system

Abstract

We provide the system. [Solution] A means of collecting past application data, preprocessing the data, and training a generated artificial intelligence model, A means of receiving information necessary for an application from the user in an interactive format, A means for automatically generating an application form based on received user input and a trained generative artificial intelligence model, A means to display the generated application form to the user and enable review and editing, A means of finally approving and submitting the application form that the user has reviewed, A means to automatically track the progress after the application is approved and notify the relevant departments, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, the in-house request application procedure has been very time-consuming and labor-intensive for applicants, especially complex and difficult to understand for new or less experienced employees. As a result, there have often been delays and mistakes in applications, leading to a decrease in the efficiency of the entire business. Furthermore, there has been a lack of a method for efficiently managing the progress and status of each request. It has been necessary to solve such problems and simplify and speed up the application procedure.

Means for Solving the Problems

[0005] This invention provides a system that trains an artificial intelligence model based on past application data and automatically generates approval application forms using information entered by the user. This system has a function to allow the user to review and edit the generated application form and supports the process of submitting the finally approved application form. Furthermore, by providing a function to correct the content of the application form by comparing it with business rules and a function to manage the progress on a dashboard, it reduces errors and delays and improves operational efficiency.

[0006] "Past application data" refers to the collection of information related to all approval requests made within the company to date.

[0007] A "generative artificial intelligence model" is an AI technology that uses data to mimic human intellectual behavior and automatically generate approval request forms.

[0008] "User input" refers to the information and data that a user provides in order to submit an application.

[0009] "Application form generation" is a process that automatically creates the necessary documents for an application based on user input and a generation artificial intelligence model.

[0010] "Review and editing" refers to the process of checking the generated application form and correcting or adjusting its contents.

[0011] "Business rules" are the norms and standards that must be followed in procedures and operations within a company.

[0012] A "dashboard" is a management screen that visually summarizes the progress and status of applications so that they can be seen at a glance.

[0013] "Approval and submission" refers to the act of the user finally reviewing the application and officially indicating their intention to proceed with the process.

[0014] "Progress tracking" is the process of managing and monitoring how far along an application is in its processing after it has been submitted. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system that trains an artificial intelligence model based on past application data and automatically generates approval application forms. A specific embodiment of this system is shown below.

[0037] First, the server collects past approval request data stored within the company. This data is compiled into a dataset and used as training material for an AI model. The dataset includes information such as the type of request, the amount, and the approver.

[0038] Next, if a user needs to submit an application, they use an interface installed on the terminal to enter the required information. This interface is designed to allow users to intuitively input information in an interactive format.

[0039] The server automatically generates approval requests using a generative artificial intelligence model based on information received from the user. In this process, the AI ​​utilizes learned historical data to create the most suitable application content for the input information. It also automatically checks whether the generated application conforms to business rules and makes corrections as needed.

[0040] The generated application form is provided to the user via their terminal, allowing them to review its contents. The user can preview the application and issue editing instructions as needed. This minimizes errors in the application form.

[0041] The final approved application is formally submitted upon user approval. Approved applications are tracked on the server, and notifications are automatically sent to the appropriate department.

[0042] This system significantly streamlines the approval process, allowing even less experienced employees to submit applications quickly and accurately. For example, when requesting the purchase of equipment needed for a new project, the user simply enters the equipment name, quantity, and budget, and the system automatically generates and submits the approval request. As a result, it achieves increased operational efficiency and reduced errors.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects past internal approval request data from the database and creates a training dataset for the AI ​​model. At this stage, the data is cleaned, incomplete records are removed, and rich information is compiled.

[0046] Step 2:

[0047] The server uses the dataset to train a generative artificial intelligence model. During training, it learns features and patterns used in past applications to build a model with high predictive accuracy.

[0048] Step 3:

[0049] Users enter the necessary information through the terminal's user interface to submit an approval request. This interface provides users with hints and formats to assist with the input process.

