system

Abstract

Provide a system. [Solution] a user interface means for inputting business know-how; natural language processing means for analyzing the business know-how; an artificial intelligence model means for learning the analyzed business know-how; an output interface means for providing a business procedure using the artificial intelligence model; feedback receiving means for receiving and analyzing feedback from a user; a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback; A system including:

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] In companies, business know-how primarily depends on the experience and skills of individual employees, resulting in a lack of efficiency and accuracy when transferring work to new employees. In such situations, standardizing work is difficult, and work quality and productivity are often inconsistent. Another problem is that because know-how is dependent on specific individuals, it is easily lost when those individuals leave the company. The present invention aims to solve these problems and achieve an efficient and accurate transfer of business know-how. [Means for solving the problem]

[0005] The system of the present invention solves the above-mentioned problems by providing a system including a user interface for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for training the analyzed business know-how, an output interface means for providing business procedures using the artificial intelligence model, a feedback receiving means for receiving and analyzing feedback from users, and a retraining means for retraining the artificial intelligence model based on the analyzed feedback. Specifically, an employee inputs business know-how into the system, which analyzes the information using natural language processing and trains the AI ​​model with the analysis results. Furthermore, the AI ​​model guides new employees through specific business procedures in real time and continuously improves the accuracy of the model through a feedback mechanism, thereby ensuring efficient and accurate handover of business know-how.

[0006] "Business know-how" is a general term for information such as procedures, knowledge, skills, and ingenuity required to carry out business.

[0007] "User interface means" is a function that provides an interface for a user to input information into the system and obtain information from the system.

[0008] "Natural language processing means" refers to the technologies and algorithms that allow computers to understand and analyze the natural language that humans use on a daily basis.

[0009] "Artificial intelligence model means" refers to an AI model that learns business know-how and makes inferences and judgments based on data.

[0010] "Output interface means" is a function that provides an interface for presenting information and business procedures learned by the AI ​​model to the user.

[0011] The "feedback receiving means" is a function for receiving feedback such as opinions, problems, and unclear points from users.

[0012] The "relearning means" is a function that allows the AI ​​model to be retrained based on the received feedback, improving its accuracy. [Brief explanation of the drawings]

[0013] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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, a 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), and an APU (Accelerated Processing Unit).

[0017] 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.

[0018] 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.

[0019] 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), Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0025] 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.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] The present invention is a tool for training an AI to learn business know-how and using the AI ​​to carry out business handover. Specific embodiments for carrying out the present invention will be described below.

[0035] Basic system configuration

[0036] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, and a re-learning means.

[0037] Explanation of program processing

[0038] 1. Gathering know-how

[0039] To gather business know-how, a user first logs into the system and inputs business procedures, such as "procedures for issuing invoices," in text format via the user interface. For example, the user sequentially inputs steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[0040] 2. Data analysis and learning

[0041] The server uses natural language processing to analyze the business know-how entered by the user. This analysis includes grammatical analysis of the text and keyword extraction. The analyzed data is organized into a data set showing the business flow and important points. The server then trains an artificial intelligence model on the analysis results. The model learns the relevance of each step and specific implementation methods, accumulating knowledge about business procedures.

[0042] 3. Providing business procedures

[0043] When the terminal provides work procedures to a new user (for example, a new employee), it guides them through the specific work procedures in real time based on the learning results from the server. When the user operates the system and clicks the "Start work procedures" button, the terminal displays the work procedures step by step based on the information learned by the AI. For example, instructions such as "Please enter the client's information into the management system" are displayed, along with detailed operating instructions and points to note.

[0044] Specific examples

[0045] Gathering know-how

[0046] The user inputs business know-how under the title "Invoice Issuance Procedure." Specifically, the following steps are described in detail:

[0047] 1. Enter client information into the management system.

[0048] 2. Calculate the amount to be claimed.

[0049] 3. Fill in the required information on the invoice form.

[0050] 4. Save the invoice as a PDF.

[0051] 5. Email it to your client.

[0052] Data analysis and learning

[0053] The server receives this data and analyzes it using natural language processing. For example, it extracts keywords and operational procedures related to each step and organizes them into a business flow. This data is then trained into an artificial intelligence model, allowing the AI ​​to understand specific steps and important points.

[0054] Providing business procedures

[0055] When new employee User B uses the system to learn how to issue an invoice, the device displays guidance based on the information learned by the AI. For example, when User B clicks the "Start invoice issuance procedure" button, the first step is to "Enter client information into the management system." Next, instructions such as "Calculate the invoice amount" and "Enter the information into the invoice format" are displayed in sequence, with specific support provided for each step.

[0056] Feedback Mechanism

[0057] If User B encounters any unclear points or problems while working, he or she inputs that information into the system as feedback. The server analyzes this feedback and retrains the AI ​​model. This improves the accuracy and reliability of the system so that future users do not encounter similar problems.

[0058] As described above, the present invention is a system that realizes efficient and accurate business handover through a series of processes including collection, analysis, learning, provision, and feedback of business know-how.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user inputs business know-how. Specifically, after logging in to the system, the user inputs business procedures such as "invoice issuance procedures" in text format via the provided user interface. For example, the following information is input for each procedure:

[0062] 1. Enter client information into the management system.

[0063] 2. Calculate the amount to be claimed.

[0064] 3. Fill in the required information on the invoice form.

[0065] 4. Save the invoice as a PDF.

[0066] 5. Email it to your client.

[0067] Step 2:

[0068] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[0069] Step 3:

[0070] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[0071] Step 4:

[0072] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[0073] Step 5:

[0074] User B, who is new to the system, clicks the "Start business procedure" button. This causes the device to retrieve information learned from the AI ​​model and display sequential instructions in real time. For example, the device may display instructions such as "Enter client information into the management system," along with detailed operating instructions and important points to note.

[0075] Step 6:

[0076] If User B encounters any unclear points or problems in the system while following the procedures, he or she clicks the "Feedback" button and enters the details of the problem or question into the system. This feedback is sent to the system.

[0077] Step 7:

[0078] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[0079] Step 8:

[0080] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[0081] Through these steps, this system achieves efficient and accurate business handover through a series of processes: collecting, analyzing, learning, providing, and providing feedback on business know-how.

[0082] Example 1

[0083] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0084] Traditional methods of job handover are time-consuming and laborious, and often result in inaccurate information being conveyed or important procedures being overlooked. Another problem is the lack of an appropriate support system for new employees to efficiently learn their jobs. This leads to reduced work efficiency and an increase in mistakes and rework.

[0085] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0086] In this invention, the server includes a user interface means for inputting business knowledge, a natural language processing means for analyzing the business knowledge, and a machine learning model means for training the analyzed business knowledge. This makes it possible to efficiently and accurately collect, analyze, and train business knowledge. Furthermore, by including an opinion receiving means for receiving and analyzing opinions from users and a re-learning means for re-training the machine learning model based on the analyzed opinions, it is possible to continuously improve the system and increase its accuracy.

[0087] "Business knowledge" refers to procedures, know-how, related information, etc. required when performing business.

[0088] "User interface means" refers to the operation screen and interactive tools that allow users to input, edit, and view business knowledge.

[0089] "Natural language processing means" refers to algorithms and technologies for analyzing text data and understanding its meaning and structure.

[0090] "Machine learning model means" refers to a system that uses machine learning technology to learn patterns and knowledge from input data and make inferences and predictions.

[0091] "Output interface means" refers to devices and software for providing learning results to users and displaying business procedures.

[0092] "Opinion receiving means" refers to a system or function for receiving and processing feedback and opinions from users.

[0093] "Retraining methods" refers to techniques and processes used to retrain a machine learning model and improve its performance based on received opinions and feedback.

[0094] The present invention is a system for collecting, analyzing, learning, providing, and feeding back business knowledge, and specific embodiments thereof will be described.

[0095] Basic system configuration

[0096] This system is composed of a user interface means for inputting business knowledge, a natural language processing means for analyzing the input information, a machine learning model means for learning the analyzed information, an output interface means for providing the learning results, an opinion receiving means for receiving opinions from users, and a re-learning means.

[0097] Gathering know-how

[0098] The user first logs in to the system and inputs business knowledge in text format via the user interface. For example, under the title "Procedure for issuing invoices," the user might input steps such as "Enter client information into the management system," "Calculate the invoice amount," "Fill in the information into the invoice format," "Save as PDF," and "Send to the client by email."

[0099] Data analysis and learning

[0100] 1. The server receives the business knowledge input by the user. The received data is temporarily stored in a database (e.g., MySQL (registered trademark)).

[0101] 2. Analyze the input business knowledge using a natural language processing engine (e.g., SpaCy) including legal procedures. The analysis includes grammatical analysis, keyword extraction, and sentence structuring.

[0102] For example, keywords such as "entering information" and "invoice format" are extracted from the sentence "entering information into an invoice format."

[0103] 3. The server organizes the business procedure data based on the analysis results and saves it as a dataset, which clearly shows the relationships and order of each procedure.

[0104] For example, the continuity between "Enter client information into the management system" and "Calculate the billing amount" is maintained.

[0105] 4. The server trains a machine learning model (e.g., GPT-4 (registered trademark)) on the data and accumulates the learned knowledge.

[0106] Providing business procedures

[0107] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The terminal guides the user through the business procedure in real time based on the learning results from the server.

[0108] Examples:

[0109] For example, when a user clicks the "Start Business Procedure" button, the following instruction appears on the screen: "Please enter the client's information into the management system." At this time, detailed operating instructions and important points are also provided.

[0110] Next, steps such as "Calculate the bill amount" and "Enter the information into the billing form" are displayed, with specific support information provided for each step.

[0111] Feedback Mechanism

[0112] If a user has a question or problem while going through a work procedure, they click the "Feedback" button and enter the problem. The server receives this feedback, analyzes it using a natural language processing engine, and saves it as a feedback dataset. The feedback data is then input into a machine learning model, and retraining improves the accuracy and reliability of the system.

[0113] Prompt Sentence Examples

[0114] "Please have the AI ​​learn the following business procedure. The title is 'Invoice Issuance Procedure'.

[0115] 1. Enter client information into the management system.

[0116] 2. Calculate the amount to be claimed.

[0117] 3. Fill in the required information on the invoice form.

[0118] 4. Save the invoice as a PDF.

[0119] 5. Email it to your client.

[0120] I would love to see AI learn these steps and provide a way to guide new users."

[0121] As described above, the present invention is a system that efficiently collects, analyzes, learns, provides, and improves business knowledge through feedback, thereby realizing efficient business handover.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Gathering know-how

[0124] A user logs into the system and inputs business knowledge. Specifically, the user enters business procedures such as "procedures for issuing invoices" in text format via the user interface. For example, the user might enter steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[0125] Input: Text data of business procedures

[0126] Output: User-entered business procedure data

[0127] Step 2: Receiving and temporarily storing data

[0128] The server receives the business procedure data sent by the user and temporarily stores this data in a database (e.g., MySQL).

[0129] Input: Business procedure data entered by the user

[0130] Output: Business procedure data stored in a database

[0131] Step 3: Natural Language Processing

[0132] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received business procedure data. This analysis involves grammatical analysis, keyword extraction, and sentence structuring. For example, from the sentence "filling in information on an invoice format," it extracts keywords such as "filling in information" and "invoice format."

[0133] Input: Business procedure data stored in the database

[0134] Output: Analyzed business procedure data (keywords and sentence structure)

[0135] Step 4: Organizing the dataset

[0136] The server organizes the business procedure data based on the analysis results and saves it as a dataset. This includes clarifying the relationship and order of each step. For example, it maintains the continuity between "Enter client information into the management system" and "Calculate the billing amount."

[0137] Input: Parsed business procedure data

[0138] Output: Organized business procedure dataset

[0139] Step 5: Training the AI ​​model

[0140] The server trains a machine learning model (e.g., GPT-4) using the organized dataset. The model learns the structure and relationships of business procedures and understands detailed support methods for each procedure.

[0141] Input: Organized business procedure dataset

[0142] Output: Trained AI model

[0143] Step 6: Providing business procedures and guidance

[0144] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The device retrieves guidance information from the trained AI model and guides the user through the business procedure in real time. For example, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[0145] Input: Business procedure start request from user

[0146] Output: Business procedure guide displayed on the terminal

[0147] Step 7: Provide support information

[0148] The device will display detailed support information and notes for each step, including detailed instructions such as "Please make sure the information you entered is accurate."

[0149] Input: Guide information for trained AI models

[0150] Output: Detailed supporting information displayed on the terminal

[0151] Step 8: Provide feedback

[0152] If a user encounters a question or problem while going through the work procedure, they can click the "Feedback" button to enter the problem, and this information will be sent to the system.

[0153] Input: User feedback information

[0154] Output: Feedback data sent to the server

[0155] Step 9: Receive and analyze feedback

[0156] The server receives the feedback sent by the user and analyzes it using a natural language processing engine. The analysis results are stored as a feedback dataset.

[0157] Input: Feedback data

[0158] Output: Parsed feedback dataset

[0159] Step 10: Retrain

[0160] The server inputs the feedback data into the machine learning model and performs retraining, which improves the accuracy and reliability of the model.

[0161] Input: Parsed feedback dataset

[0162] Output: Retrained AI model

[0163] Through the above series of processing steps, the present invention realizes accurate and efficient handover of business knowledge and enables continuous improvement of the system.

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] The present invention aims to provide a system that provides real-time guidance on work procedures at logistics centers, enabling even new or temporary staff to perform their work efficiently. Current work handover methods rely on understanding manuals or verbal explanations from person to person, which can lack accuracy and efficiency. Furthermore, there is a lack of mechanisms for improving work procedures based on feedback, which can lead to recurrence of similar problems. Therefore, there is a need for a system that uses AI to learn work know-how, efficiently guides staff through work procedures, and retrains the model through feedback.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0168] In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means, a feedback receiving means, a relearning means, and a guide means for guiding business procedures in real time via a smart device. This enables efficient handover of business procedures at a logistics center and continuous improvement of business procedures based on feedback.

[0169] "Business know-how" refers to the knowledge, techniques, and procedures required to carry out a specific business task effectively and efficiently.

[0170] "User interface means" refers to an operation screen or input device that allows a user to input business know-how into the system.

[0171] "Natural language processing means" refers to technology for analyzing input text data and understanding and processing its content.

[0172] "Artificial intelligence model means" refers to algorithms or systems that learn analyzed business know-how and provide business procedures based on that knowledge.

[0173] "Output interface means" refers to a display screen or output device for providing the user with the business procedures learned by the artificial intelligence model.

[0174] "Feedback receiving means" refers to a system or device for receiving and analyzing feedback from a user.

[0175] "Retraining means" refers to a learning process for improving the accuracy of an artificial intelligence model based on analyzed feedback.

[0176] "Guide means" refers to a system or device that guides users through business procedures in real time via a smart device.

[0177] "Smart devices" refers to mobile information terminals with advanced functions, such as smartphones and smart glasses.

[0178] A "business procedure" refers to a series of steps or processes for accomplishing a particular task.

[0179] The present invention relates to a system for providing real-time guidance of work procedures at a logistics center using smart devices. Specific embodiments for carrying out the present invention will be described below.

[0180] Basic system configuration

[0181] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, a relearning means, and a guide means for guiding business procedures in real time via a smart device.

[0182] Hardware and software used

[0183] Hardware:

[0184] Smart devices (e.g., smart glasses, smartphones)

[0185] software:

[0186] Natural language processing libraries (e.g. Spacy)

[0187] Generative AI models (e.g., GPT-2, transformers library)

[0188] Data processing and calculation

[0189] 1. Gathering business know-how:

[0190] The server collects business know-how in text format through a user interface. This process also supports voice input using voice recognition. For example, detailed business procedures can be entered under a title such as "Incoming Inspection Procedure." This makes it easy for even new or temporary staff to input information.

[0191] 2. Data analysis and learning:

[0192] The server analyzes the collected business know-how using natural language processing and trains an AI model based on the results. For example, Spacy can be used to extract keywords and phrases related to business procedures, and a generative AI model (GPT-2) can then train on these.

[0193] 3. Providing business procedures:

[0194] The terminal (smart device) guides the work procedures in real time based on the learning results. When a new staff member starts a task, for example, by clicking the "Start work procedure" button, the specific steps learned by the AI ​​are displayed one by one. Instructions such as "Please scan the product barcode" and "Please check the quantity" are displayed.

[0195] 4. Feedback mechanism:

[0196] Users input any problems or questions they encounter as they work into the system as feedback. The server analyzes this feedback information and retrains the AI ​​model to improve the accuracy of future work procedures.

[0197] Examples of concrete examples and prompts

[0198] Examples:

[0199] The incoming goods inspection procedure guides users through steps such as "scanning the product barcode," "confirming the quantity," and "checking for defects." Users can check these steps in real time via their smart devices and carry out their work.

[0200] Example prompt sentence:

[0201] "When new staff members learn the receiving inspection procedures, AI can generate a step-by-step guide based on their operational know-how."

[0202] Generated text:

[0203] 1. Scan the product barcode.

[0204] 2. Check the quantity.

[0205] 3. Check for any defects.

[0206] 4. Once you have finished checking, move on to the next product.

[0207] In this way, the system of the present invention realizes efficient operations and accurate handover in a logistics center.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] The user inputs business know-how

[0211] Users input specific operational procedures at the logistics center (e.g., incoming goods inspection procedures) in text format through a user interface. Voice recognition can also be used for input.

[0212] Input: Detailed text data of business procedures

[0213] Output: Text data of the entered business procedures

[0214] Step 2:

[0215] The server analyzes business know-how

[0216] The server analyzes the input business know-how using natural language processing tools (e.g., Spacy), performing grammatical analysis and extracting keywords to identify important points in the business procedures.

[0217] Input: Text data of business procedures entered by the user

[0218] Output: Analyzed keywords and grammatical structures

[0219] Step 3:

[0220] The server trains the AI ​​model

[0221] The server then trains an artificial intelligence model (e.g., GPT-2) on the analyzed business know-how data. The model then understands the relationships between business procedures and how to carry them out, and improves its reasoning capabilities based on this.

