the employee's anxiety and gently explains specific ways to deal with the situation. This allows for the analysis of employees' emotions when they ask questions and the provision of support appropriate to their emotions, improving employee satisfaction.

[0069] User support can diversify channels and provide support in multiple ways, such as through chatbots, email, and telephone. For example, if an employee asks a question through a chatbot, such as "How do I apply for vacation?", the generation AI provides an answer through the chatbot. User support can also provide support through email and telephone. For example, if an employee sends a question by email, the generation AI replies with an appropriate answer via email. User support can also respond to employee questions via telephone. For example, if an employee calls and asks, "How do I apply for paid vacation?", the generation AI provides an appropriate answer to the question. This allows user support channels to diversify and provide support in multiple ways, such as through chatbots, email, and telephone.

[0070] User support can automatically log the content so that it can be referenced later. For example, when an employee asks, "How do I apply for vacation?", the generation AI automatically logs the interaction so that it can be referenced later. User support can also log questions that employees have previously asked and their answers, so that it can be referenced as needed. For example, when an employee asks, "How do I apply for paid vacation?", the generation AI logs the interaction so that it can be referenced later if another employee asks the same question. This allows the content of user support to be automatically logged so that it can be referenced later.

[0071] The emotion estimation function analyzes the emotions of employees when they receive support in real time and can make suggestions to elicit positive emotions. For example, when an employee asks, "Please tell me how to apply for vacation," the generative AI analyzes the employee's emotions in real time and displays an encouraging message to elicit positive emotions. The emotion estimation function can also make suggestions to help employees relax if they are feeling stressed. For example, when an employee asks, "What should I do if my paid vacation application is late?" the generative AI analyzes the employee's emotions and provides advice to help them relax. This allows the system to analyze the emotions of employees when they receive support in real time and make suggestions to elicit positive emotions, thereby improving employee satisfaction.

[0072] Generative AI can analyze past question and answer data, extract trends and patterns, and provide more accurate answers. For example, generative AI can analyze past question and answer data to extract trends and patterns related to vacation requests, and provide more accurate answers. Generative AI can also use data mining and time series analysis to improve the quality of answers to employee questions. For example, generative AI can analyze past question data to identify topics and patterns frequently asked by employees and provide answers based on those. This allows generative AI to analyze past question and answer data to extract trends and patterns and provide more accurate answers.

[0073] Generative AI can collect employee feedback and continuously improve the quality of responses based on that feedback. For example, generative AI can collect employee feedback and continuously improve the quality of responses regarding vacation requests. Generative AI can also utilize surveys and user reviews to improve the quality of responses based on feedback. For example, generative AI can collect employee feedback about how they felt about the responses and improve the quality of responses based on the results. This allows generative AI to collect employee feedback and continuously improve the quality of responses based on that feedback.

[0074] The emotion estimation function can analyze the emotions of employees when providing feedback and make improvement suggestions based on those emotions. For example, the emotion estimation function allows the generation AI to analyze the emotions of employees when providing feedback and make suggestions to improve the quality of responses regarding vacation requests. The emotion estimation function can also analyze the emotions of employees when providing feedback in real time and make suggestions to elicit positive emotions. For example, when an employee provides feedback, the generation AI can analyze the employee's emotions and provide advice to help them relax. This makes it possible to analyze the emotions of employees when providing feedback and make improvement suggestions based on those emotions.

[0075] The learning function can automatically generate training programs to help employees improve their skills and knowledge. For example, the generation AI uses the learning function to automatically generate a training program to help employees improve their skills and knowledge regarding vacation requests. The learning function can also analyze an employee's past learning history and skill level to provide an individualized training program. For example, the learning function automatically generates a new training program based on training programs that the employee has previously taken. In this way, the learning function can be used to automatically generate training programs to help employees improve their skills and knowledge.

[0076] The emotion estimation function can analyze the emotions of employees when they use the learning function in real time and make suggestions to elicit positive emotions. For example, the emotion estimation function uses a generative AI to analyze the emotions of employees when they use the learning function in real time and display encouraging messages to elicit positive emotions. The emotion estimation function can also make suggestions to help employees relax if they feel stressed while learning. For example, when an employee is taking a training program, the generative AI can analyze the employee's emotions and provide advice to help them relax. This allows the system to analyze the emotions of employees when they use the learning function in real time and make suggestions to elicit positive emotions, thereby improving employee satisfaction.