[0050] Step 4:

[0051] The terminal prepares the input data collected from the user for transfer to the authorized user, and formats the data, including performing data integrity checks.

[0052] Step 5:

[0053] The server automatically generates approval requests using an artificial intelligence model based on the formatted data. During generation, it verifies that the proposed content conforms to company regulations.

[0054] Step 6:

[0055] The terminal provides the user with a preview of the generated approval request form, allowing them to review the application details. It also includes a user interface that provides clear and easy-to-understand feedback to the user.

[0056] Step 7:

[0057] The user reviews the generated application form and specifies any points that need correction. Based on the feedback, the application is reprocessed.

[0058] Step 8:

[0059] The server formally submits the application after final confirmation and automatically sets up notifications for the relevant approval process. Progress tracking then begins.

[0060] Step 9:

[0061] The server periodically tracks the approval status and progress of applications and reports the status to administrators via a dashboard, including relevant data analysis.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] In companies and organizations, the document application process is time-consuming and labor-intensive, and prone to errors depending on the applicant's experience and understanding. Furthermore, the approval and progress management processes are time-consuming, making efficiency improvements essential. Another challenge is that the approval process can be delayed if the document content does not conform to business regulations.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for collecting historical document data and preprocessing the data to train a generative artificial intelligence model; means for interactively receiving information necessary for an application from an information provider; and means for automatically generating a document based on the received information provider input and the trained generative artificial intelligence model. This automates the document application process, minimizing the effort required from the information provider while enabling accurate and rapid document creation and approval.

[0067] "Past document data" refers to records of documents created and submitted within a company or organization to date, and serves as fundamental data for understanding specific processes and content.

[0068] A "generative artificial intelligence model" is a system that combines algorithms and data structures to generate new documents, trained through machine learning based on collected data.

[0069] An "information provider" is an individual or organization that inputs the information necessary for document applications and streamlines operations through system-based document generation.

[0070] "Interactive means of receiving information" refers to an interface or protocol designed to allow users to provide information to a system in a natural way.

[0071] "Means of generating documents" refers to a process or function that automatically creates documents in the appropriate format and content based on input from a recipient information provider and trained artificial intelligence.

[0072] "Business rules" refer to guidelines or standards that must be followed when carrying out business within a company or organization, and the content of the document must conform to these rules.

[0073] An "information display device" refers to a device or system that visually provides information such as the content and progress of generated data and documents, and is used by administrators to understand the situation.

[0074] This invention is a system that utilizes historical document data and automates the document application process using a generative artificial intelligence model. In this system, the server, terminal, and user each play their respective roles, enabling efficient document creation and management.

[0075] The server first collects historical document data stored in the company's internal systems. This data is extracted from the database and preprocessed as a training dataset for the AI ​​model. Specifically, data cleaning and labeling are performed to prepare the data so that the generated AI model can learn properly. This model is often implemented using platforms such as Python or Tensorflow®.

[0076] When a document application is required, the user uses a user interface provided on the terminal. This interface operates via a web browser and is designed to allow the user to interactively input application information. After entering the necessary information, the user sends it to the server.

[0077] The server automatically generates documents using a generative AI model based on information received from the user. The model analyzes the user's input information based on past data and proposes the optimal document content. The generated documents are checked by an algorithm to ensure consistency with business regulations, and the content is corrected if necessary.

[0078] The final generated document is displayed to the user via their device, allowing them to review and edit its content. The user previews the document, makes any necessary corrections, and then finally approves and submits it. This process allows users to quickly submit accurate documents through simple on-screen operations.

[0079] As a concrete example, consider a case where a user requests the purchase of equipment for a new project. The user inputs the need for "5 desktop computers and 5 monitors" into the terminal interface. Based on this information, the server uses an AI model to generate an appropriate approval document, which is then formally submitted after user confirmation.