[0222] Input: Analyzed keywords and grammatical structure data

[0223] Output: Learned business procedure model

[0224] Step 4:

[0225] The terminal provides business procedures

[0226] The device (e.g., smart glasses or smartphone) displays the work procedure in real time based on the learning results. When the user presses the "Start work procedure" button, specific instructions (e.g., "Scan the product barcode") are displayed sequentially.

[0227] Input: Learned business procedure model

[0228] Output: Real-time operational instructions

[0229] Step 5:

[0230] User enters feedback

[0231] Users input feedback into the system about any problems or unclear points that arise while working.

[0232] Input: Feedback information on problems or unclear points that occurred during work

[0233] Output: Feedback text data

[0234] Step 6:

[0235] The server analyzes the feedback and re-learns

[0236] The server analyzes the feedback received from the user using natural language processing means and retrains the artificial intelligence model using retraining means, thereby improving the accuracy of the model and making subsequent guidance more effective.

[0237] Input: Text data of user feedback

[0238] Output: Improved business procedure model

[0239] The above are the specific processing steps of the program for the system that realizes the application example.

[0240] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0241] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[0242] The system consists of the following components:

[0243] 1. User interface means for inputting business know-how

[0244] 2. Natural language processing means for analyzing input business know-how

[0245] 3. AI modeling means for learning the analyzed business know-how

[0246] 4. Output interface means for providing business procedures using AI models

[0247] 5. Feedback receiving means for receiving and analyzing user feedback

[0248] 6. A retraining method to retrain the AI ​​model based on the analyzed feedback

[0249] 7. Emotion engine means for recognizing user emotions

[0250] 8. A method for adjusting work procedures based on user emotions recognized by an emotion engine

[0251] Explanation of program processing

[0252] 1. Gathering know-how

[0253] A user logs into the system and inputs details of business know-how using the user interface means. For example, a specific procedure such as "procedure for issuing an invoice" is input in text format.

[0254] 2. Data analysis and learning

[0255] The server analyzes the input business procedures using natural language processing. The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained into an AI model. The AI ​​model learns the relevance of procedures and specific execution methods, improving its reasoning capabilities.

[0256] 3. Emotion recognition and business procedure provision

[0257] When a user receives instructions for a task, the device displays the instructions in real time based on information learned from the AI ​​model. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This may include providing more detailed explanations or additional support information.

[0258] Specific examples

[0259] Gathering know-how

[0260] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[0261] 1. Enter client information into the management system.

[0262] 2. Calculate the amount to be claimed.

[0263] 3. Fill in the required information on the invoice form.

[0264] 4. Save the invoice as a PDF.

[0265] 5. Email it to your client.

[0266] Data analysis and learning

[0267] The server receives this data and analyzes it using natural language processing. As a result of the analysis, keywords and grammatical structures related to each step are extracted and structured as a business flow. This is then trained into an AI model, which then understands the specific steps and important points to note.

[0268] Providing business procedures and emotion recognition

[0269] When new employee User B uses the system to learn how to issue an invoice, the device uses information from the AI ​​model to guide the user through the process in real time. For example, instructions like "Please enter client information into the management system" are displayed. The emotion engine recognizes the user's emotions, and if the user is confused, it provides more detailed explanations and supplementary information to help the user carry out their work with confidence.

[0270] Feedback Mechanism

[0271] If User B encounters any questions or problems while working, he or she enters that information into the system as feedback. The server receives the feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to the user from the next time onwards.

[0272] As described above, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[0273] The processing flow will be explained below.

[0274] Step 1:

[0275] A user logs into the system and inputs business know-how. Specifically, the user uses a user interface to input business procedures such as "procedures for issuing invoices" in text format. For example, the user might input the following steps in order:

[0276] 1. Enter client information into the management system.

[0277] 2. Calculate the amount to be claimed.

[0278] 3. Fill in the required information on the invoice form.

[0279] 4. Save the invoice as a PDF.

[0280] 5. Email it to your client.

[0281] Step 2:

[0282] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[0283] Step 3:

[0284] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[0285] Step 4:

[0286] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[0287] Step 5:

[0288] When User B clicks the "Start Business Procedure" button, the device retrieves the information learned from the AI ​​model and displays the business procedure step by step. For example, the first step is to display the instruction "Enter the client's information into the management system," followed by detailed operating instructions and important points to note.

[0289] Step 6:

[0290] The device uses a camera and microphone to recognize the user's emotions, and the emotion engine analyzes facial expressions and voice. The emotion engine recognizes the user's emotions in real time and adjusts the instructions provided by the system based on that. For example, if the device recognizes that the user is confused, it will display more detailed explanations or support information.

[0291] Step 7:

[0292] User B provides feedback. If any questions or problems arise while working, the user clicks the "Feedback" button and enters the problem or question into the system. This feedback is sent to the system.

[0293] Step 8:

[0294] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[0295] Step 9:

[0296] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[0297] Through these steps, the system achieves efficient, accurate and considerate business handover through a series of processes including collection, analysis, learning, provision, feedback and emotion recognition of business know-how.

[0298] Example 2

[0299] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0300] Conventional job handover systems make it difficult to standardize and streamline job know-how, and lack support that takes users' feelings into consideration, causing inconvenience and stress for new entrants. They also lack a mechanism for effectively utilizing user feedback to improve the system. Therefore, a more efficient and user-friendly job handover system is needed.

[0301] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for inputting business know-how, an analysis means for analyzing the business know-how, an intelligence model means for learning the analyzed business know-how, an output means for providing business procedures using the intelligence model, a recognition means for recognizing a user's emotion, an adjustment means for adjusting the business procedures based on the recognized emotion, a receiving means for receiving and analyzing feedback from the user, and a re-learning means for re-learning the intelligence model based on the analyzed feedback. This makes it possible to efficiently take over business and provide support that takes into consideration the user's emotion.

[0302] "Input means" refers to a device or interface that allows a user to input data such as business know-how into the system.

[0303] "Analysis means" refers to a device or function for processing and analyzing input data to extract necessary information.

[0304] The "intelligent model means" is a model that uses artificial intelligence to learn based on analyzed data and accumulate knowledge that is useful for providing business procedures.

[0305] "Output means" refers to a device or interface for displaying or providing the business procedure provided by the intelligent model to the user.

[0306] "Recognition means" refers to a device or function for recognizing the user's emotions or state.

[0307] "Adjustment means" is a device or function for adjusting business procedures or response methods based on recognized emotions.

[0308] "Receiving means" refers to a device or interface for receiving feedback from a user and incorporating it into the system.

[0309] A "relearning means" is a device or function that causes the intelligence model to be retrained based on the received feedback.

[0310] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[0311] The system consists of the following components:

[0312] 1. Input method for inputting business know-how

[0313] 2. Analysis method for analyzing input business know-how

[0314] 3. Intelligent model means for learning the analyzed business know-how

[0315] 4. Output means for providing business procedures using intelligent models

[0316] 5. Recognition method for recognizing user emotions

[0317] 6. Adjustment measures to adjust work procedures based on perceived emotions

[0318] 7. Receiving means for receiving and analyzing user feedback

[0319] 8. A retraining method for retraining the intelligence model based on the analyzed feedback

[0320] Specifically, the system operates in the following manner.

[0321] Gathering know-how

[0322] A user logs into the system and inputs details of business know-how using an input device. For example, a specific procedure such as "procedures for issuing invoices" is input in text format. This know-how is saved in a database on the server.

[0323] Data analysis and learning

[0324] The server analyzes the input business procedures using an analysis tool (e.g., SpaCy or NLTK). The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained by an intelligent model tool (e.g., Hugging Face's Transformers). The intelligent model learns the relationships between procedures and specific execution methods, improving its reasoning capabilities.

[0325] Emotion recognition and business procedure provision

[0326] When a user receives instructions for a task, the device displays them in real time based on information learned from the intelligent model. The recognition means analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This could include providing more detailed explanations or additional support information.

[0327] Gathering feedback and relearning

[0328] If a user encounters any questions or problems while working, they can enter that information as feedback into the system. The server receives the feedback, analyzes it using analytical means, and retrains the intelligence model. This allows the server to provide more accurate and detailed instructions to the user from the next time onwards.

[0329] Specific examples

[0330] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[0331] 1. Enter client information into the management system.

[0332] 2. Calculate the amount to be claimed.

[0333] 3. Fill in the required information on the invoice form.

[0334] 4. Save the invoice as a PDF.

[0335] 5. Email it to your client.

[0336] Prompt Sentence Examples

[0337] Enter client information into the management system.

[0338] Calculate the amount to be charged.

[0339] Fill in the required information on the invoice form.

[0340] Save the invoice in PDF format.

[0341] Email it to your client.

[0342] In this way, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[0343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0344] Step 1: Gathering know-how

[0345] A user logs in to the system. After entering the correct login information and passing the authentication process, the user is redirected to the business know-how input screen. Here, the user enters specific business procedures (for example, "procedures for issuing invoices") in text format. This input data is sent to the server and saved in the database.

[0346] input:

[0347] User login information (ID and password)

[0348] Business know-how entered in text format

[0349] output:

[0350] Business know-how stored in a database

[0351] Operation:

[0352] User interface prompts for data entry and saving

[0353] Step 2: Analyze and train the data

[0354] The server analyzes the stored business procedures using an analysis means. The server uses natural language processing means (e.g., SpaCy or NLTK) to tokenize the input text data and extract important keywords and grammatical structures. This structures the business flow and prepares it as data for the next learning by the intelligence model means.

[0355] input:

[0356] Business know-how stored in a database

[0357] output:

[0358] Structured business flow data

[0359] Operation:

[0360] Executing natural language processing algorithms and storing results

[0361] Step 3: Training the Intelligence Model

[0362] The server trains the analyzed data using an intelligent model (for example, Hugging Face's Transformers). The server calls the intelligent model and trains it on the data, allowing it to understand the relevance of business procedures and how to execute them. Once training is complete, the model is ready to be used to provide business procedures.

[0363] input:

[0364] Structured business flow data

[0365] output:

[0366] An intelligent model that understands business procedures

[0367] Operation:

[0368] Execution of the learning process of the intelligent model and notification of its completion

[0369] Step 4: Provide business procedures

[0370] Based on the information learned from the intelligent model, the device provides users with real-time instructions on how to proceed. Specifically, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[0371] input:

[0372] Intelligence Model

[0373] output:

[0374] Real-time operational procedures

[0375] Operation:

[0376] Displaying instruction messages on the user screen

[0377] Step 5: Emotion Recognition

[0378] The device's recognition means analyzes the user's facial expressions and voice to recognize their emotions. The device identifies the user's emotions based on the recognized emotion data. For example, if the user is confused, the system will display additional explanations or support.

[0379] input:

[0380] User facial expression and voice data

[0381] output:

[0382] Recognized emotion data

[0383] Operation:

[0384] Data collection and analysis using cameras and microphones

[0385] Step 6: Adjust your work procedures based on emotions

[0386] The device can then adjust its work procedures based on the recognized emotion data, for example, providing more detailed explanations or displaying additional support information if the user is confused.

[0387] input:

[0388] Recognized emotion data

[0389] output:

[0390] Adjusted operating procedures

[0391] Operation:

[0392] Displaying additional instruction messages on the user screen

[0393] Step 7: Gather feedback

[0394] The user inputs feedback about the work procedure into the system. The user writes down any problems or questions about the work in progress and sends them to the server via the input means.

[0395] input:

[0396] User feedback (text format)

[0397] output:

[0398] Feedback stored in the database

[0399] Operation:

[0400] User interface prompts for feedback entry and saving

[0401] Step 8: Analyze feedback and retrain

[0402] The server analyzes the received feedback and retrains the intelligence model means. The server analyzes the feedback using natural language processing means and extracts areas for improvement and problems. New analysis data is supplied to the intelligence model and retraining is performed.

[0403] input:

[0404] Feedback stored in the database

[0405] output:

[0406] Improved Intelligence Model

[0407] Operation:

[0408] Conducting feedback analysis and retraining process of the intelligence model

[0409] Through the above steps, this system realizes task handover that takes emotions into consideration, aiming to improve work efficiency and user satisfaction.

[0410] (Application example 2)

[0411] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0412] Conventional task handover systems lack the ability to effectively convey task know-how and the ability to appropriately adjust instructions based on the user's emotional state. This often leaves new operators feeling confused and frustrated, leading to reduced productivity and work efficiency. Furthermore, there is a lack of effective means for utilizing user feedback to improve the system's accuracy, which delays improvements to the task handover process.

[0413] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means for providing business procedures using the artificial intelligence model, a feedback receiving means for receiving and analyzing feedback from the user, a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback, an emotion engine means for recognizing user emotions, and a means for adjusting business procedures based on the recognized user emotions. This makes it possible to provide appropriate instructions in real time according to the user's emotions during the business handover process, thereby improving productivity and business efficiency. Furthermore, the accuracy of the system can be continuously improved by utilizing user feedback and emotion data.

[0414] "Business know-how" refers to the knowledge and procedures required to carry out a specific business.

[0415] "User interface means" refers to the interface that a user uses to input business know-how into the system.

[0416] "Natural language processing means" refers to the techniques and processes used to parse meaning and context from text data.

[0417] "Artificial intelligence model means" refers to a machine learning model that learns from analyzed data and generates business procedures.

[0418] "Output interface means" refers to an interface for providing a business procedure to a user.

[0419] "Feedback receiving means" refers to a mechanism for receiving and analyzing feedback from a user.

[0420] "Retraining" refers to the process of retraining an AI model based on received feedback to improve its accuracy.

[0421] The "emotion engine means" refers to a mechanism for recognizing the user's emotions and responding or giving instructions according to those emotions.

[0422] The "means for adjusting the business procedure" refers to a mechanism for appropriately changing the method of providing the business procedure and the content thereof based on the recognized user's emotions.

[0423] The present invention relates to a system that uses a "Smart Factory Assistant" application that is installed on a factory robot. Hereinafter, an embodiment of the present invention will be specifically described.

[0424] Hardware and Software Configuration

[0425] The server uses the following hardware and software:

[0426] Hardware:

[0427] Factory robots

[0428] software:

[0429] Python libraries: transformers, EmotionRecognizer

[0430] Pre-trained AI models: BERT, GPT, etc.

[0431] System Operation

[0432] 1. Gathering business know-how:

[0433] A user inputs business know-how (e.g., "machine operating procedures") using a terminal installed in a factory robot. The input text data is collected via the user interface.

[0434] 2. Data analysis and AI model training:

[0435] The server analyzes the text data entered by the user using natural language processing. The analyzed data is extracted as business flow and important points. Based on this data, an artificial intelligence model (e.g., BERT) is used to train the system and understand specific procedures and points to note.

[0436] 3. Providing business procedures:

[0437] When a user requests a work procedure, the terminal installed on the factory robot displays instructions from the AI ​​model in real time, such as "Please set the material in the machine."

[0438] 4. Emotion recognition and regulation:

[0439] The emotion engine analyzes the user's voice and facial expression data to recognize the user's emotions in real time. Based on the recognized emotions, the system adjusts the work procedure. For example, if the user is confused, it provides detailed additional explanations.

[0440] 5. Feedback mechanism:

[0441] Users can input feedback into the system about any questions or problems they encounter while working. The server receives this feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to users from the next time onwards.

[0442] Specific examples

[0443] Example prompts for confused users:

[0444] "Press the red switch on the right. Then press and hold this button for three seconds."

[0445] Example prompt for angry users:

[0446] "Take a deep breath, and let's start again together."

[0447] The server integrates the above methods to provide a system for efficient and user-friendly task handover by factory robots. This system dynamically adjusts work procedures according to the user's emotions, improving work productivity and efficiency while reducing user stress.

[0448] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0449] Step 1:

[0450] The user inputs business know-how (e.g., "machine operating procedures") using a terminal installed on the factory robot. The input data is collected in text format and sent to the server. This allows the business know-how to be collected.

[0451] Input: Text data of business know-how

[0452] Output: Sending collected data

[0453] Step 2:

[0454] The server receives the business know-how sent by the user and analyzes it using natural language processing. Specifically, it tokenizes the text data and extracts important keywords and grammatical structures. This allows the business flow and key items to be identified.

[0455] Input: Text data of collected business know-how

[0456] Output: Parsed keywords and grammatical structures

[0457] Step 3:

[0458] The server trains an artificial intelligence model (e.g., BERT) on the analyzed business know-how. Specifically, the extracted keywords and grammatical structures are fed as input data to the AI ​​model, which then understands and infers business procedures. This allows the AI ​​model to learn the business know-how and store it as executable procedures.

[0459] Input: Parsed keywords and grammatical structures

[0460] Output: The trained AI model

[0461] Step 4:

[0462] When a user requests the provision of a business procedure, the device sends a request to the server. The server uses the trained AI model to generate instructions for the business procedure according to the user's request and sends them to the device, which displays them in real time.

[0463] Input: User's request to provide business procedures

[0464] Output: Generated work procedure instructions

[0465] Step 5:

[0466] The device collects the user's voice and facial expression data and recognizes the user's emotions in real time using an emotion engine means. The emotion engine analyzes changes in voice tone and facial expressions to identify the user's emotional state (e.g., confusion, anger).

[0467] Input: User's voice and facial expression data

[0468] Output: Identified user emotional state

[0469] Step 6:

[0470] The server adjusts the work procedure based on the user's recognized emotional state. For example, if the user is confused, it generates detailed additional explanations, and if the user is angry, it generates gentler explanations. This helps the user to perform the work appropriately.

[0471] Input: Identified emotional state of the user

[0472] Output: Coordinated work instructions

[0473] Step 7:

[0474] The user inputs feedback about any unclear points or problems that arise as they proceed with their work. The device sends this feedback to the server, which analyzes it and retrains the AI ​​model. This allows the device to provide more accurate and detailed instructions to the user next time.

[0475] Input: User feedback

[0476] Output: Retrained AI model

[0477] 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.

[0478] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0479] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0480] [Second embodiment]

[0481] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0482] 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.

[0483] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0484] 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.

[0485] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0486] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0487] 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.

[0488] 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.

[0489] 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 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.

[0490] 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.

[0491] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0492] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0493] The present invention is a tool for training an AI to learn business know-how and using the AI ​​to carry out business handover. Specific embodiments for carrying out the present invention will be described below.