[0077] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0078] The question understanding unit can also provide relevant video tutorials and interactive guides in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generation AI can provide a video tutorial explaining the procedure for requesting vacation. The question understanding unit can also use interactive guides to help employees go through the procedure step by step. For example, if an employee asks, "How do I request paid vacation?", the generation AI can provide an interactive guide, allowing employees to receive real-time support as they go through the procedure. This allows the system to deepen employees' understanding by providing relevant video tutorials and interactive guides in response to their questions.

[0079] The question understanding unit can also provide relevant legal advice and compliance information in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generation AI can provide legal requirements and compliance information related to vacation requests. The question understanding unit can also provide relevant legal advice when an employee asks about a specific legal issue. For example, if an employee asks, "What should I do if my paid vacation request is denied?", the generation AI can provide legal advice tailored to the situation. This allows the system to deepen employees' understanding by providing them with relevant legal advice and compliance information in response to their questions.

[0080] The question understanding unit can also provide relevant industry best practices and success stories in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generation AI will provide industry best practices and success stories. The question understanding unit can also provide relevant success stories when an employee asks about a specific business process. For example, if an employee asks, "How do I request paid vacation?", the generation AI can provide success stories from other companies so that the employee can refer to those procedures. This allows employees to deepen their understanding by providing relevant industry best practices and success stories in response to their questions.

[0081] The question understanding unit uses its emotion estimation function to analyze the emotions of employees when they ask questions and can provide feedback that corresponds to their emotions. For example, when an employee asks, "Please tell me the procedure for applying for vacation," the generation AI analyzes the employee's emotions and provides feedback that elicits positive emotions. The question understanding unit can also provide feedback that helps employees relax if they are feeling stressed. For example, when an employee asks, "What should I do if my paid vacation application is delayed?" the generation AI analyzes the employee's emotions and provides feedback that helps them relax. This makes it possible to analyze the emotions of employees when they ask questions and provide feedback that corresponds to their emotions, thereby improving employee satisfaction.

[0082] The question understanding unit uses emotion estimation to analyze the emotions expressed by employees when they ask questions and can provide customized support based on their emotions. For example, when an employee asks, "Please tell me how to apply for vacation," the generation AI analyzes the employee's emotions and, if they are feeling stressed, provides customized support to help them relax. The question understanding unit can also provide customized support to reassure employees if they are feeling anxious. For example, when an employee asks, "What should I do if my paid vacation application is delayed?" the generation AI analyzes the employee's emotions and gently explains specific steps to take. This allows the system to analyze the emotions expressed by employees when they ask questions and provide customized support based on their emotions, thereby improving employee satisfaction.

[0083] The question understanding unit uses emotion estimation to analyze the emotions expressed by employees when they ask questions and can provide resources appropriate to their emotions. For example, when an employee asks, "Please tell me how to apply for vacation," the generation AI analyzes the employee's emotions and, if they are feeling stressed, provides resources to help them relax. The question understanding unit can also provide resources that give employees a sense of security if they are feeling anxious. For example, when an employee asks, "What should I do if my paid vacation application is delayed?" the generation AI analyzes the employee's emotions and gently explains specific steps to take. This allows the system to analyze the emotions expressed by employees when they ask questions and provide resources appropriate to their emotions, thereby improving employee satisfaction.

[0084] The question understanding unit uses its emotion estimation function to analyze the emotions expressed when an employee asks a question and can provide a training program tailored to that emotion. For example, when an employee asks, "Please tell me how to apply for vacation," the generation AI analyzes the employee's emotions and, if the employee is feeling stressed, provides a training program designed to help them relax. The question understanding unit can also provide a training program that gives employees a sense of security if they are feeling anxious. For example, when an employee asks, "What should I do if my paid vacation application is delayed?" the generation AI analyzes the employee's emotions and gently explains specific steps to take. This allows the system to analyze the emotions expressed when an employee asks a question and provide a training program tailored to their emotions, thereby improving employee satisfaction.