[0080] An example of a prompt message might be, "Please generate the necessary approval request to purchase 10 printers and 20 ink cartridges for a new project." This allows the user to quickly request the generation of the required documents.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The server collects historical document data from internal systems. As input, it retrieves document information from a database. This information includes application type, amount, approver, etc. After data collection, data cleaning is performed to standardize numerical consistency and text formatting. This generates a training dataset for the AI ​​model to learn from.

[0084] Step 2:

[0085] Users enter the necessary application information using an interface on their device. This interface is designed to interactively guide users through information input by prompting them with questions. The specific information users enter includes the purpose of the application, specific items and quantities related to the application, and the budget. This becomes the input data for the interface.

[0086] Step 3:

[0087] The server receives application information submitted by the user and uses it as input to activate a generation AI model. Because the AI ​​model learns patterns based on past data, it generates the optimal application form from the input information. Data processing includes automatic field entry into document templates and customization based on relevant rules. The output of this process is an automatically generated application document.

[0088] Step 4:

[0089] The server checks whether the generated application form conforms to business rules. At this stage, the business rules engine is used to verify that the document content matches standard protocols and company norms. If violations are detected, the content is corrected using the automatic correction function. This completes the final document.

[0090] Step 5:

[0091] The final generated application form is sent from the server to the terminal and displayed to the user. The user can review the application form and make corrections directly on the terminal as needed. Input at this stage consists of user feedback and additional editing information. After final confirmation, the user approves and officially submits the application form with a single click.

[0092] Step 6:

[0093] The server stores formally approved applications in a database and tracks their progress using a management system. Furthermore, it automatically sends notifications to relevant departments and personnel. These notifications include the application details, approval status, and next actions. This ensures that all stakeholders share the latest information and can respond appropriately.

[0094] (Application Example 1)

[0095] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0096] Traditionally, electronic payment application and approval processes in companies are often performed manually, making them time-consuming and prone to errors. Furthermore, delays in approval and incomplete application content can reduce operational efficiency. Additionally, these processes are difficult for new employees to handle, requiring speed and accuracy.

[0097] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0098] In this invention, the server includes means for collecting past information, preprocessing the information, and training a generative artificial intelligence model; means for receiving content necessary for information processing from the user in an interactive format; and means for automatically generating information documents based on the received user input and the trained generative artificial intelligence model. This enables the automatic generation of electronic payment application forms based on past purchase data, streamlining the approval process and allowing for rapid processing with fewer errors.

[0099] "Past information" refers to data and records related to applications and purchases collected in the past.

[0100] "Preprocessing" refers to the process of organizing and transforming data into a format suitable for training artificial intelligence models.

[0101] A "generative artificial intelligence model" refers to a program that utilizes machine learning to automatically generate informational documents and application forms based on past information.

[0102] "User" refers to the individual or department responsible for inputting information using this system and reviewing and approving the generated information documents.

[0103] "Means of receiving information in an interactive format" refers to an interface that allows the user to interactively input information into the system.

[0104] "Information documents" refer to application forms and settlement documents that are automatically generated based on the information provided by the user.

[0105] The "approval process" refers to a series of steps taken to verify that informational documents are appropriate and to proceed with formal procedures.

[0106] "Means of tracking progress and notifying relevant departments" refers to the function of tracking the processing status of information documents and informing relevant parties in a timely manner.

[0107] To realize this invention, the server first collects historical information, preprocesses it, and trains a generative artificial intelligence model. The server is configured as a database server, storing data on past applications and purchases, and uses this data to train the model. For this training, machine learning libraries such as TensorFlow and PyTorch are used.

[0108] The terminal is responsible for collecting information related to applications and payments from the user. This terminal is equipped with a user interface for receiving information interactively, and is built on a web-based architecture using frameworks such as Flask. Through this interface, the user can input the necessary information and send it to the server.

[0109] The server receives user input data and supplies it to an artificial intelligence model to automatically generate informational documents. The AI ​​model utilizes learned historical data to create optimal documents and performs checks based on business rules. The generated informational documents are displayed to the user via their terminal. The user reviews the generated documents and edits them if necessary. Once the user approves the document, the server tracks the approval process and notifies the relevant departments of the progress. Notifications can be sent via email or chatbot.