[0494] Basic system configuration

[0495] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, and a re-learning means.

[0496] Explanation of program processing

[0497] 1. Gathering know-how

[0498] To gather business know-how, a user first logs into the system and inputs business procedures, such as "procedures for issuing invoices," in text format via the user interface. For example, the user sequentially inputs steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[0499] 2. Data analysis and learning

[0500] The server uses natural language processing to analyze the business know-how entered by the user. This analysis includes grammatical analysis of the text and keyword extraction. The analyzed data is organized into a data set showing the business flow and important points. The server then trains an artificial intelligence model on the analysis results. The model learns the relevance of each step and specific implementation methods, accumulating knowledge about business procedures.

[0501] 3. Providing business procedures

[0502] When the terminal provides work procedures to a new user (for example, a new employee), it guides them through the specific work procedures in real time based on the learning results from the server. When the user operates the system and clicks the "Start work procedures" button, the terminal displays the work procedures step by step based on the information learned by the AI. For example, instructions such as "Please enter the client's information into the management system" are displayed, along with detailed operating instructions and points to note.

[0503] Specific examples

[0504] Gathering know-how

[0505] The user inputs business know-how under the title "Invoice Issuance Procedure." Specifically, the following steps are described in detail:

[0506] 1. Enter client information into the management system.

[0507] 2. Calculate the amount to be claimed.

[0508] 3. Fill in the required information on the invoice form.

[0509] 4. Save the invoice as a PDF.

[0510] 5. Email it to your client.

[0511] Data analysis and learning

[0512] The server receives this data and analyzes it using natural language processing. For example, it extracts keywords and operational procedures related to each step and organizes them into a business flow. This data is then trained into an artificial intelligence model, allowing the AI ​​to understand specific steps and important points.

[0513] Providing business procedures

[0514] When new employee User B uses the system to learn how to issue an invoice, the device displays guidance based on the information learned by the AI. For example, when User B clicks the "Start invoice issuance procedure" button, the first step is to "Enter client information into the management system." Next, instructions such as "Calculate the invoice amount" and "Enter the information into the invoice format" are displayed in sequence, with specific support provided for each step.

[0515] Feedback Mechanism

[0516] If User B encounters any unclear points or problems while working, he or she inputs that information into the system as feedback. The server analyzes this feedback and retrains the AI ​​model. This improves the accuracy and reliability of the system so that future users do not encounter similar problems.

[0517] As described above, the present invention is a system that realizes efficient and accurate business handover through a series of processes including collection, analysis, learning, provision, and feedback of business know-how.

[0518] The processing flow will be explained below.

[0519] Step 1:

[0520] The user inputs business know-how. Specifically, after logging in to the system, the user inputs business procedures such as "invoice issuance procedures" in text format via the provided user interface. For example, the following information is input for each procedure:

[0521] 1. Enter client information into the management system.

[0522] 2. Calculate the amount to be claimed.

[0523] 3. Fill in the required information on the invoice form.

[0524] 4. Save the invoice as a PDF.

[0525] 5. Email it to your client.

[0526] Step 2:

[0527] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[0528] Step 3:

[0529] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[0530] Step 4:

[0531] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[0532] Step 5:

[0533] User B, who is new to the system, clicks the "Start business procedure" button. This causes the device to retrieve information learned from the AI ​​model and display sequential instructions in real time. For example, the device may display instructions such as "Enter client information into the management system," along with detailed operating instructions and important points to note.

[0534] Step 6:

[0535] If User B encounters any unclear points or problems in the system while following the procedures, he or she clicks the "Feedback" button and enters the details of the problem or question into the system. This feedback is sent to the system.

[0536] Step 7:

[0537] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[0538] Step 8:

[0539] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[0540] Through these steps, this system achieves efficient and accurate business handover through a series of processes: collecting, analyzing, learning, providing, and providing feedback on business know-how.

[0541] Example 1

[0542] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0543] Traditional methods of job handover are time-consuming and laborious, and often result in inaccurate information being conveyed or important procedures being overlooked. Another problem is the lack of an appropriate support system for new employees to efficiently learn their jobs. This leads to reduced work efficiency and an increase in mistakes and rework.

[0544] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0545] In this invention, the server includes a user interface means for inputting business knowledge, a natural language processing means for analyzing the business knowledge, and a machine learning model means for training the analyzed business knowledge. This makes it possible to efficiently and accurately collect, analyze, and train business knowledge. Furthermore, by including an opinion receiving means for receiving and analyzing opinions from users and a re-learning means for re-training the machine learning model based on the analyzed opinions, it is possible to continuously improve the system and increase its accuracy.

[0546] "Business knowledge" refers to procedures, know-how, related information, etc. required when performing business.

[0547] "User interface means" refers to the operation screen and interactive tools that allow users to input, edit, and view business knowledge.

[0548] "Natural language processing means" refers to algorithms and technologies for analyzing text data and understanding its meaning and structure.

[0549] "Machine learning model means" refers to a system that uses machine learning technology to learn patterns and knowledge from input data and make inferences and predictions.

[0550] "Output interface means" refers to devices and software for providing learning results to users and displaying business procedures.

[0551] "Opinion receiving means" refers to a system or function for receiving and processing feedback and opinions from users.

[0552] "Retraining methods" refers to techniques and processes used to retrain a machine learning model and improve its performance based on received opinions and feedback.

[0553] The present invention is a system for collecting, analyzing, learning, providing, and feeding back business knowledge, and specific embodiments thereof will be described.

[0554] Basic system configuration

[0555] This system is composed of a user interface means for inputting business knowledge, a natural language processing means for analyzing the input information, a machine learning model means for learning the analyzed information, an output interface means for providing the learning results, an opinion receiving means for receiving opinions from users, and a re-learning means.

[0556] Gathering know-how

[0557] The user first logs in to the system and inputs business knowledge in text format via the user interface. For example, under the title "Procedure for issuing invoices," the user might input steps such as "Enter client information into the management system," "Calculate the invoice amount," "Fill in the information into the invoice format," "Save as PDF," and "Send to the client by email."

[0558] Data analysis and learning

[0559] 1. The server receives the business knowledge input from the user. The received data is temporarily stored in a database (e.g., MySQL).

[0560] 2. Analyze the input business knowledge using a natural language processing engine (e.g., SpaCy) including legal procedures. The analysis includes grammatical analysis, keyword extraction, and sentence structuring.

[0561] For example, keywords such as "entering information" and "invoice format" are extracted from the sentence "entering information into an invoice format."

[0562] 3. The server organizes the business procedure data based on the analysis results and saves it as a dataset, which clearly shows the relationships and order of each procedure.

[0563] For example, the continuity between "Enter client information into the management system" and "Calculate the billing amount" is maintained.

[0564] 4. The server trains a machine learning model (e.g., GPT-4) on the data and accumulates the learned knowledge.

[0565] Providing business procedures

[0566] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The terminal guides the user through the business procedure in real time based on the learning results from the server.

[0567] Examples:

[0568] For example, when a user clicks the "Start Business Procedure" button, the following instruction appears on the screen: "Please enter the client's information into the management system." At this time, detailed operating instructions and important points are also provided.

[0569] Next, steps such as "Calculate the bill amount" and "Enter the information into the billing form" are displayed, with specific support information provided for each step.

[0570] Feedback Mechanism

[0571] If a user has a question or problem while going through a work procedure, they click the "Feedback" button and enter the problem. The server receives this feedback, analyzes it using a natural language processing engine, and saves it as a feedback dataset. The feedback data is then input into a machine learning model, and retraining improves the accuracy and reliability of the system.

[0572] Prompt Sentence Examples

[0573] "Please have the AI ​​learn the following business procedure. The title is 'Invoice Issuance Procedure'.

[0574] 1. Enter client information into the management system.

[0575] 2. Calculate the amount to be claimed.

[0576] 3. Fill in the required information on the invoice form.

[0577] 4. Save the invoice as a PDF.

[0578] 5. Email it to your client.

[0579] I would love to see AI learn these steps and provide a way to guide new users."

[0580] As described above, the present invention is a system that efficiently collects, analyzes, learns, provides, and improves business knowledge through feedback, thereby realizing efficient business handover.

[0581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0582] Step 1: Gathering know-how

[0583] A user logs into the system and inputs business knowledge. Specifically, the user enters business procedures such as "procedures for issuing invoices" in text format via the user interface. For example, the user might enter steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[0584] Input: Text data of business procedures

[0585] Output: User-entered business procedure data

[0586] Step 2: Receiving and temporarily storing data

[0587] The server receives the business procedure data sent by the user and temporarily stores this data in a database (e.g., MySQL).

[0588] Input: Business procedure data entered by the user

[0589] Output: Business procedure data stored in a database

[0590] Step 3: Natural Language Processing

[0591] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received business procedure data. This analysis involves grammatical analysis, keyword extraction, and sentence structuring. For example, from the sentence "filling in information on an invoice format," it extracts keywords such as "filling in information" and "invoice format."

[0592] Input: Business procedure data stored in the database

[0593] Output: Analyzed business procedure data (keywords and sentence structure)

[0594] Step 4: Organizing the dataset

[0595] The server organizes the business procedure data based on the analysis results and saves it as a dataset. This includes clarifying the relationship and order of each step. For example, it maintains the continuity between "Enter client information into the management system" and "Calculate the billing amount."

[0596] Input: Parsed business procedure data

[0597] Output: Organized business procedure dataset

[0598] Step 5: Training the AI ​​model

[0599] The server trains a machine learning model (e.g., GPT-4) using the organized dataset. The model learns the structure and relationships of business procedures and understands detailed support methods for each procedure.

[0600] Input: Organized business procedure dataset

[0601] Output: Trained AI model

[0602] Step 6: Providing business procedures and guidance

[0603] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The device retrieves guidance information from the trained AI model and guides the user through the business procedure in real time. For example, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[0604] Input: Business procedure start request from user

[0605] Output: Business procedure guide displayed on the terminal

[0606] Step 7: Provide support information

[0607] The device will display detailed support information and notes for each step, including detailed instructions such as "Please make sure the information you entered is accurate."

[0608] Input: Guide information for trained AI models

[0609] Output: Detailed supporting information displayed on the terminal

[0610] Step 8: Provide feedback

[0611] If a user encounters a question or problem while going through the work procedure, they can click the "Feedback" button to enter the problem, and this information will be sent to the system.

[0612] Input: User feedback information

[0613] Output: Feedback data sent to the server

[0614] Step 9: Receive and analyze feedback

[0615] The server receives the feedback sent by the user and analyzes it using a natural language processing engine. The analysis results are stored as a feedback dataset.

[0616] Input: Feedback data

[0617] Output: Parsed feedback dataset

[0618] Step 10: Retrain

[0619] The server inputs the feedback data into the machine learning model and performs retraining, which improves the accuracy and reliability of the model.

[0620] Input: Parsed feedback dataset

[0621] Output: Retrained AI model

[0622] Through the above series of processing steps, the present invention realizes accurate and efficient handover of business knowledge and enables continuous improvement of the system.

[0623] (Application example 1)

[0624] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0625] The present invention aims to provide a system that provides real-time guidance on work procedures at logistics centers, enabling even new or temporary staff to perform their work efficiently. Current work handover methods rely on understanding manuals or verbal explanations from person to person, which can lack accuracy and efficiency. Furthermore, there is a lack of mechanisms for improving work procedures based on feedback, which can lead to recurrence of similar problems. Therefore, there is a need for a system that uses AI to learn work know-how, efficiently guides staff through work procedures, and retrains the model through feedback.

[0626] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0627] In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means, a feedback receiving means, a relearning means, and a guide means for guiding business procedures in real time via a smart device. This enables efficient handover of business procedures at a logistics center and continuous improvement of business procedures based on feedback.

[0628] "Business know-how" refers to the knowledge, techniques, and procedures required to carry out a specific business task effectively and efficiently.

[0629] "User interface means" refers to an operation screen or input device that allows a user to input business know-how into the system.

[0630] "Natural language processing means" refers to technology for analyzing input text data and understanding and processing its content.

[0631] "Artificial intelligence model means" refers to algorithms or systems that learn analyzed business know-how and provide business procedures based on that knowledge.

[0632] "Output interface means" refers to a display screen or output device for providing the user with the business procedures learned by the artificial intelligence model.

[0633] "Feedback receiving means" refers to a system or device for receiving and analyzing feedback from a user.

[0634] "Retraining means" refers to a learning process for improving the accuracy of an artificial intelligence model based on analyzed feedback.

[0635] "Guide means" refers to a system or device that guides users through business procedures in real time via a smart device.

[0636] "Smart devices" refers to mobile information terminals with advanced functions, such as smartphones and smart glasses.

[0637] A "business procedure" refers to a series of steps or processes for accomplishing a particular task.

[0638] The present invention relates to a system for providing real-time guidance of work procedures at a logistics center using smart devices. Specific embodiments for carrying out the present invention will be described below.

[0639] Basic system configuration

[0640] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, a relearning means, and a guide means for guiding business procedures in real time via a smart device.

[0641] Hardware and software used

[0642] Hardware:

[0643] Smart devices (e.g., smart glasses, smartphones)

[0644] software:

[0645] Natural language processing libraries (e.g. Spacy)

[0646] Generative AI models (e.g., GPT-2, transformers library)

[0647] Data processing and calculation

[0648] 1. Gathering business know-how:

[0649] The server collects business know-how in text format through a user interface. This process also supports voice input using voice recognition. For example, detailed business procedures can be entered under a title such as "Incoming Inspection Procedure." This makes it easy for even new or temporary staff to input information.

[0650] 2. Data analysis and learning:

[0651] The server analyzes the collected business know-how using natural language processing and trains an AI model based on the results. For example, Spacy can be used to extract keywords and phrases related to business procedures, and a generative AI model (GPT-2) can then train on these.

[0652] 3. Providing business procedures:

[0653] The terminal (smart device) guides the work procedures in real time based on the learning results. When a new staff member starts a task, for example, by clicking the "Start work procedure" button, the specific steps learned by the AI ​​are displayed one by one. Instructions such as "Please scan the product barcode" and "Please check the quantity" are displayed.

[0654] 4. Feedback mechanism:

[0655] Users input any problems or questions they encounter as they work into the system as feedback. The server analyzes this feedback information and retrains the AI ​​model to improve the accuracy of future work procedures.

[0656] Examples of concrete examples and prompts

[0657] Examples:

[0658] The incoming goods inspection procedure guides users through steps such as "scanning the product barcode," "confirming the quantity," and "checking for defects." Users can check these steps in real time via their smart devices and carry out their work.

[0659] Example prompt sentence:

[0660] "When new staff members learn the receiving inspection procedures, AI can generate a step-by-step guide based on their operational know-how."

[0661] Generated text:

[0662] 1. Scan the product barcode.

[0663] 2. Check the quantity.

[0664] 3. Check for any defects.

[0665] 4. Once you have finished checking, move on to the next product.

[0666] In this way, the system of the present invention realizes efficient operations and accurate handover in a logistics center.

[0667] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0668] Step 1:

[0669] The user inputs business know-how

[0670] Users input specific operational procedures at the logistics center (e.g., incoming goods inspection procedures) in text format through a user interface. Voice recognition can also be used for input.

[0671] Input: Detailed text data of business procedures

[0672] Output: Text data of the entered business procedures

[0673] Step 2:

[0674] The server analyzes business know-how

[0675] The server analyzes the input business know-how using natural language processing tools (e.g., Spacy), performing grammatical analysis and extracting keywords to identify important points in the business procedures.

[0676] Input: Text data of business procedures entered by the user

[0677] Output: Analyzed keywords and grammatical structures

[0678] Step 3:

[0679] The server trains the AI ​​model

[0680] The server then trains an artificial intelligence model (e.g., GPT-2) on the analyzed business know-how data. The model then understands the relationships between business procedures and how to carry them out, and improves its reasoning capabilities based on this.

[0681] Input: Analyzed keywords and grammatical structure data

[0682] Output: Learned business procedure model

[0683] Step 4:

[0684] The terminal provides business procedures

[0685] The device (e.g., smart glasses or smartphone) displays the work procedure in real time based on the learning results. When the user presses the "Start work procedure" button, specific instructions (e.g., "Scan the product barcode") are displayed sequentially.

[0686] Input: Learned business procedure model

[0687] Output: Real-time operational instructions

[0688] Step 5:

[0689] User enters feedback

[0690] Users input feedback into the system about any problems or unclear points that arise while working.

[0691] Input: Feedback information on problems or unclear points that occurred during work

[0692] Output: Feedback text data

[0693] Step 6:

[0694] The server analyzes the feedback and re-learns

[0695] The server analyzes the feedback received from the user using natural language processing means and retrains the artificial intelligence model using retraining means, thereby improving the accuracy of the model and making subsequent guidance more effective.

[0696] Input: Text data of user feedback

[0697] Output: Improved business procedure model

[0698] The above are the specific processing steps of the program for the system that realizes the application example.

[0699] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0700] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[0701] The system consists of the following components:

[0702] 1. User interface means for inputting business know-how

[0703] 2. Natural language processing means for analyzing input business know-how

[0704] 3. AI modeling means for learning the analyzed business know-how

[0705] 4. Output interface means for providing business procedures using AI models

[0706] 5. Feedback receiving means for receiving and analyzing user feedback

[0707] 6. A retraining method to retrain the AI ​​model based on the analyzed feedback

[0708] 7. Emotion engine means for recognizing user emotions

[0709] 8. A method for adjusting work procedures based on user emotions recognized by an emotion engine

[0710] Explanation of program processing

[0711] 1. Gathering know-how

[0712] A user logs into the system and inputs details of business know-how using the user interface means. For example, a specific procedure such as "procedure for issuing an invoice" is input in text format.

[0713] 2. Data analysis and learning

[0714] The server analyzes the input business procedures using natural language processing. The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained into an AI model. The AI ​​model learns the relevance of procedures and specific execution methods, improving its reasoning capabilities.

[0715] 3. Emotion recognition and business procedure provision

[0716] When a user receives instructions for a task, the device displays the instructions in real time based on information learned from the AI ​​model. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This may include providing more detailed explanations or additional support information.

[0717] Specific examples

[0718] Gathering know-how

[0719] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[0720] 1. Enter client information into the management system.