[0085] The knowledge database can also provide relevant external resources and links in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generative AI will provide links to official external websites and related online resources. The knowledge database can also provide relevant external resources when an employee asks a question about a specific topic. For example, if an employee asks, "How do I request paid vacation?", the generative AI will provide links to relevant legal information and guidelines. This allows the system to provide relevant external resources and links in response to employee questions, thereby deepening employees' understanding.

[0086] The knowledge database can also provide relevant statistical data and analytical results in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generative AI will provide statistical data and analytical results related to vacation requests. The knowledge database can also provide relevant statistical data and analytical results when an employee asks a question about a specific topic. For example, if an employee asks, "How do I request paid vacation?", the generative AI will provide statistical data on the usage of paid vacation and the success rate of requests. This allows employees to deepen their understanding by providing relevant statistical data and analytical results in response to their questions.

[0087] The knowledge database can also provide relevant case studies and examples in response to employee questions. For example, if an employee asks, "What is the procedure for requesting vacation?", the generative AI will provide case studies and examples related to vacation requests. The knowledge database can also provide relevant case studies and examples when an employee asks a question about a specific topic. For example, if an employee asks, "How do I request paid vacation?", the generative AI will provide success stories and failure stories from other employees. This allows employees to deepen their understanding by providing relevant case studies and examples in response to their questions.

[0088] The processing flow of the second embodiment will be briefly explained below.

[0089] Step 1: The question understanding unit understands the question from the employee. For example, the question understanding unit uses natural language processing technology to analyze the employee's question and understand its intent. The question understanding unit can also identify important parts of the question using keyword extraction technology. For example, if an employee asks, "Please tell me the procedure for applying for vacation," the question is analyzed and information about vacation applications is extracted. Step 2: The answer generation unit generates an answer based on the question understood by the question understanding unit. For example, the answer generation unit uses a rule-based generation method to generate an appropriate answer to the question. The answer generation unit can also use a machine learning model to generate a more advanced answer to the question. For example, if an employee asks, "How do I apply for paid leave?", the answer generation unit uses a rule-based generation method to explain the specific application procedure. Step 3: The knowledge database provides the answer generated by the answer generator. For example, the knowledge database may contain information about a company's human resources policies and procedures, and provide accurate answers to questions. The knowledge database is also dynamically updated, allowing it to always provide the latest information. For example, the knowledge database is automatically updated when a company's human resources policies change, providing answers based on the latest information.

[0090] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0091] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0092] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0093] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0094] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0095] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0096] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0097] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0098] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0099] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0100] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0101] 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.

[0102] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0103] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0104] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0105] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0106] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0108] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0109] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0110] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0111] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0112] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0113] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0114] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0115] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0116] 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.

[0117] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0118] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0119] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0120] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0121] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0122] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0123] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0124] 7, a 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.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0130] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0131] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0132] 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.

[0133] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0134] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0135] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0136] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0137] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0138] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0139] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0140] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0141] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0142] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0143] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0144] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0145] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0146] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0147] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0148] 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.

[0149] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0150] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0151] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0152] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0153] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0154] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0155] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0156] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0157] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A question understanding department that understands questions from employees; an answer generation unit that generates an answer based on the question understood by the question understanding unit; a knowledge database that provides the answers generated by the answer generation unit; A system characterized by:

2. The question understanding unit To better understand the intent of the question, the AI ​​analyzes the employee's past question history and behavioral patterns to generate a personalized answer.

2. The system of claim 1.

3. The question understanding unit Improve convenience for employees by diversifying the ways to input questions, including voice input and handwriting input.

2. The system of claim 1.

4. The knowledge database includes: Dynamically updated to always provide answers based on the latest policies and procedures 2. The system of claim 1.

5. The generated AI is In response to the employee's questions, the related FAQs and guidelines are also provided to facilitate self-resolution.

2. The system of claim 1.

6. The question understanding unit The employee's feelings when asking a question are analyzed, and the answer is generated according to the feelings, thereby improving the employee's satisfaction.

2. The system of claim 1.

Images