[0721] 2. Calculate the amount to be claimed.

[0722] 3. Fill in the required information on the invoice form.

[0723] 4. Save the invoice as a PDF.

[0724] 5. Email it to your client.

[0725] Data analysis and learning

[0726] The server receives this data and analyzes it using natural language processing. As a result of the analysis, keywords and grammatical structures related to each step are extracted and structured as a business flow. This is then trained into an AI model, which then understands the specific steps and important points to note.

[0727] Providing business procedures and emotion recognition

[0728] When new employee User B uses the system to learn how to issue an invoice, the device uses information from the AI ​​model to guide the user through the process in real time. For example, instructions like "Please enter client information into the management system" are displayed. The emotion engine recognizes the user's emotions, and if the user is confused, it provides more detailed explanations and supplementary information to help the user carry out their work with confidence.

[0729] Feedback Mechanism

[0730] If User B encounters any questions or problems while working, he or she enters that information into the system as feedback. The server receives the feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to the user from the next time onwards.

[0731] As described above, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[0732] The processing flow will be explained below.

[0733] Step 1:

[0734] A user logs into the system and inputs business know-how. Specifically, the user uses a user interface to input business procedures such as "procedures for issuing invoices" in text format. For example, the user might input the following steps in order:

[0735] 1. Enter client information into the management system.

[0736] 2. Calculate the amount to be claimed.

[0737] 3. Fill in the required information on the invoice form.

[0738] 4. Save the invoice as a PDF.

[0739] 5. Email it to your client.

[0740] Step 2:

[0741] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[0742] Step 3:

[0743] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[0744] Step 4:

[0745] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[0746] Step 5:

[0747] When User B clicks the "Start Business Procedure" button, the device retrieves the information learned from the AI ​​model and displays the business procedure step by step. For example, the first step is to display the instruction "Enter the client's information into the management system," followed by detailed operating instructions and important points to note.

[0748] Step 6:

[0749] The device uses a camera and microphone to recognize the user's emotions, and the emotion engine analyzes facial expressions and voice. The emotion engine recognizes the user's emotions in real time and adjusts the instructions provided by the system based on that. For example, if the device recognizes that the user is confused, it will display more detailed explanations or support information.

[0750] Step 7:

[0751] User B provides feedback. If any questions or problems arise while working, the user clicks the "Feedback" button and enters the problem or question into the system. This feedback is sent to the system.

[0752] Step 8:

[0753] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[0754] Step 9:

[0755] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[0756] Through these steps, the system achieves efficient, accurate and considerate business handover through a series of processes including collection, analysis, learning, provision, feedback and emotion recognition of business know-how.

[0757] Example 2

[0758] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0759] Conventional job handover systems make it difficult to standardize and streamline job know-how, and lack support that takes users' feelings into consideration, causing inconvenience and stress for new entrants. They also lack a mechanism for effectively utilizing user feedback to improve the system. Therefore, a more efficient and user-friendly job handover system is needed.

[0760] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for inputting business know-how, an analysis means for analyzing the business know-how, an intelligence model means for learning the analyzed business know-how, an output means for providing business procedures using the intelligence model, a recognition means for recognizing a user's emotion, an adjustment means for adjusting the business procedures based on the recognized emotion, a receiving means for receiving and analyzing feedback from the user, and a re-learning means for re-learning the intelligence model based on the analyzed feedback. This makes it possible to efficiently take over business and provide support that takes into consideration the user's emotion.

[0761] "Input means" refers to a device or interface that allows a user to input data such as business know-how into the system.

[0762] "Analysis means" refers to a device or function for processing and analyzing input data to extract necessary information.

[0763] The "intelligent model means" is a model that uses artificial intelligence to learn based on analyzed data and accumulate knowledge that is useful for providing business procedures.

[0764] "Output means" refers to a device or interface for displaying or providing the business procedure provided by the intelligent model to the user.

[0765] "Recognition means" refers to a device or function for recognizing the user's emotions or state.

[0766] "Adjustment means" is a device or function for adjusting business procedures or response methods based on recognized emotions.

[0767] "Receiving means" refers to a device or interface for receiving feedback from a user and incorporating it into the system.

[0768] A "relearning means" is a device or function that causes the intelligence model to be retrained based on the received feedback.

[0769] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[0770] The system consists of the following components:

[0771] 1. Input method for inputting business know-how

[0772] 2. Analysis method for analyzing input business know-how

[0773] 3. Intelligent model means for learning the analyzed business know-how

[0774] 4. Output means for providing business procedures using intelligent models

[0775] 5. Recognition method for recognizing user emotions

[0776] 6. Adjustment measures to adjust work procedures based on perceived emotions

[0777] 7. Receiving means for receiving and analyzing user feedback

[0778] 8. A retraining method for retraining the intelligence model based on the analyzed feedback

[0779] Specifically, the system operates in the following manner.

[0780] Gathering know-how

[0781] A user logs into the system and inputs details of business know-how using an input device. For example, a specific procedure such as "procedures for issuing invoices" is input in text format. This know-how is saved in a database on the server.

[0782] Data analysis and learning

[0783] The server analyzes the input business procedures using an analysis tool (e.g., SpaCy or NLTK). The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained by an intelligent model tool (e.g., Hugging Face's Transformers). The intelligent model learns the relationships between procedures and specific execution methods, improving its reasoning capabilities.

[0784] Emotion recognition and business procedure provision

[0785] When a user receives instructions for a task, the device displays them in real time based on information learned from the intelligent model. The recognition means analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This could include providing more detailed explanations or additional support information.

[0786] Gathering feedback and relearning

[0787] If a user encounters any questions or problems while working, they can enter that information as feedback into the system. The server receives the feedback, analyzes it using analytical means, and retrains the intelligence model. This allows the server to provide more accurate and detailed instructions to the user from the next time onwards.

[0788] Specific examples

[0789] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[0790] 1. Enter client information into the management system.

[0791] 2. Calculate the amount to be claimed.

[0792] 3. Fill in the required information on the invoice form.

[0793] 4. Save the invoice as a PDF.

[0794] 5. Email it to your client.

[0795] Prompt Sentence Examples

[0796] Enter client information into the management system.

[0797] Calculate the amount to be charged.

[0798] Fill in the required information on the invoice form.

[0799] Save the invoice in PDF format.

[0800] Email it to your client.

[0801] In this way, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[0802] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0803] Step 1: Gathering know-how

[0804] A user logs in to the system. After entering the correct login information and passing the authentication process, the user is redirected to the business know-how input screen. Here, the user enters specific business procedures (for example, "procedures for issuing invoices") in text format. This input data is sent to the server and saved in the database.

[0805] input:

[0806] User login information (ID and password)

[0807] Business know-how entered in text format

[0808] output:

[0809] Business know-how stored in a database

[0810] Operation:

[0811] User interface prompts for data entry and saving

[0812] Step 2: Analyze and train the data

[0813] The server analyzes the stored business procedures using an analysis means. The server uses natural language processing means (e.g., SpaCy or NLTK) to tokenize the input text data and extract important keywords and grammatical structures. This structures the business flow and prepares it as data for the next learning by the intelligence model means.

[0814] input:

[0815] Business know-how stored in a database

[0816] output:

[0817] Structured business flow data

[0818] Operation:

[0819] Executing natural language processing algorithms and storing results

[0820] Step 3: Training the Intelligence Model

[0821] The server trains the analyzed data using an intelligent model (for example, Hugging Face's Transformers). The server calls the intelligent model and trains it on the data, allowing it to understand the relevance of business procedures and how to execute them. Once training is complete, the model is ready to be used to provide business procedures.

[0822] input:

[0823] Structured business flow data

[0824] output:

[0825] An intelligent model that understands business procedures

[0826] Operation:

[0827] Execution of the learning process of the intelligent model and notification of its completion

[0828] Step 4: Provide business procedures

[0829] Based on the information learned from the intelligent model, the device provides users with real-time instructions on how to proceed. Specifically, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[0830] input:

[0831] Intelligence Model

[0832] output:

[0833] Real-time operational procedures

[0834] Operation:

[0835] Displaying instruction messages on the user screen

[0836] Step 5: Emotion Recognition

[0837] The device's recognition means analyzes the user's facial expressions and voice to recognize their emotions. The device identifies the user's emotions based on the recognized emotion data. For example, if the user is confused, the system will display additional explanations or support.

[0838] input:

[0839] User facial expression and voice data

[0840] output:

[0841] Recognized emotion data

[0842] Operation:

[0843] Data collection and analysis using cameras and microphones

[0844] Step 6: Adjust your work procedures based on emotions

[0845] The device can then adjust its work procedures based on the recognized emotion data, for example, providing more detailed explanations or displaying additional support information if the user is confused.

[0846] input:

[0847] Recognized emotion data

[0848] output:

[0849] Adjusted operating procedures

[0850] Operation:

[0851] Displaying additional instruction messages on the user screen

[0852] Step 7: Gather feedback

[0853] The user inputs feedback about the work procedure into the system. The user writes down any problems or questions about the work in progress and sends them to the server via the input means.

[0854] input:

[0855] User feedback (text format)

[0856] output:

[0857] Feedback stored in the database

[0858] Operation:

[0859] User interface prompts for feedback entry and saving

[0860] Step 8: Analyze feedback and retrain

[0861] The server analyzes the received feedback and retrains the intelligence model means. The server analyzes the feedback using natural language processing means and extracts areas for improvement and problems. New analysis data is supplied to the intelligence model and retraining is performed.

[0862] input:

[0863] Feedback stored in the database

[0864] output:

[0865] Improved Intelligence Model

[0866] Operation:

[0867] Conducting feedback analysis and retraining process of the intelligence model

[0868] Through the above steps, this system realizes task handover that takes emotions into consideration, aiming to improve work efficiency and user satisfaction.

[0869] (Application example 2)

[0870] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0871] Conventional task handover systems lack the ability to effectively convey task know-how and the ability to appropriately adjust instructions based on the user's emotional state. This often leaves new operators feeling confused and frustrated, leading to reduced productivity and work efficiency. Furthermore, there is a lack of effective means for utilizing user feedback to improve the system's accuracy, which delays improvements to the task handover process.

[0872] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means for providing business procedures using the artificial intelligence model, a feedback receiving means for receiving and analyzing feedback from the user, a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback, an emotion engine means for recognizing user emotions, and a means for adjusting business procedures based on the recognized user emotions. This makes it possible to provide appropriate instructions in real time according to the user's emotions during the business handover process, thereby improving productivity and business efficiency. Furthermore, the accuracy of the system can be continuously improved by utilizing user feedback and emotion data.

[0873] "Business know-how" refers to the knowledge and procedures required to carry out a specific business.

[0874] "User interface means" refers to the interface that a user uses to input business know-how into the system.

[0875] "Natural language processing means" refers to the techniques and processes used to parse meaning and context from text data.

[0876] "Artificial intelligence model means" refers to a machine learning model that learns from analyzed data and generates business procedures.

[0877] "Output interface means" refers to an interface for providing a business procedure to a user.

[0878] "Feedback receiving means" refers to a mechanism for receiving and analyzing feedback from a user.

[0879] "Retraining" refers to the process of retraining an AI model based on received feedback to improve its accuracy.

[0880] The "emotion engine means" refers to a mechanism for recognizing the user's emotions and responding or giving instructions according to those emotions.

[0881] The "means for adjusting the business procedure" refers to a mechanism for appropriately changing the method of providing the business procedure and the content thereof based on the recognized user's emotions.

[0882] The present invention relates to a system that uses a "Smart Factory Assistant" application that is installed on a factory robot. Hereinafter, an embodiment of the present invention will be specifically described.

[0883] Hardware and Software Configuration

[0884] The server uses the following hardware and software:

[0885] Hardware:

[0886] Factory robots

[0887] software:

[0888] Python libraries: transformers, EmotionRecognizer

[0889] Pre-trained AI models: BERT, GPT, etc.

[0890] System Operation

[0891] 1. Gathering business know-how:

[0892] A user inputs business know-how (e.g., "machine operating procedures") using a terminal installed in a factory robot. The input text data is collected via the user interface.

[0893] 2. Data analysis and AI model training:

[0894] The server analyzes the text data entered by the user using natural language processing. The analyzed data is extracted as business flow and important points. Based on this data, an artificial intelligence model (e.g., BERT) is used to train the system and understand specific procedures and points to note.

[0895] 3. Providing business procedures:

[0896] When a user requests a work procedure, the terminal installed on the factory robot displays instructions from the AI ​​model in real time, such as "Please set the material in the machine."

[0897] 4. Emotion recognition and regulation:

[0898] The emotion engine analyzes the user's voice and facial expression data to recognize the user's emotions in real time. Based on the recognized emotions, the system adjusts the work procedure. For example, if the user is confused, it provides detailed additional explanations.

[0899] 5. Feedback mechanism:

[0900] Users can input feedback into the system about any questions or problems they encounter while working. The server receives this feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to users from the next time onwards.

[0901] Specific examples

[0902] Example prompts for confused users:

[0903] "Press the red switch on the right. Then press and hold this button for three seconds."

[0904] Example prompt for angry users:

[0905] "Take a deep breath, and let's start again together."

[0906] The server integrates the above methods to provide a system for efficient and user-friendly task handover by factory robots. This system dynamically adjusts work procedures according to the user's emotions, improving work productivity and efficiency while reducing user stress.

[0907] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0908] Step 1:

[0909] The user inputs business know-how (e.g., "machine operating procedures") using a terminal installed on the factory robot. The input data is collected in text format and sent to the server. This allows the business know-how to be collected.

[0910] Input: Text data of business know-how

[0911] Output: Sending collected data

[0912] Step 2:

[0913] The server receives the business know-how sent by the user and analyzes it using natural language processing. Specifically, it tokenizes the text data and extracts important keywords and grammatical structures. This allows the business flow and key items to be identified.

[0914] Input: Text data of collected business know-how

[0915] Output: Parsed keywords and grammatical structures

[0916] Step 3:

[0917] The server trains an artificial intelligence model (e.g., BERT) on the analyzed business know-how. Specifically, the extracted keywords and grammatical structures are fed as input data to the AI ​​model, which then understands and infers business procedures. This allows the AI ​​model to learn the business know-how and store it as executable procedures.

[0918] Input: Parsed keywords and grammatical structures

[0919] Output: The trained AI model

[0920] Step 4:

[0921] When a user requests the provision of a business procedure, the device sends a request to the server. The server uses the trained AI model to generate instructions for the business procedure according to the user's request and sends them to the device, which displays them in real time.

[0922] Input: User's request to provide business procedures

[0923] Output: Generated work procedure instructions

[0924] Step 5:

[0925] The device collects the user's voice and facial expression data and recognizes the user's emotions in real time using an emotion engine means. The emotion engine analyzes changes in voice tone and facial expressions to identify the user's emotional state (e.g., confusion, anger).

[0926] Input: User's voice and facial expression data

[0927] Output: Identified user emotional state

[0928] Step 6:

[0929] The server adjusts the work procedure based on the user's recognized emotional state. For example, if the user is confused, it generates detailed additional explanations, and if the user is angry, it generates gentler explanations. This helps the user to perform the work appropriately.

[0930] Input: Identified emotional state of the user

[0931] Output: Coordinated work instructions

[0932] Step 7:

[0933] The user inputs feedback about any unclear points or problems that arise as they proceed with their work. The device sends this feedback to the server, which analyzes it and retrains the AI ​​model. This allows the device to provide more accurate and detailed instructions to the user next time.

[0934] Input: User feedback

[0935] Output: Retrained AI model

[0936] 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.

[0937] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0938] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0939] [Third embodiment]

[0940] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0941] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0942] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[0943] 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.

[0944] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0945] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0946] 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.

[0947] 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.

[0948] 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 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.

[0949] 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.

[0950] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0951] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0952] The present invention is a tool for training an AI to learn business know-how and using the AI ​​to carry out business handover. Specific embodiments for carrying out the present invention will be described below.

[0953] Basic system configuration

[0954] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, and a re-learning means.

[0955] Explanation of program processing

[0956] 1. Gathering know-how

[0957] To gather business know-how, a user first logs into the system and inputs business procedures, such as "procedures for issuing invoices," in text format via the user interface. For example, the user sequentially inputs steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[0958] 2. Data analysis and learning

[0959] The server uses natural language processing to analyze the business know-how entered by the user. This analysis includes grammatical analysis of the text and keyword extraction. The analyzed data is organized into a data set showing the business flow and important points. The server then trains an artificial intelligence model on the analysis results. The model learns the relevance of each step and specific implementation methods, accumulating knowledge about business procedures.

[0960] 3. Providing business procedures

[0961] When the terminal provides work procedures to a new user (for example, a new employee), it guides them through the specific work procedures in real time based on the learning results from the server. When the user operates the system and clicks the "Start work procedures" button, the terminal displays the work procedures step by step based on the information learned by the AI. For example, instructions such as "Please enter the client's information into the management system" are displayed, along with detailed operating instructions and points to note.

[0962] Specific examples

[0963] Gathering know-how

[0964] The user inputs business know-how under the title "Invoice Issuance Procedure." Specifically, the following steps are described in detail:

[0965] 1. Enter client information into the management system.

[0966] 2. Calculate the amount to be claimed.

[0967] 3. Fill in the required information on the invoice form.

[0968] 4. Save the invoice as a PDF.

[0969] 5. Email it to your client.

[0970] Data analysis and learning

[0971] The server receives this data and analyzes it using natural language processing. For example, it extracts keywords and operational procedures related to each step and organizes them into a business flow. This data is then trained into an artificial intelligence model, allowing the AI ​​to understand specific steps and important points.

[0972] Providing business procedures

[0973] When new employee User B uses the system to learn how to issue an invoice, the device displays guidance based on the information learned by the AI. For example, when User B clicks the "Start invoice issuance procedure" button, the first step is to "Enter client information into the management system." Next, instructions such as "Calculate the invoice amount" and "Enter the information into the invoice format" are displayed in sequence, with specific support provided for each step.

[0974] Feedback Mechanism

[0975] If User B encounters any unclear points or problems while working, he or she inputs that information into the system as feedback. The server analyzes this feedback and retrains the AI ​​model. This improves the accuracy and reliability of the system so that future users do not encounter similar problems.

[0976] As described above, the present invention is a system that realizes efficient and accurate business handover through a series of processes including collection, analysis, learning, provision, and feedback of business know-how.

[0977] The processing flow will be explained below.

[0978] Step 1:

[0979] The user inputs business know-how. Specifically, after logging in to the system, the user inputs business procedures such as "invoice issuance procedures" in text format via the provided user interface. For example, the following information is input for each procedure:

[0980] 1. Enter client information into the management system.

[0981] 2. Calculate the amount to be claimed.

[0982] 3. Fill in the required information on the invoice form.

[0983] 4. Save the invoice as a PDF.

[0984] 5. Email it to your client.

[0985] Step 2:

[0986] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[0987] Step 3:

[0988] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[0989] Step 4:

[0990] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[0991] Step 5:

[0992] User B, who is new to the system, clicks the "Start business procedure" button. This causes the device to retrieve information learned from the AI ​​model and display sequential instructions in real time. For example, the device may display instructions such as "Enter client information into the management system," along with detailed operating instructions and important points to note.

[0993] Step 6:

[0994] If User B encounters any unclear points or problems in the system while following the procedures, he or she clicks the "Feedback" button and enters the details of the problem or question into the system. This feedback is sent to the system.

[0995] Step 7:

[0996] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[0997] Step 8:

[0998] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[0999] Through these steps, this system achieves efficient and accurate business handover through a series of processes: collecting, analyzing, learning, providing, and providing feedback on business know-how.

[1000] Example 1

[1001] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1002] Traditional methods of job handover are time-consuming and laborious, and often result in inaccurate information being conveyed or important procedures being overlooked. Another problem is the lack of an appropriate support system for new employees to efficiently learn their jobs. This leads to reduced work efficiency and an increase in mistakes and rework.

[1003] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1004] In this invention, the server includes a user interface means for inputting business knowledge, a natural language processing means for analyzing the business knowledge, and a machine learning model means for training the analyzed business knowledge. This makes it possible to efficiently and accurately collect, analyze, and train business knowledge. Furthermore, by including an opinion receiving means for receiving and analyzing opinions from users and a re-learning means for re-training the machine learning model based on the analyzed opinions, it is possible to continuously improve the system and increase its accuracy.

[1005] "Business knowledge" refers to procedures, know-how, related information, etc. required when performing business.

[1006] "User interface means" refers to the operation screen and interactive tools that allow users to input, edit, and view business knowledge.

[1007] "Natural language processing means" refers to algorithms and technologies for analyzing text data and understanding its meaning and structure.

[1008] "Machine learning model means" refers to a system that uses machine learning technology to learn patterns and knowledge from input data and make inferences and predictions.

[1009] "Output interface means" refers to devices and software for providing learning results to users and displaying business procedures.

[1010] "Opinion receiving means" refers to a system or function for receiving and processing feedback and opinions from users.

[1011] "Retraining methods" refers to techniques and processes used to retrain a machine learning model and improve its performance based on received opinions and feedback.

[1012] The present invention is a system for collecting, analyzing, learning, providing, and feeding back business knowledge, and specific embodiments thereof will be described.

[1013] Basic system configuration

[1014] This system is composed of a user interface means for inputting business knowledge, a natural language processing means for analyzing the input information, a machine learning model means for learning the analyzed information, an output interface means for providing the learning results, an opinion receiving means for receiving opinions from users, and a re-learning means.

[1015] Gathering know-how

[1016] The user first logs in to the system and inputs business knowledge in text format via the user interface. For example, under the title "Procedure for issuing invoices," the user might input steps such as "Enter client information into the management system," "Calculate the invoice amount," "Fill in the information into the invoice format," "Save as PDF," and "Send to the client by email."

[1017] Data analysis and learning

[1018] 1. The server receives the business knowledge input from the user. The received data is temporarily stored in a database (e.g., MySQL).

[1019] 2. Analyze the input business knowledge using a natural language processing engine (e.g., SpaCy) including legal procedures. The analysis includes grammatical analysis, keyword extraction, and sentence structuring.

[1020] For example, keywords such as "entering information" and "invoice format" are extracted from the sentence "entering information into an invoice format."

[1021] 3. The server organizes the business procedure data based on the analysis results and saves it as a dataset, which clearly shows the relationships and order of each procedure.

[1022] For example, the continuity between "Enter client information into the management system" and "Calculate the billing amount" is maintained.

[1023] 4. The server trains a machine learning model (e.g., GPT-4) on the data and accumulates the learned knowledge.

[1024] Providing business procedures

[1025] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The terminal guides the user through the business procedure in real time based on the learning results from the server.

[1026] Examples:

[1027] For example, when a user clicks the "Start Business Procedure" button, the following instruction appears on the screen: "Please enter the client's information into the management system." At this time, detailed operating instructions and important points are also provided.

[1028] Next, steps such as "Calculate the bill amount" and "Enter the information into the billing form" are displayed, with specific support information provided for each step.

[1029] Feedback Mechanism

[1030] If a user has a question or problem while going through a work procedure, they click the "Feedback" button and enter the problem. The server receives this feedback, analyzes it using a natural language processing engine, and saves it as a feedback dataset. The feedback data is then input into a machine learning model, and retraining improves the accuracy and reliability of the system.

[1031] Prompt Sentence Examples

[1032] "Please have the AI ​​learn the following business procedure. The title is 'Invoice Issuance Procedure'.

[1033] 1. Enter client information into the management system.

[1034] 2. Calculate the amount to be claimed.

[1035] 3. Fill in the required information on the invoice form.

[1036] 4. Save the invoice as a PDF.

[1037] 5. Email it to your client.

[1038] I would love to see AI learn these steps and provide a way to guide new users."

[1039] As described above, the present invention is a system that efficiently collects, analyzes, learns, provides, and improves business knowledge through feedback, thereby realizing efficient business handover.

[1040] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1041] Step 1: Gathering know-how

[1042] A user logs into the system and inputs business knowledge. Specifically, the user enters business procedures such as "procedures for issuing invoices" in text format via the user interface. For example, the user might enter steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[1043] Input: Text data of business procedures

[1044] Output: User-entered business procedure data

[1045] Step 2: Receiving and temporarily storing data

[1046] The server receives the business procedure data sent by the user and temporarily stores this data in a database (e.g., MySQL).

[1047] Input: Business procedure data entered by the user

[1048] Output: Business procedure data stored in a database

[1049] Step 3: Natural Language Processing

[1050] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received business procedure data. This analysis involves grammatical analysis, keyword extraction, and sentence structuring. For example, from the sentence "filling in information on an invoice format," it extracts keywords such as "filling in information" and "invoice format."

[1051] Input: Business procedure data stored in the database

[1052] Output: Analyzed business procedure data (keywords and sentence structure)

[1053] Step 4: Organizing the dataset

[1054] The server organizes the business procedure data based on the analysis results and saves it as a dataset. This includes clarifying the relationship and order of each step. For example, it maintains the continuity between "Enter client information into the management system" and "Calculate the billing amount."

[1055] Input: Parsed business procedure data

[1056] Output: Organized business procedure dataset

[1057] Step 5: Training the AI ​​model

[1058] The server trains a machine learning model (e.g., GPT-4) using the organized dataset. The model learns the structure and relationships of business procedures and understands detailed support methods for each procedure.

[1059] Input: Organized business procedure dataset

[1060] Output: Trained AI model

[1061] Step 6: Providing business procedures and guidance

[1062] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The device retrieves guidance information from the trained AI model and guides the user through the business procedure in real time. For example, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[1063] Input: Business procedure start request from user

[1064] Output: Business procedure guide displayed on the terminal

[1065] Step 7: Provide support information

[1066] The device will display detailed support information and notes for each step, including detailed instructions such as "Please make sure the information you entered is accurate."

[1067] Input: Guide information for trained AI models

[1068] Output: Detailed supporting information displayed on the terminal

[1069] Step 8: Provide feedback

[1070] If a user encounters a question or problem while going through the work procedure, they can click the "Feedback" button to enter the problem, and this information will be sent to the system.

[1071] Input: User feedback information

[1072] Output: Feedback data sent to the server

[1073] Step 9: Receive and analyze feedback

[1074] The server receives the feedback sent by the user and analyzes it using a natural language processing engine. The analysis results are stored as a feedback dataset.

[1075] Input: Feedback data

[1076] Output: Parsed feedback dataset

[1077] Step 10: Retrain

[1078] The server inputs the feedback data into the machine learning model and performs retraining, which improves the accuracy and reliability of the model.

[1079] Input: Parsed feedback dataset

[1080] Output: Retrained AI model

[1081] Through the above series of processing steps, the present invention realizes accurate and efficient handover of business knowledge and enables continuous improvement of the system.

[1082] (Application example 1)

[1083] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1084] The present invention aims to provide a system that provides real-time guidance on work procedures at logistics centers, enabling even new or temporary staff to perform their work efficiently. Current work handover methods rely on understanding manuals or verbal explanations from person to person, which can lack accuracy and efficiency. Furthermore, there is a lack of mechanisms for improving work procedures based on feedback, which can lead to recurrence of similar problems. Therefore, there is a need for a system that uses AI to learn work know-how, efficiently guides staff through work procedures, and retrains the model through feedback.

[1085] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1086] In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means, a feedback receiving means, a relearning means, and a guide means for guiding business procedures in real time via a smart device. This enables efficient handover of business procedures at a logistics center and continuous improvement of business procedures based on feedback.

[1087] "Business know-how" refers to the knowledge, techniques, and procedures required to carry out a specific business task effectively and efficiently.

[1088] "User interface means" refers to an operation screen or input device that allows a user to input business know-how into the system.

[1089] "Natural language processing means" refers to technology for analyzing input text data and understanding and processing its content.

[1090] "Artificial intelligence model means" refers to algorithms or systems that learn analyzed business know-how and provide business procedures based on that knowledge.

[1091] "Output interface means" refers to a display screen or output device for providing the user with the business procedures learned by the artificial intelligence model.

[1092] "Feedback receiving means" refers to a system or device for receiving and analyzing feedback from a user.

[1093] "Retraining means" refers to a learning process for improving the accuracy of an artificial intelligence model based on analyzed feedback.

[1094] "Guide means" refers to a system or device that guides users through business procedures in real time via a smart device.

[1095] "Smart devices" refers to mobile information terminals with advanced functions, such as smartphones and smart glasses.

[1096] A "business procedure" refers to a series of steps or processes for accomplishing a particular task.

[1097] The present invention relates to a system for providing real-time guidance of work procedures at a logistics center using smart devices. Specific embodiments for carrying out the present invention will be described below.

[1098] Basic system configuration

[1099] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, a relearning means, and a guide means for guiding business procedures in real time via a smart device.

[1100] Hardware and software used

[1101] Hardware:

[1102] Smart devices (e.g., smart glasses, smartphones)

[1103] software:

[1104] Natural language processing libraries (e.g. Spacy)

[1105] Generative AI models (e.g., GPT-2, transformers library)

[1106] Data processing and calculation

[1107] 1. Gathering business know-how:

[1108] The server collects business know-how in text format through a user interface. This process also supports voice input using voice recognition. For example, detailed business procedures can be entered under a title such as "Incoming Inspection Procedure." This makes it easy for even new or temporary staff to input information.

[1109] 2. Data analysis and learning:

[1110] The server analyzes the collected business know-how using natural language processing and trains an AI model based on the results. For example, Spacy can be used to extract keywords and phrases related to business procedures, and a generative AI model (GPT-2) can then train on these.

[1111] 3. Providing business procedures:

[1112] The terminal (smart device) guides the work procedures in real time based on the learning results. When a new staff member starts a task, for example, by clicking the "Start work procedure" button, the specific steps learned by the AI ​​are displayed one by one. Instructions such as "Please scan the product barcode" and "Please check the quantity" are displayed.

[1113] 4. Feedback mechanism:

[1114] Users input any problems or questions they encounter as they work into the system as feedback. The server analyzes this feedback information and retrains the AI ​​model to improve the accuracy of future work procedures.

[1115] Examples of concrete examples and prompts

[1116] Examples:

[1117] The incoming goods inspection procedure guides users through steps such as "scanning the product barcode," "confirming the quantity," and "checking for defects." Users can check these steps in real time via their smart devices and carry out their work.

[1118] Example prompt sentence:

[1119] "When new staff members learn the receiving inspection procedures, AI can generate a step-by-step guide based on their operational know-how."

[1120] Generated text:

[1121] 1. Scan the product barcode.

[1122] 2. Check the quantity.

[1123] 3. Check for any defects.

[1124] 4. Once you have finished checking, move on to the next product.

[1125] In this way, the system of the present invention realizes efficient operations and accurate handover in a logistics center.

[1126] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1127] Step 1:

[1128] The user inputs business know-how

[1129] Users input specific operational procedures at the logistics center (e.g., incoming goods inspection procedures) in text format through a user interface. Voice recognition can also be used for input.

[1130] Input: Detailed text data of business procedures

[1131] Output: Text data of the entered business procedures

[1132] Step 2:

[1133] The server analyzes business know-how

[1134] The server analyzes the input business know-how using natural language processing tools (e.g., Spacy), performing grammatical analysis and extracting keywords to identify important points in the business procedures.

[1135] Input: Text data of business procedures entered by the user

[1136] Output: Analyzed keywords and grammatical structures

[1137] Step 3:

[1138] The server trains the AI ​​model

[1139] The server then trains an artificial intelligence model (e.g., GPT-2) on the analyzed business know-how data. The model then understands the relationships between business procedures and how to carry them out, and improves its reasoning capabilities based on this.

[1140] Input: Analyzed keywords and grammatical structure data

[1141] Output: Learned business procedure model

[1142] Step 4:

[1143] The terminal provides business procedures

[1144] The device (e.g., smart glasses or smartphone) displays the work procedure in real time based on the learning results. When the user presses the "Start work procedure" button, specific instructions (e.g., "Scan the product barcode") are displayed sequentially.

[1145] Input: Learned business procedure model

[1146] Output: Real-time operational instructions

[1147] Step 5:

[1148] User enters feedback

[1149] Users input feedback into the system about any problems or unclear points that arise while working.

[1150] Input: Feedback information on problems or unclear points that occurred during work

[1151] Output: Feedback text data

[1152] Step 6:

[1153] The server analyzes the feedback and re-learns

[1154] The server analyzes the feedback received from the user using natural language processing means and retrains the artificial intelligence model using retraining means, thereby improving the accuracy of the model and making subsequent guidance more effective.

[1155] Input: Text data of user feedback

[1156] Output: Improved business procedure model

[1157] The above are the specific processing steps of the program for the system that realizes the application example.

[1158] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1159] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[1160] The system consists of the following components:

[1161] 1. User interface means for inputting business know-how

[1162] 2. Natural language processing means for analyzing input business know-how

[1163] 3. AI modeling means for learning the analyzed business know-how

[1164] 4. Output interface means for providing business procedures using AI models

[1165] 5. Feedback receiving means for receiving and analyzing user feedback

[1166] 6. A retraining method to retrain the AI ​​model based on the analyzed feedback

[1167] 7. Emotion engine means for recognizing user emotions

[1168] 8. A method for adjusting work procedures based on user emotions recognized by an emotion engine

[1169] Explanation of program processing

[1170] 1. Gathering know-how

[1171] A user logs into the system and inputs details of business know-how using the user interface means. For example, a specific procedure such as "procedure for issuing an invoice" is input in text format.

[1172] 2. Data analysis and learning

[1173] The server analyzes the input business procedures using natural language processing. The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained into an AI model. The AI ​​model learns the relevance of procedures and specific execution methods, improving its reasoning capabilities.

[1174] 3. Emotion recognition and business procedure provision

[1175] When a user receives instructions for a task, the device displays the instructions in real time based on information learned from the AI ​​model. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This may include providing more detailed explanations or additional support information.

[1176] Specific examples

[1177] Gathering know-how

[1178] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[1179] 1. Enter client information into the management system.

[1180] 2. Calculate the amount to be claimed.

[1181] 3. Fill in the required information on the invoice form.

[1182] 4. Save the invoice as a PDF.

[1183] 5. Email it to your client.

[1184] Data analysis and learning

[1185] The server receives this data and analyzes it using natural language processing. As a result of the analysis, keywords and grammatical structures related to each step are extracted and structured as a business flow. This is then trained into an AI model, which then understands the specific steps and important points to note.

[1186] Providing business procedures and emotion recognition

[1187] When new employee User B uses the system to learn how to issue an invoice, the device uses information from the AI ​​model to guide the user through the process in real time. For example, instructions like "Please enter client information into the management system" are displayed. The emotion engine recognizes the user's emotions, and if the user is confused, it provides more detailed explanations and supplementary information to help the user carry out their work with confidence.

[1188] Feedback Mechanism

[1189] If User B encounters any questions or problems while working, he or she enters that information into the system as feedback. The server receives the feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to the user from the next time onwards.

[1190] As described above, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] A user logs into the system and inputs business know-how. Specifically, the user uses a user interface to input business procedures such as "procedures for issuing invoices" in text format. For example, the user might input the following steps in order:

[1194] 1. Enter client information into the management system.

[1195] 2. Calculate the amount to be claimed.

[1196] 3. Fill in the required information on the invoice form.

[1197] 4. Save the invoice as a PDF.

[1198] 5. Email it to your client.

[1199] Step 2:

[1200] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[1201] Step 3:

[1202] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[1203] Step 4:

[1204] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[1205] Step 5:

[1206] When User B clicks the "Start Business Procedure" button, the device retrieves the information learned from the AI ​​model and displays the business procedure step by step. For example, the first step is to display the instruction "Enter the client's information into the management system," followed by detailed operating instructions and important points to note.

[1207] Step 6:

[1208] The device uses a camera and microphone to recognize the user's emotions, and the emotion engine analyzes facial expressions and voice. The emotion engine recognizes the user's emotions in real time and adjusts the instructions provided by the system based on that. For example, if the device recognizes that the user is confused, it will display more detailed explanations or support information.

[1209] Step 7:

[1210] User B provides feedback. If any questions or problems arise while working, the user clicks the "Feedback" button and enters the problem or question into the system. This feedback is sent to the system.

[1211] Step 8:

[1212] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[1213] Step 9:

[1214] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[1215] Through these steps, the system achieves efficient, accurate and considerate business handover through a series of processes including collection, analysis, learning, provision, feedback and emotion recognition of business know-how.

[1216] Example 2

[1217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1218] Conventional job handover systems make it difficult to standardize and streamline job know-how, and lack support that takes users' feelings into consideration, causing inconvenience and stress for new entrants. They also lack a mechanism for effectively utilizing user feedback to improve the system. Therefore, a more efficient and user-friendly job handover system is needed.

[1219] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for inputting business know-how, an analysis means for analyzing the business know-how, an intelligence model means for learning the analyzed business know-how, an output means for providing business procedures using the intelligence model, a recognition means for recognizing a user's emotion, an adjustment means for adjusting the business procedures based on the recognized emotion, a receiving means for receiving and analyzing feedback from the user, and a re-learning means for re-learning the intelligence model based on the analyzed feedback. This makes it possible to efficiently take over business and provide support that takes into consideration the user's emotion.

[1220] "Input means" refers to a device or interface that allows a user to input data such as business know-how into the system.

[1221] "Analysis means" refers to a device or function for processing and analyzing input data to extract necessary information.

[1222] The "intelligent model means" is a model that uses artificial intelligence to learn based on analyzed data and accumulate knowledge that is useful for providing business procedures.

[1223] "Output means" refers to a device or interface for displaying or providing the business procedure provided by the intelligent model to the user.

[1224] "Recognition means" refers to a device or function for recognizing the user's emotions or state.

[1225] "Adjustment means" is a device or function for adjusting business procedures or response methods based on recognized emotions.

[1226] "Receiving means" refers to a device or interface for receiving feedback from a user and incorporating it into the system.

[1227] A "relearning means" is a device or function that causes the intelligence model to be retrained based on the received feedback.

[1228] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[1229] The system consists of the following components:

[1230] 1. Input method for inputting business know-how

[1231] 2. Analysis method for analyzing input business know-how

[1232] 3. Intelligent model means for learning the analyzed business know-how

[1233] 4. Output means for providing business procedures using intelligent models

[1234] 5. Recognition method for recognizing user emotions

[1235] 6. Adjustment measures to adjust work procedures based on perceived emotions

[1236] 7. Receiving means for receiving and analyzing user feedback

[1237] 8. A retraining method for retraining the intelligence model based on the analyzed feedback

[1238] Specifically, the system operates in the following manner.

[1239] Gathering know-how

[1240] A user logs into the system and inputs details of business know-how using an input device. For example, a specific procedure such as "procedures for issuing invoices" is input in text format. This know-how is saved in a database on the server.

[1241] Data analysis and learning

[1242] The server analyzes the input business procedures using an analysis tool (e.g., SpaCy or NLTK). The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained by an intelligent model tool (e.g., Hugging Face's Transformers). The intelligent model learns the relationships between procedures and specific execution methods, improving its reasoning capabilities.

[1243] Emotion recognition and business procedure provision

[1244] When a user receives instructions for a task, the device displays them in real time based on information learned from the intelligent model. The recognition means analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This could include providing more detailed explanations or additional support information.

[1245] Gathering feedback and relearning

[1246] If a user encounters any questions or problems while working, they can enter that information as feedback into the system. The server receives the feedback, analyzes it using analytical means, and retrains the intelligence model. This allows the server to provide more accurate and detailed instructions to the user from the next time onwards.

[1247] Specific examples

[1248] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[1249] 1. Enter client information into the management system.

[1250] 2. Calculate the amount to be claimed.

[1251] 3. Fill in the required information on the invoice form.

[1252] 4. Save the invoice as a PDF.

[1253] 5. Email it to your client.

[1254] Prompt Sentence Examples

[1255] Enter client information into the management system.

[1256] Calculate the amount to be charged.

[1257] Fill in the required information on the invoice form.

[1258] Save the invoice in PDF format.

[1259] Email it to your client.

[1260] In this way, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[1261] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1262] Step 1: Gathering know-how

[1263] A user logs in to the system. After entering the correct login information and passing the authentication process, the user is redirected to the business know-how input screen. Here, the user enters specific business procedures (for example, "procedures for issuing invoices") in text format. This input data is sent to the server and saved in the database.

[1264] input:

[1265] User login information (ID and password)

[1266] Business know-how entered in text format

[1267] output:

[1268] Business know-how stored in a database

[1269] Operation:

[1270] User interface prompts for data entry and saving

[1271] Step 2: Analyze and train the data

[1272] The server analyzes the stored business procedures using an analysis means. The server uses natural language processing means (e.g., SpaCy or NLTK) to tokenize the input text data and extract important keywords and grammatical structures. This structures the business flow and prepares it as data for the next learning by the intelligence model means.

[1273] input:

[1274] Business know-how stored in a database

[1275] output:

[1276] Structured business flow data

[1277] Operation:

[1278] Executing natural language processing algorithms and storing results

[1279] Step 3: Training the Intelligence Model

[1280] The server trains the analyzed data using an intelligent model (for example, Hugging Face's Transformers). The server calls the intelligent model and trains it on the data, allowing it to understand the relevance of business procedures and how to execute them. Once training is complete, the model is ready to be used to provide business procedures.

[1281] input:

[1282] Structured business flow data

[1283] output:

[1284] An intelligent model that understands business procedures

[1285] Operation:

[1286] Execution of the learning process of the intelligent model and notification of its completion

[1287] Step 4: Provide business procedures

[1288] Based on the information learned from the intelligent model, the device provides users with real-time instructions on how to proceed. Specifically, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[1289] input:

[1290] Intelligence Model

[1291] output:

[1292] Real-time operational procedures

[1293] Operation:

[1294] Displaying instruction messages on the user screen

[1295] Step 5: Emotion Recognition

[1296] The device's recognition means analyzes the user's facial expressions and voice to recognize their emotions. The device identifies the user's emotions based on the recognized emotion data. For example, if the user is confused, the system will display additional explanations or support.

[1297] input:

[1298] User facial expression and voice data

[1299] output:

[1300] Recognized emotion data

[1301] Operation:

[1302] Data collection and analysis using cameras and microphones

[1303] Step 6: Adjust your work procedures based on emotions

[1304] The device can then adjust its work procedures based on the recognized emotion data, for example, providing more detailed explanations or displaying additional support information if the user is confused.

[1305] input:

[1306] Recognized emotion data

[1307] output:

[1308] Adjusted operating procedures

[1309] Operation:

[1310] Displaying additional instruction messages on the user screen

[1311] Step 7: Gather feedback

[1312] The user inputs feedback about the work procedure into the system. The user writes down any problems or questions about the work in progress and sends them to the server via the input means.

[1313] input:

[1314] User feedback (text format)

[1315] output:

[1316] Feedback stored in the database

[1317] Operation:

[1318] User interface prompts for feedback entry and saving

[1319] Step 8: Analyze feedback and retrain

[1320] The server analyzes the received feedback and retrains the intelligence model means. The server analyzes the feedback using natural language processing means and extracts areas for improvement and problems. New analysis data is supplied to the intelligence model and retraining is performed.

[1321] input:

[1322] Feedback stored in the database

[1323] output:

[1324] Improved Intelligence Model

[1325] Operation:

[1326] Conducting feedback analysis and retraining process of the intelligence model

[1327] Through the above steps, this system realizes task handover that takes emotions into consideration, aiming to improve work efficiency and user satisfaction.

[1328] (Application example 2)

[1329] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1330] Conventional task handover systems lack the ability to effectively convey task know-how and the ability to appropriately adjust instructions based on the user's emotional state. This often leaves new operators feeling confused and frustrated, leading to reduced productivity and work efficiency. Furthermore, there is a lack of effective means for utilizing user feedback to improve the system's accuracy, which delays improvements to the task handover process.

[1331] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means for providing business procedures using the artificial intelligence model, a feedback receiving means for receiving and analyzing feedback from the user, a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback, an emotion engine means for recognizing user emotions, and a means for adjusting business procedures based on the recognized user emotions. This makes it possible to provide appropriate instructions in real time according to the user's emotions during the business handover process, thereby improving productivity and business efficiency. Furthermore, the accuracy of the system can be continuously improved by utilizing user feedback and emotion data.

[1332] "Business know-how" refers to the knowledge and procedures required to carry out a specific business.

[1333] "User interface means" refers to the interface that a user uses to input business know-how into the system.

[1334] "Natural language processing means" refers to the techniques and processes used to parse meaning and context from text data.

[1335] "Artificial intelligence model means" refers to a machine learning model that learns from analyzed data and generates business procedures.

[1336] "Output interface means" refers to an interface for providing a business procedure to a user.

[1337] "Feedback receiving means" refers to a mechanism for receiving and analyzing feedback from a user.

[1338] "Retraining" refers to the process of retraining an AI model based on received feedback to improve its accuracy.

[1339] The "emotion engine means" refers to a mechanism for recognizing the user's emotions and responding or giving instructions according to those emotions.

[1340] The "means for adjusting the business procedure" refers to a mechanism for appropriately changing the method of providing the business procedure and the content thereof based on the recognized user's emotions.

[1341] The present invention relates to a system that uses a "Smart Factory Assistant" application that is installed on a factory robot. Hereinafter, an embodiment of the present invention will be specifically described.

[1342] Hardware and Software Configuration

[1343] The server uses the following hardware and software:

[1344] Hardware:

[1345] Factory robots

[1346] software:

[1347] Python libraries: transformers, EmotionRecognizer

[1348] Pre-trained AI models: BERT, GPT, etc.

[1349] System Operation

[1350] 1. Gathering business know-how:

[1351] A user inputs business know-how (e.g., "machine operating procedures") using a terminal installed in a factory robot. The input text data is collected via the user interface.

[1352] 2. Data analysis and AI model training:

[1353] The server analyzes the text data entered by the user using natural language processing. The analyzed data is extracted as business flow and important points. Based on this data, an artificial intelligence model (e.g., BERT) is used to train the system and understand specific procedures and points to note.

[1354] 3. Providing business procedures:

[1355] When a user requests a work procedure, the terminal installed on the factory robot displays instructions from the AI ​​model in real time, such as "Please set the material in the machine."

[1356] 4. Emotion recognition and regulation:

[1357] The emotion engine analyzes the user's voice and facial expression data to recognize the user's emotions in real time. Based on the recognized emotions, the system adjusts the work procedure. For example, if the user is confused, it provides detailed additional explanations.

[1358] 5. Feedback mechanism:

[1359] Users can input feedback into the system about any questions or problems they encounter while working. The server receives this feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to users from the next time onwards.

[1360] Specific examples

[1361] Example prompts for confused users:

[1362] "Press the red switch on the right. Then press and hold this button for three seconds."

[1363] Example prompt for angry users:

[1364] "Take a deep breath, and let's start again together."

[1365] The server integrates the above methods to provide a system for efficient and user-friendly task handover by factory robots. This system dynamically adjusts work procedures according to the user's emotions, improving work productivity and efficiency while reducing user stress.

[1366] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1367] Step 1:

[1368] The user inputs business know-how (e.g., "machine operating procedures") using a terminal installed on the factory robot. The input data is collected in text format and sent to the server. This allows the business know-how to be collected.

[1369] Input: Text data of business know-how

[1370] Output: Sending collected data

[1371] Step 2:

[1372] The server receives the business know-how sent by the user and analyzes it using natural language processing. Specifically, it tokenizes the text data and extracts important keywords and grammatical structures. This allows the business flow and key items to be identified.

[1373] Input: Text data of collected business know-how

[1374] Output: Parsed keywords and grammatical structures

[1375] Step 3:

[1376] The server trains an artificial intelligence model (e.g., BERT) on the analyzed business know-how. Specifically, the extracted keywords and grammatical structures are fed as input data to the AI ​​model, which then understands and infers business procedures. This allows the AI ​​model to learn the business know-how and store it as executable procedures.

[1377] Input: Parsed keywords and grammatical structures

[1378] Output: The trained AI model

[1379] Step 4:

[1380] When a user requests the provision of a business procedure, the device sends a request to the server. The server uses the trained AI model to generate instructions for the business procedure according to the user's request and sends them to the device, which displays them in real time.

[1381] Input: User's request to provide business procedures

[1382] Output: Generated work procedure instructions

[1383] Step 5:

[1384] The device collects the user's voice and facial expression data and recognizes the user's emotions in real time using an emotion engine means. The emotion engine analyzes changes in voice tone and facial expressions to identify the user's emotional state (e.g., confusion, anger).

[1385] Input: User's voice and facial expression data

[1386] Output: Identified user emotional state

[1387] Step 6:

[1388] The server adjusts the work procedure based on the user's recognized emotional state. For example, if the user is confused, it generates detailed additional explanations, and if the user is angry, it generates gentler explanations. This helps the user to perform the work appropriately.

[1389] Input: Identified emotional state of the user

[1390] Output: Coordinated work instructions

[1391] Step 7:

[1392] The user inputs feedback about any unclear points or problems that arise as they proceed with their work. The device sends this feedback to the server, which analyzes it and retrains the AI ​​model. This allows the device to provide more accurate and detailed instructions to the user next time.

[1393] Input: User feedback

[1394] Output: Retrained AI model

[1395] 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.

[1396] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1397] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1398] [Fourth embodiment]

[1399] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1400] 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.

[1401] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the 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).

[1402] 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.

[1403] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1404] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1405] 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.

[1406] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1407] 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.

[1408] 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 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.

[1409] 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.

[1410] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1411] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1412] The present invention is a tool for training an AI to learn business know-how and using the AI ​​to carry out business handover. Specific embodiments for carrying out the present invention will be described below.

[1413] Basic system configuration

[1414] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, and a re-learning means.

[1415] Explanation of program processing

[1416] 1. Gathering know-how

[1417] To gather business know-how, a user first logs into the system and inputs business procedures, such as "procedures for issuing invoices," in text format via the user interface. For example, the user sequentially inputs steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[1418] 2. Data analysis and learning

[1419] The server uses natural language processing to analyze the business know-how entered by the user. This analysis includes grammatical analysis of the text and keyword extraction. The analyzed data is organized into a data set showing the business flow and important points. The server then trains an artificial intelligence model on the analysis results. The model learns the relevance of each step and specific implementation methods, accumulating knowledge about business procedures.

[1420] 3. Providing business procedures

[1421] When the terminal provides work procedures to a new user (for example, a new employee), it guides them through the specific work procedures in real time based on the learning results from the server. When the user operates the system and clicks the "Start work procedures" button, the terminal displays the work procedures step by step based on the information learned by the AI. For example, instructions such as "Please enter the client's information into the management system" are displayed, along with detailed operating instructions and points to note.

[1422] Specific examples

[1423] Gathering know-how

[1424] The user inputs business know-how under the title "Invoice Issuance Procedure." Specifically, the following steps are described in detail:

[1425] 1. Enter client information into the management system.

[1426] 2. Calculate the amount to be claimed.

[1427] 3. Fill in the required information on the invoice form.

[1428] 4. Save the invoice as a PDF.

[1429] 5. Email it to your client.

[1430] Data analysis and learning

[1431] The server receives this data and analyzes it using natural language processing. For example, it extracts keywords and operational procedures related to each step and organizes them into a business flow. This data is then trained into an artificial intelligence model, allowing the AI ​​to understand specific steps and important points.

[1432] Providing business procedures

[1433] When new employee User B uses the system to learn how to issue an invoice, the device displays guidance based on the information learned by the AI. For example, when User B clicks the "Start invoice issuance procedure" button, the first step is to "Enter client information into the management system." Next, instructions such as "Calculate the invoice amount" and "Enter the information into the invoice format" are displayed in sequence, with specific support provided for each step.

[1434] Feedback Mechanism

[1435] If User B encounters any unclear points or problems while working, he or she inputs that information into the system as feedback. The server analyzes this feedback and retrains the AI ​​model. This improves the accuracy and reliability of the system so that future users do not encounter similar problems.

[1436] As described above, the present invention is a system that realizes efficient and accurate business handover through a series of processes including collection, analysis, learning, provision, and feedback of business know-how.

[1437] The processing flow will be explained below.

[1438] Step 1:

[1439] The user inputs business know-how. Specifically, after logging in to the system, the user inputs business procedures such as "invoice issuance procedures" in text format via the provided user interface. For example, the following information is input for each procedure:

[1440] 1. Enter client information into the management system.

[1441] 2. Calculate the amount to be claimed.

[1442] 3. Fill in the required information on the invoice form.

[1443] 4. Save the invoice as a PDF.

[1444] 5. Email it to your client.

[1445] Step 2:

[1446] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[1447] Step 3:

[1448] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[1449] Step 4:

[1450] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[1451] Step 5:

[1452] User B, who is new to the system, clicks the "Start business procedure" button. This causes the device to retrieve information learned from the AI ​​model and display sequential instructions in real time. For example, the device may display instructions such as "Enter client information into the management system," along with detailed operating instructions and important points to note.

[1453] Step 6:

[1454] If User B encounters any unclear points or problems in the system while following the procedures, he or she clicks the "Feedback" button and enters the details of the problem or question into the system. This feedback is sent to the system.

[1455] Step 7:

[1456] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[1457] Step 8:

[1458] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[1459] Through these steps, this system achieves efficient and accurate business handover through a series of processes: collecting, analyzing, learning, providing, and providing feedback on business know-how.

[1460] Example 1

[1461] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1462] Traditional methods of job handover are time-consuming and laborious, and often result in inaccurate information being conveyed or important procedures being overlooked. Another problem is the lack of an appropriate support system for new employees to efficiently learn their jobs. This leads to reduced work efficiency and an increase in mistakes and rework.

[1463] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1464] In this invention, the server includes a user interface means for inputting business knowledge, a natural language processing means for analyzing the business knowledge, and a machine learning model means for training the analyzed business knowledge. This makes it possible to efficiently and accurately collect, analyze, and train business knowledge. Furthermore, by including an opinion receiving means for receiving and analyzing opinions from users and a re-learning means for re-training the machine learning model based on the analyzed opinions, it is possible to continuously improve the system and increase its accuracy.

[1465] "Business knowledge" refers to procedures, know-how, related information, etc. required when performing business.

[1466] "User interface means" refers to the operation screen and interactive tools that allow users to input, edit, and view business knowledge.

[1467] "Natural language processing means" refers to algorithms and technologies for analyzing text data and understanding its meaning and structure.

[1468] "Machine learning model means" refers to a system that uses machine learning technology to learn patterns and knowledge from input data and make inferences and predictions.

[1469] "Output interface means" refers to devices and software for providing learning results to users and displaying business procedures.

[1470] "Opinion receiving means" refers to a system or function for receiving and processing feedback and opinions from users.

[1471] "Retraining methods" refers to techniques and processes used to retrain a machine learning model and improve its performance based on received opinions and feedback.

[1472] The present invention is a system for collecting, analyzing, learning, providing, and feeding back business knowledge, and specific embodiments thereof will be described.

[1473] Basic system configuration

[1474] This system is composed of a user interface means for inputting business knowledge, a natural language processing means for analyzing the input information, a machine learning model means for learning the analyzed information, an output interface means for providing the learning results, an opinion receiving means for receiving opinions from users, and a re-learning means.

[1475] Gathering know-how

[1476] The user first logs in to the system and inputs business knowledge in text format via the user interface. For example, under the title "Procedure for issuing invoices," the user might input steps such as "Enter client information into the management system," "Calculate the invoice amount," "Fill in the information into the invoice format," "Save as PDF," and "Send to the client by email."

[1477] Data analysis and learning

[1478] 1. The server receives the business knowledge input from the user. The received data is temporarily stored in a database (e.g., MySQL).

[1479] 2. Analyze the input business knowledge using a natural language processing engine (e.g., SpaCy) including legal procedures. The analysis includes grammatical analysis, keyword extraction, and sentence structuring.

[1480] For example, keywords such as "entering information" and "invoice format" are extracted from the sentence "entering information into an invoice format."

[1481] 3. The server organizes the business procedure data based on the analysis results and saves it as a dataset, which clearly shows the relationships and order of each procedure.

[1482] For example, the continuity between "Enter client information into the management system" and "Calculate the billing amount" is maintained.

[1483] 4. The server trains a machine learning model (e.g., GPT-4) on the data and accumulates the learned knowledge.

[1484] Providing business procedures

[1485] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The terminal guides the user through the business procedure in real time based on the learning results from the server.

[1486] Examples:

[1487] For example, when a user clicks the "Start Business Procedure" button, the following instruction appears on the screen: "Please enter the client's information into the management system." At this time, detailed operating instructions and important points are also provided.

[1488] Next, steps such as "Calculate the bill amount" and "Enter the information into the billing form" are displayed, with specific support information provided for each step.

[1489] Feedback Mechanism

[1490] If a user has a question or problem while going through a work procedure, they click the "Feedback" button and enter the problem. The server receives this feedback, analyzes it using a natural language processing engine, and saves it as a feedback dataset. The feedback data is then input into a machine learning model, and retraining improves the accuracy and reliability of the system.

[1491] Prompt Sentence Examples

[1492] "Please have the AI ​​learn the following business procedure. The title is 'Invoice Issuance Procedure'.

[1493] 1. Enter client information into the management system.

[1494] 2. Calculate the amount to be claimed.

[1495] 3. Fill in the required information on the invoice form.

[1496] 4. Save the invoice as a PDF.

[1497] 5. Email it to your client.

[1498] I would love to see AI learn these steps and provide a way to guide new users."

[1499] As described above, the present invention is a system that efficiently collects, analyzes, learns, provides, and improves business knowledge through feedback, thereby realizing efficient business handover.

[1500] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1501] Step 1: Gathering know-how

[1502] A user logs into the system and inputs business knowledge. Specifically, the user enters business procedures such as "procedures for issuing invoices" in text format via the user interface. For example, the user might enter steps such as "enter client information into the management system," "calculate the invoice amount," "fill in the information in the invoice format," "save as PDF," and "send to the client by email."

[1503] Input: Text data of business procedures

[1504] Output: User-entered business procedure data

[1505] Step 2: Receiving and temporarily storing data

[1506] The server receives the business procedure data sent by the user and temporarily stores this data in a database (e.g., MySQL).

[1507] Input: Business procedure data entered by the user

[1508] Output: Business procedure data stored in a database

[1509] Step 3: Natural Language Processing

[1510] The server uses a natural language processing engine (e.g., SpaCy) to analyze the received business procedure data. This analysis involves grammatical analysis, keyword extraction, and sentence structuring. For example, from the sentence "filling in information on an invoice format," it extracts keywords such as "filling in information" and "invoice format."

[1511] Input: Business procedure data stored in the database

[1512] Output: Analyzed business procedure data (keywords and sentence structure)

[1513] Step 4: Organizing the dataset

[1514] The server organizes the business procedure data based on the analysis results and saves it as a dataset. This includes clarifying the relationship and order of each step. For example, it maintains the continuity between "Enter client information into the management system" and "Calculate the billing amount."

[1515] Input: Parsed business procedure data

[1516] Output: Organized business procedure dataset

[1517] Step 5: Training the AI ​​model

[1518] The server trains a machine learning model (e.g., GPT-4) using the organized dataset. The model learns the structure and relationships of business procedures and understands detailed support methods for each procedure.

[1519] Input: Organized business procedure dataset

[1520] Output: Trained AI model

[1521] Step 6: Providing business procedures and guidance

[1522] A new user (e.g., a new employee) logs in to the system and clicks the "Start Business Procedure" button. The device retrieves guidance information from the trained AI model and guides the user through the business procedure in real time. For example, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[1523] Input: Business procedure start request from user

[1524] Output: Business procedure guide displayed on the terminal

[1525] Step 7: Provide support information

[1526] The device will display detailed support information and notes for each step, including detailed instructions such as "Please make sure the information you entered is accurate."

[1527] Input: Guide information for trained AI models

[1528] Output: Detailed supporting information displayed on the terminal

[1529] Step 8: Provide feedback

[1530] If a user encounters a question or problem while going through the work procedure, they can click the "Feedback" button to enter the problem, and this information will be sent to the system.

[1531] Input: User feedback information

[1532] Output: Feedback data sent to the server

[1533] Step 9: Receive and analyze feedback

[1534] The server receives the feedback sent by the user and analyzes it using a natural language processing engine. The analysis results are stored as a feedback dataset.

[1535] Input: Feedback data

[1536] Output: Parsed feedback dataset

[1537] Step 10: Retrain

[1538] The server inputs the feedback data into the machine learning model and performs retraining, which improves the accuracy and reliability of the model.

[1539] Input: Parsed feedback dataset

[1540] Output: Retrained AI model

[1541] Through the above series of processing steps, the present invention realizes accurate and efficient handover of business knowledge and enables continuous improvement of the system.

[1542] (Application example 1)

[1543] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1544] The present invention aims to provide a system that provides real-time guidance on work procedures at logistics centers, enabling even new or temporary staff to perform their work efficiently. Current work handover methods rely on understanding manuals or verbal explanations from person to person, which can lack accuracy and efficiency. Furthermore, there is a lack of mechanisms for improving work procedures based on feedback, which can lead to recurrence of similar problems. Therefore, there is a need for a system that uses AI to learn work know-how, efficiently guides staff through work procedures, and retrains the model through feedback.

[1545] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1546] In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means, a feedback receiving means, a relearning means, and a guide means for guiding business procedures in real time via a smart device. This enables efficient handover of business procedures at a logistics center and continuous improvement of business procedures based on feedback.

[1547] "Business know-how" refers to the knowledge, techniques, and procedures required to carry out a specific business task effectively and efficiently.

[1548] "User interface means" refers to an operation screen or input device that allows a user to input business know-how into the system.

[1549] "Natural language processing means" refers to technology for analyzing input text data and understanding and processing its content.

[1550] "Artificial intelligence model means" refers to algorithms or systems that learn analyzed business know-how and provide business procedures based on that knowledge.

[1551] "Output interface means" refers to a display screen or output device for providing the user with the business procedures learned by the artificial intelligence model.

[1552] "Feedback receiving means" refers to a system or device for receiving and analyzing feedback from a user.

[1553] "Retraining means" refers to a learning process for improving the accuracy of an artificial intelligence model based on analyzed feedback.

[1554] "Guide means" refers to a system or device that guides users through business procedures in real time via a smart device.

[1555] "Smart devices" refers to mobile information terminals with advanced functions, such as smartphones and smart glasses.

[1556] A "business procedure" refers to a series of steps or processes for accomplishing a particular task.

[1557] The present invention relates to a system for providing real-time guidance of work procedures at a logistics center using smart devices. Specific embodiments for carrying out the present invention will be described below.

[1558] Basic system configuration

[1559] This system is composed of a user interface means for inputting business know-how, a natural language processing means for analyzing the input information, an artificial intelligence model means for learning the analyzed information, an output interface means for providing the learning results, a feedback receiving means for receiving feedback from the user, a relearning means, and a guide means for guiding business procedures in real time via a smart device.

[1560] Hardware and software used

[1561] Hardware:

[1562] Smart devices (e.g., smart glasses, smartphones)

[1563] software:

[1564] Natural language processing libraries (e.g. Spacy)

[1565] Generative AI models (e.g., GPT-2, transformers library)

[1566] Data processing and calculation

[1567] 1. Gathering business know-how:

[1568] The server collects business know-how in text format through a user interface. This process also supports voice input using voice recognition. For example, detailed business procedures can be entered under a title such as "Incoming Inspection Procedure." This makes it easy for even new or temporary staff to input information.

[1569] 2. Data analysis and learning:

[1570] The server analyzes the collected business know-how using natural language processing and trains an AI model based on the results. For example, Spacy can be used to extract keywords and phrases related to business procedures, and a generative AI model (GPT-2) can then train on these.

[1571] 3. Providing business procedures:

[1572] The terminal (smart device) guides the work procedures in real time based on the learning results. When a new staff member starts a task, for example, by clicking the "Start work procedure" button, the specific steps learned by the AI ​​are displayed one by one. Instructions such as "Please scan the product barcode" and "Please check the quantity" are displayed.

[1573] 4. Feedback mechanism:

[1574] Users input any problems or questions they encounter as they work into the system as feedback. The server analyzes this feedback information and retrains the AI ​​model to improve the accuracy of future work procedures.

[1575] Examples of concrete examples and prompts

[1576] Examples:

[1577] The incoming goods inspection procedure guides users through steps such as "scanning the product barcode," "confirming the quantity," and "checking for defects." Users can check these steps in real time via their smart devices and carry out their work.

[1578] Example prompt sentence:

[1579] "When new staff members learn the receiving inspection procedures, AI can generate a step-by-step guide based on their operational know-how."

[1580] Generated text:

[1581] 1. Scan the product barcode.

[1582] 2. Check the quantity.

[1583] 3. Check for any defects.

[1584] 4. Once you have finished checking, move on to the next product.

[1585] In this way, the system of the present invention realizes efficient operations and accurate handover in a logistics center.

[1586] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1587] Step 1:

[1588] The user inputs business know-how

[1589] Users input specific operational procedures at the logistics center (e.g., incoming goods inspection procedures) in text format through a user interface. Voice recognition can also be used for input.

[1590] Input: Detailed text data of business procedures

[1591] Output: Text data of the entered business procedures

[1592] Step 2:

[1593] The server analyzes business know-how

[1594] The server analyzes the input business know-how using natural language processing tools (e.g., Spacy), performing grammatical analysis and extracting keywords to identify important points in the business procedures.

[1595] Input: Text data of business procedures entered by the user

[1596] Output: Analyzed keywords and grammatical structures

[1597] Step 3:

[1598] The server trains the AI ​​model

[1599] The server then trains an artificial intelligence model (e.g., GPT-2) on the analyzed business know-how data. The model then understands the relationships between business procedures and how to carry them out, and improves its reasoning capabilities based on this.

[1600] Input: Analyzed keywords and grammatical structure data

[1601] Output: Learned business procedure model

[1602] Step 4:

[1603] The terminal provides business procedures

[1604] The device (e.g., smart glasses or smartphone) displays the work procedure in real time based on the learning results. When the user presses the "Start work procedure" button, specific instructions (e.g., "Scan the product barcode") are displayed sequentially.

[1605] Input: Learned business procedure model

[1606] Output: Real-time operational instructions

[1607] Step 5:

[1608] User enters feedback

[1609] Users input feedback into the system about any problems or unclear points that arise while working.

[1610] Input: Feedback information on problems or unclear points that occurred during work

[1611] Output: Feedback text data

[1612] Step 6:

[1613] The server analyzes the feedback and re-learns

[1614] The server analyzes the feedback received from the user using natural language processing means and retrains the artificial intelligence model using retraining means, thereby improving the accuracy of the model and making subsequent guidance more effective.

[1615] Input: Text data of user feedback

[1616] Output: Improved business procedure model

[1617] The above are the specific processing steps of the program for the system that realizes the application example.

[1618] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1619] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[1620] The system consists of the following components:

[1621] 1. User interface means for inputting business know-how

[1622] 2. Natural language processing means for analyzing input business know-how

[1623] 3. AI modeling means for learning the analyzed business know-how

[1624] 4. Output interface means for providing business procedures using AI models

[1625] 5. Feedback receiving means for receiving and analyzing user feedback

[1626] 6. A retraining method to retrain the AI ​​model based on the analyzed feedback

[1627] 7. Emotion engine means for recognizing user emotions

[1628] 8. A method for adjusting work procedures based on user emotions recognized by an emotion engine

[1629] Explanation of program processing

[1630] 1. Gathering know-how

[1631] A user logs into the system and inputs details of business know-how using the user interface means. For example, a specific procedure such as "procedure for issuing an invoice" is input in text format.

[1632] 2. Data analysis and learning

[1633] The server analyzes the input business procedures using natural language processing. The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained into an AI model. The AI ​​model learns the relevance of procedures and specific execution methods, improving its reasoning capabilities.

[1634] 3. Emotion recognition and business procedure provision

[1635] When a user receives instructions for a task, the device displays the instructions in real time based on information learned from the AI ​​model. The emotion engine analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This may include providing more detailed explanations or additional support information.

[1636] Specific examples

[1637] Gathering know-how

[1638] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[1639] 1. Enter client information into the management system.

[1640] 2. Calculate the amount to be claimed.

[1641] 3. Fill in the required information on the invoice form.

[1642] 4. Save the invoice as a PDF.

[1643] 5. Email it to your client.

[1644] Data analysis and learning

[1645] The server receives this data and analyzes it using natural language processing. As a result of the analysis, keywords and grammatical structures related to each step are extracted and structured as a business flow. This is then trained into an AI model, which then understands the specific steps and important points to note.

[1646] Providing business procedures and emotion recognition

[1647] When new employee User B uses the system to learn how to issue an invoice, the device uses information from the AI ​​model to guide the user through the process in real time. For example, instructions like "Please enter client information into the management system" are displayed. The emotion engine recognizes the user's emotions, and if the user is confused, it provides more detailed explanations and supplementary information to help the user carry out their work with confidence.

[1648] Feedback Mechanism

[1649] If User B encounters any questions or problems while working, he or she enters that information into the system as feedback. The server receives the feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to the user from the next time onwards.

[1650] As described above, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[1651] The processing flow will be explained below.

[1652] Step 1:

[1653] A user logs into the system and inputs business know-how. Specifically, the user uses a user interface to input business procedures such as "procedures for issuing invoices" in text format. For example, the user might input the following steps in order:

[1654] 1. Enter client information into the management system.

[1655] 2. Calculate the amount to be claimed.

[1656] 3. Fill in the required information on the invoice form.

[1657] 4. Save the invoice as a PDF.

[1658] 5. Email it to your client.

[1659] Step 2:

[1660] The server receives the entered business procedures. The received data is first stored in a database. The stored data is then sent to the next process for analysis.

[1661] Step 3:

[1662] The server analyzes the stored business procedures using natural language processing. Specifically, it analyzes the keywords and grammatical structures contained in each step of the business procedures. Through this analysis, important points and relationships of each step are extracted and converted into a structured data format.

[1663] Step 4:

[1664] The server then trains the AI ​​model on the analyzed data. The AI ​​model learns patterns and related information about business procedures based on the analyzed data it receives, improving its inference capabilities. This makes it ready to provide specific business procedures to new users.

[1665] Step 5:

[1666] When User B clicks the "Start Business Procedure" button, the device retrieves the information learned from the AI ​​model and displays the business procedure step by step. For example, the first step is to display the instruction "Enter the client's information into the management system," followed by detailed operating instructions and important points to note.

[1667] Step 6:

[1668] The device uses a camera and microphone to recognize the user's emotions, and the emotion engine analyzes facial expressions and voice. The emotion engine recognizes the user's emotions in real time and adjusts the instructions provided by the system based on that. For example, if the device recognizes that the user is confused, it will display more detailed explanations or support information.

[1669] Step 7:

[1670] User B provides feedback. If any questions or problems arise while working, the user clicks the "Feedback" button and enters the problem or question into the system. This feedback is sent to the system.

[1671] Step 8:

[1672] The server analyzes the received feedback. Specifically, it analyzes the feedback content to detect common items and frequently occurring problems. The analysis results are used in the next processing step.

[1673] Step 9:

[1674] The server retrains the AI ​​model based on the analysis results. This retraining process improves the accuracy of the model, enabling it to provide more accurate and detailed instructions to future users. By incorporating this feedback, the reliability and usability of the entire system are improved.

[1675] Through these steps, the system achieves efficient, accurate and considerate business handover through a series of processes including collection, analysis, learning, provision, feedback and emotion recognition of business know-how.

[1676] Example 2

[1677] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1678] Conventional job handover systems make it difficult to standardize and streamline job know-how, and lack support that takes users' feelings into consideration, causing inconvenience and stress for new entrants. They also lack a mechanism for effectively utilizing user feedback to improve the system. Therefore, a more efficient and user-friendly job handover system is needed.

[1679] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes an input means for inputting business know-how, an analysis means for analyzing the business know-how, an intelligence model means for learning the analyzed business know-how, an output means for providing business procedures using the intelligence model, a recognition means for recognizing a user's emotion, an adjustment means for adjusting the business procedures based on the recognized emotion, a receiving means for receiving and analyzing feedback from the user, and a re-learning means for re-learning the intelligence model based on the analyzed feedback. This makes it possible to efficiently take over business and provide support that takes into consideration the user's emotion.

[1680] "Input means" refers to a device or interface that allows a user to input data such as business know-how into the system.

[1681] "Analysis means" refers to a device or function for processing and analyzing input data to extract necessary information.

[1682] The "intelligent model means" is a model that uses artificial intelligence to learn based on analyzed data and accumulate knowledge that is useful for providing business procedures.

[1683] "Output means" refers to a device or interface for displaying or providing the business procedure provided by the intelligent model to the user.

[1684] "Recognition means" refers to a device or function for recognizing the user's emotions or state.

[1685] "Adjustment means" is a device or function for adjusting business procedures or response methods based on recognized emotions.

[1686] "Receiving means" refers to a device or interface for receiving feedback from a user and incorporating it into the system.

[1687] A "relearning means" is a device or function that causes the intelligence model to be retrained based on the received feedback.

[1688] This invention is a tool for training AI to learn business know-how and using that AI to carry out task handovers. It also incorporates an emotion engine that recognizes the user's emotions and has the function of adjusting the delivery of task procedures based on the user's emotions. This system enables task handovers to be carried out more efficiently and with human consideration.

[1689] The system consists of the following components:

[1690] 1. Input method for inputting business know-how

[1691] 2. Analysis method for analyzing input business know-how

[1692] 3. Intelligent model means for learning the analyzed business know-how

[1693] 4. Output means for providing business procedures using intelligent models

[1694] 5. Recognition method for recognizing user emotions

[1695] 6. Adjustment measures to adjust work procedures based on perceived emotions

[1696] 7. Receiving means for receiving and analyzing user feedback

[1697] 8. A retraining method for retraining the intelligence model based on the analyzed feedback

[1698] Specifically, the system operates in the following manner.

[1699] Gathering know-how

[1700] A user logs into the system and inputs details of business know-how using an input device. For example, a specific procedure such as "procedures for issuing invoices" is input in text format. This know-how is saved in a database on the server.

[1701] Data analysis and learning

[1702] The server analyzes the input business procedures using an analysis tool (e.g., SpaCy or NLTK). The analyzed data is extracted as business flows and important points, and saved as structured data. This data is then trained by an intelligent model tool (e.g., Hugging Face's Transformers). The intelligent model learns the relationships between procedures and specific execution methods, improving its reasoning capabilities.

[1703] Emotion recognition and business procedure provision

[1704] When a user receives instructions for a task, the device displays them in real time based on information learned from the intelligent model. The recognition means analyzes the user's facial expressions and voice to recognize their emotions. For example, if the user is feeling angry or confused, the device will detect this and adjust the displayed instructions and procedures. This could include providing more detailed explanations or additional support information.

[1705] Gathering feedback and relearning

[1706] If a user encounters any questions or problems while working, they can enter that information as feedback into the system. The server receives the feedback, analyzes it using analytical means, and retrains the intelligence model. This allows the server to provide more accurate and detailed instructions to the user from the next time onwards.

[1707] Specific examples

[1708] A user enters business know-how under the title "Invoice Issuance Procedure." The following steps are described in detail:

[1709] 1. Enter client information into the management system.

[1710] 2. Calculate the amount to be claimed.

[1711] 3. Fill in the required information on the invoice form.

[1712] 4. Save the invoice as a PDF.

[1713] 5. Email it to your client.

[1714] Prompt Sentence Examples

[1715] Enter client information into the management system.

[1716] Calculate the amount to be charged.

[1717] Fill in the required information on the invoice form.

[1718] Save the invoice in PDF format.

[1719] Email it to your client.

[1720] In this way, the present invention provides a system that incorporates an emotion engine to improve the efficiency of task handover while taking into consideration the user's emotions. This not only achieves standardization of tasks and improved accuracy of handover, but also improves user satisfaction.

[1721] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1722] Step 1: Gathering know-how

[1723] A user logs in to the system. After entering the correct login information and passing the authentication process, the user is redirected to the business know-how input screen. Here, the user enters specific business procedures (for example, "procedures for issuing invoices") in text format. This input data is sent to the server and saved in the database.

[1724] input:

[1725] User login information (ID and password)

[1726] Business know-how entered in text format

[1727] output:

[1728] Business know-how stored in a database

[1729] Operation:

[1730] User interface prompts for data entry and saving

[1731] Step 2: Analyze and train the data

[1732] The server analyzes the stored business procedures using an analysis means. The server uses natural language processing means (e.g., SpaCy or NLTK) to tokenize the input text data and extract important keywords and grammatical structures. This structures the business flow and prepares it as data for the next learning by the intelligence model means.

[1733] input:

[1734] Business know-how stored in a database

[1735] output:

[1736] Structured business flow data

[1737] Operation:

[1738] Executing natural language processing algorithms and storing results

[1739] Step 3: Training the Intelligence Model

[1740] The server trains the analyzed data using an intelligent model (for example, Hugging Face's Transformers). The server calls the intelligent model and trains it on the data, allowing it to understand the relevance of business procedures and how to execute them. Once training is complete, the model is ready to be used to provide business procedures.

[1741] input:

[1742] Structured business flow data

[1743] output:

[1744] An intelligent model that understands business procedures

[1745] Operation:

[1746] Execution of the learning process of the intelligent model and notification of its completion

[1747] Step 4: Provide business procedures

[1748] Based on the information learned from the intelligent model, the device provides users with real-time instructions on how to proceed. Specifically, instructions such as "Please enter the client's information into the management system" are displayed on the screen.

[1749] input:

[1750] Intelligence Model

[1751] output:

[1752] Real-time operational procedures

[1753] Operation:

[1754] Displaying instruction messages on the user screen

[1755] Step 5: Emotion Recognition

[1756] The device's recognition means analyzes the user's facial expressions and voice to recognize their emotions. The device identifies the user's emotions based on the recognized emotion data. For example, if the user is confused, the system will display additional explanations or support.

[1757] input:

[1758] User facial expression and voice data

[1759] output:

[1760] Recognized emotion data

[1761] Operation:

[1762] Data collection and analysis using cameras and microphones

[1763] Step 6: Adjust your work procedures based on emotions

[1764] The device can then adjust its work procedures based on the recognized emotion data, for example, providing more detailed explanations or displaying additional support information if the user is confused.

[1765] input:

[1766] Recognized emotion data

[1767] output:

[1768] Adjusted operating procedures

[1769] Operation:

[1770] Displaying additional instruction messages on the user screen

[1771] Step 7: Gather feedback

[1772] The user inputs feedback about the work procedure into the system. The user writes down any problems or questions about the work in progress and sends them to the server via the input means.

[1773] input:

[1774] User feedback (text format)

[1775] output:

[1776] Feedback stored in the database

[1777] Operation:

[1778] User interface prompts for feedback entry and saving

[1779] Step 8: Analyze feedback and retrain

[1780] The server analyzes the received feedback and retrains the intelligence model means. The server analyzes the feedback using natural language processing means and extracts areas for improvement and problems. New analysis data is supplied to the intelligence model and retraining is performed.

[1781] input:

[1782] Feedback stored in the database

[1783] output:

[1784] Improved Intelligence Model

[1785] Operation:

[1786] Conducting feedback analysis and retraining process of the intelligence model

[1787] Through the above steps, this system realizes task handover that takes emotions into consideration, aiming to improve work efficiency and user satisfaction.

[1788] (Application example 2)

[1789] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1790] Conventional task handover systems lack the ability to effectively convey task know-how and the ability to appropriately adjust instructions based on the user's emotional state. This often leaves new operators feeling confused and frustrated, leading to reduced productivity and work efficiency. Furthermore, there is a lack of effective means for utilizing user feedback to improve the system's accuracy, which delays improvements to the task handover process.

[1791] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a user interface means for inputting business know-how, a natural language processing means for analyzing the business know-how, an artificial intelligence model means for learning the analyzed business know-how, an output interface means for providing business procedures using the artificial intelligence model, a feedback receiving means for receiving and analyzing feedback from the user, a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback, an emotion engine means for recognizing user emotions, and a means for adjusting business procedures based on the recognized user emotions. This makes it possible to provide appropriate instructions in real time according to the user's emotions during the business handover process, thereby improving productivity and business efficiency. Furthermore, the accuracy of the system can be continuously improved by utilizing user feedback and emotion data.

[1792] "Business know-how" refers to the knowledge and procedures required to carry out a specific business.

[1793] "User interface means" refers to the interface that a user uses to input business know-how into the system.

[1794] "Natural language processing means" refers to the techniques and processes used to parse meaning and context from text data.

[1795] "Artificial intelligence model means" refers to a machine learning model that learns from analyzed data and generates business procedures.

[1796] "Output interface means" refers to an interface for providing a business procedure to a user.

[1797] "Feedback receiving means" refers to a mechanism for receiving and analyzing feedback from a user.

[1798] "Retraining" refers to the process of retraining an AI model based on received feedback to improve its accuracy.

[1799] The "emotion engine means" refers to a mechanism for recognizing the user's emotions and responding or giving instructions according to those emotions.

[1800] The "means for adjusting the business procedure" refers to a mechanism for appropriately changing the method of providing the business procedure and the content thereof based on the recognized user's emotions.

[1801] The present invention relates to a system that uses a "Smart Factory Assistant" application that is installed on a factory robot. Hereinafter, an embodiment of the present invention will be specifically described.

[1802] Hardware and Software Configuration

[1803] The server uses the following hardware and software:

[1804] Hardware:

[1805] Factory robots

[1806] software:

[1807] Python libraries: transformers, EmotionRecognizer

[1808] Pre-trained AI models: BERT, GPT, etc.

[1809] System Operation

[1810] 1. Gathering business know-how:

[1811] A user inputs business know-how (e.g., "machine operating procedures") using a terminal installed in a factory robot. The input text data is collected via the user interface.

[1812] 2. Data analysis and AI model training:

[1813] The server analyzes the text data entered by the user using natural language processing. The analyzed data is extracted as business flow and important points. Based on this data, an artificial intelligence model (e.g., BERT) is used to train the system and understand specific procedures and points to note.

[1814] 3. Providing business procedures:

[1815] When a user requests a work procedure, the terminal installed on the factory robot displays instructions from the AI ​​model in real time, such as "Please set the material in the machine."

[1816] 4. Emotion recognition and regulation:

[1817] The emotion engine analyzes the user's voice and facial expression data to recognize the user's emotions in real time. Based on the recognized emotions, the system adjusts the work procedure. For example, if the user is confused, it provides detailed additional explanations.

[1818] 5. Feedback mechanism:

[1819] Users can input feedback into the system about any questions or problems they encounter while working. The server receives this feedback, analyzes it, and retrains the AI ​​model, allowing it to provide more accurate and detailed instructions to users from the next time onwards.

[1820] Specific examples

[1821] Example prompts for confused users:

[1822] "Press the red switch on the right. Then press and hold this button for three seconds."

[1823] Example prompt for angry users:

[1824] "Take a deep breath, and let's start again together."

[1825] The server integrates the above methods to provide a system for efficient and user-friendly task handover by factory robots. This system dynamically adjusts work procedures according to the user's emotions, improving work productivity and efficiency while reducing user stress.

[1826] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1827] Step 1:

[1828] The user inputs business know-how (e.g., "machine operating procedures") using a terminal installed on the factory robot. The input data is collected in text format and sent to the server. This allows the business know-how to be collected.

[1829] Input: Text data of business know-how

[1830] Output: Sending collected data

[1831] Step 2:

[1832] The server receives the business know-how sent by the user and analyzes it using natural language processing. Specifically, it tokenizes the text data and extracts important keywords and grammatical structures. This allows the business flow and key items to be identified.

[1833] Input: Text data of collected business know-how

[1834] Output: Parsed keywords and grammatical structures

[1835] Step 3:

[1836] The server trains an artificial intelligence model (e.g., BERT) on the analyzed business know-how. Specifically, the extracted keywords and grammatical structures are fed as input data to the AI ​​model, which then understands and infers business procedures. This allows the AI ​​model to learn the business know-how and store it as executable procedures.

[1837] Input: Parsed keywords and grammatical structures

[1838] Output: The trained AI model

[1839] Step 4:

[1840] When a user requests the provision of a business procedure, the device sends a request to the server. The server uses the trained AI model to generate instructions for the business procedure according to the user's request and sends them to the device, which displays them in real time.

[1841] Input: User's request to provide business procedures

[1842] Output: Generated work procedure instructions

[1843] Step 5:

[1844] The device collects the user's voice and facial expression data and recognizes the user's emotions in real time using an emotion engine means. The emotion engine analyzes changes in voice tone and facial expressions to identify the user's emotional state (e.g., confusion, anger).

[1845] Input: User's voice and facial expression data

[1846] Output: Identified user emotional state

[1847] Step 6:

[1848] The server adjusts the work procedure based on the user's recognized emotional state. For example, if the user is confused, it generates detailed additional explanations, and if the user is angry, it generates gentler explanations. This helps the user to perform the work appropriately.

[1849] Input: Identified emotional state of the user

[1850] Output: Coordinated work instructions

[1851] Step 7:

[1852] The user inputs feedback about any unclear points or problems that arise as they proceed with their work. The device sends this feedback to the server, which analyzes it and retrains the AI ​​model. This allows the device to provide more accurate and detailed instructions to the user next time.

[1853] Input: User feedback

[1854] Output: Retrained AI model

[1855] 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.

[1856] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1857] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1858] 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.

[1859] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1860] 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.

[1861] 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).

[1862] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1863] 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."

[1864] 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.

[1865] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1866] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1871] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1872] 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.

[1873] 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.

[1874] 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.

[1875] 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.

[1876] The following is further disclosed regarding the above embodiment.

[1877] (Claim 1)

[1878] a user interface means for inputting business know-how;

[1879] natural language processing means for analyzing the business know-how;

[1880] an artificial intelligence model means for learning the analyzed business know-how;

[1881] an output interface means for providing a business procedure using the artificial intelligence model;

[1882] feedback receiving means for receiving and analyzing feedback from a user;

[1883] a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback;

[1884] A system including:

[1885] (Claim 2)

[1886] The system according to claim 1, wherein a business procedure is guided based on the analyzed business know-how.

[1887] (Claim 3)

[1888] The system of claim 1 , further comprising: improving the accuracy of an artificial intelligence model based on the feedback.

[1889] "Example 1"

[1890] (Claim 1)

[1891] a user interface means for inputting business knowledge;

[1892] natural language processing means for analyzing the business knowledge;

[1893] a machine learning model means for learning the analyzed business knowledge;

[1894] an output interface means for providing a business procedure using the machine learning model;

[1895] an opinion receiving means for receiving and analyzing opinions from users;

[1896] a retraining means for retraining the machine learning model based on the analyzed opinions;

[1897] A system including:

[1898] (Claim 2)

[1899] The system according to claim 1, wherein a business procedure is guided based on the analyzed business knowledge.

[1900] (Claim 3)

[1901] The system of claim 1 , further comprising: improving the accuracy of a machine learning model based on the opinions.

[1902] "Application Example 1"

[1903] (Claim 1)

[1904] a user interface means for inputting business know-how;

[1905] natural language processing means for analyzing the business know-how;

[1906] an artificial intelligence model means for learning the analyzed business know-how;

[1907] an output interface means for providing a business procedure using the artificial intelligence model;

[1908] feedback receiving means for receiving and analyzing feedback from a user;

[1909] a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback;

[1910] a guide means for guiding the business procedure in real time through a smart device;

[1911] A system including:

[1912] (Claim 2)

[1913] The system according to claim 1, wherein a business procedure is guided based on the analyzed business know-how.

[1914] (Claim 3)

[1915] The system of claim 1 , further comprising: improving the accuracy of an artificial intelligence model based on the feedback.

[1916] "Example 2: Combining Emotion Engines"

[1917] (Claim 1)

[1918] an input means for inputting business know-how;

[1919] analysis means for analyzing the business know-how;

[1920] an intelligent model means for learning the analyzed business know-how;

[1921] an output means for providing a business procedure using the intelligence model;

[1922] A recognition means for recognizing an emotion of a user;

[1923] an adjustment means for adjusting work procedures based on the perceived emotions;

[1924] receiving means for receiving and analyzing feedback from users;

[1925] a re-learning means for re-learning the intelligence model based on the analyzed feedback;

[1926] A system including:

[1927] (Claim 2)

[1928] 2. The system according to claim 1, wherein the system guides a business procedure based on the analyzed business know-how and adjusts the business procedure according to the recognized user's emotions.

[1929] (Claim 3)

[1930] The system of claim 1 , further comprising: improving the accuracy of the intelligent model based on the feedback.

[1931] "Application example 2 when combining emotion engines"

[1932] (Claim 1)

[1933] a user interface means for inputting business know-how;

[1934] natural language processing means for analyzing the business know-how;

[1935] an artificial intelligence model means for learning the analyzed business know-how;

[1936] an output interface means for providing a business procedure using the artificial intelligence model;

[1937] feedback receiving means for receiving and analyzing feedback from a user;

[1938] a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback;

[1939] emotion engine means for recognizing the emotion of a user;

[1940] means for adjusting business procedures based on the recognized user emotions;

[1941] A system including:

[1942] (Claim 2)

[1943] 2. The system according to claim 1, wherein a business procedure is guided based on the analyzed business know-how, and further, appropriate instructions are provided according to the user's emotions using the emotion engine means.

[1944] (Claim 3)

[1945] 2. The system according to claim 1, wherein the accuracy of the artificial intelligence model is improved based on data relating to the user's emotions obtained from the feedback and emotion engine means. [Explanation of symbols]

[1946] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a user interface means for inputting business know-how; natural language processing means for analyzing the business know-how; an artificial intelligence model means for learning the analyzed business know-how; an output interface means for providing a business procedure using the artificial intelligence model; feedback receiving means for receiving and analyzing feedback from a user; a re-learning means for re-learning the artificial intelligence model based on the analyzed feedback; A system including:

2. The system according to claim 1 , wherein a business procedure is guided based on the analyzed business know-how.

3. The system of claim 1 , further comprising: improving the accuracy of an artificial intelligence model based on the feedback.

Images