[0110] As a concrete example, consider a scenario where an accounting department user submits a purchase request for new software. The user enters the software name, budget, and purpose into the interface. Upon receiving this information, the server's AI model automatically generates an appropriate request form. An example of a prompt message might be: "Based on past request data, please generate an electronic payment request form using the following information: Item to be purchased is X, budget is Y yen, purpose of use is Z." This system streamlines each stage of the electronic payment request process, reduces errors, and ensures a smoother process.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server collects historical information from the database. This includes data on past applications and purchases, and this information is preprocessed. Specifically, the server cleanses and standardizes the data, shaping it into a format suitable for training machine learning models. The input is the raw data from the database, and the output is a preprocessed dataset.

[0114] Step 2:

[0115] The server trains a generative artificial intelligence model using a preprocessed dataset. TensorFlow is used as the machine learning library to learn patterns in the data. The input is the preprocessed dataset, and the output is the trained AI model.

[0116] Step 3:

[0117] The user enters the necessary information for the application through a terminal. The terminal is equipped with an interface, allowing the user to input information interactively. The input here is the application information entered by the user, and the output is the user input data sent to the server.

[0118] Step 4:

[0119] The server validates the input data received from the user and automatically generates an application document based on a trained AI model. The input is user input data, and the output is the generated information document. At this time, data is provided to the AI ​​model using prompt statements, and an application form similar to past application data is generated.

[0120] Step 5:

[0121] The terminal displays the generated information document to the user. The user can review the displayed document and edit it as needed. The input here is the generated information document, and the output is the document reflecting the user's review and edits.

[0122] Step 6:

[0123] The user approves an informational document and sends it to the server. The server receives the approved document and notifies the relevant department. This is done using notification functions such as email or chatbots. The input is the user's approved document, and the output is the status update information of the notified relevant department.

[0124] Step 7:

[0125] The server tracks the progress of information documents and generates information that can be reported to administrators on a dashboard. The input is approved document data, and the output is a progress report displayed to administrators. This allows the system to understand the overall progress and enables efficient management.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] This invention improves the user experience by combining a system that automatically generates approval requests using a generative artificial intelligence model with an emotion engine that recognizes user emotions. A specific embodiment is described below.

[0128] The server, as before, collects past approval request data and trains a generative artificial intelligence model. The model learns the features and patterns necessary for generating application forms from the past data. This makes it possible to generate the optimal application form based on information directly entered by the user.

[0129] In addition, this system incorporates an emotion engine that recognizes and analyzes the user's emotions to adjust the conversational interface in the application process. When the user enters information, the terminal collects data such as voice, facial expressions, and input speed via the emotion engine. This emotion data is then used to infer the user's emotional state.

[0130] The server analyzes emotional data and, if a user is experiencing stress, assists the process by simplifying the application process or adding explanations to reduce the user's burden. This makes it possible to provide users with the most appropriate feedback in real time.

[0131] For example, when a user submits a purchase request for a new product, if they show signs of anxiety while entering the information, the system will sense their intention and display more detailed step-by-step instructions on the screen. Furthermore, the system will simplify the process when unnecessary steps are required, thereby improving user convenience.

[0132] Finally, once the user reviews and approves the generated application via their device, the server formally submits the application and sends progress data to the administrator's dashboard. This ensures a smooth application process and efficient management across the entire company. The system features a flexible design that optimizes the entire process while taking user experience into consideration.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server collects past internal approval request data from the database and preprocesses the data to create a training dataset for the AI ​​model. This cleans the data and extracts features, preparing it for accurate model learning.

[0136] Step 2:

[0137] The server trains a generative artificial intelligence model using a prepared dataset. This model learns patterns from past application data and has the ability to automatically generate the optimal application form based on user input.

[0138] Step 3:

[0139] The terminal prompts users who wish to apply to enter the necessary information interactively through its user interface. This interface includes devices such as a camera and microphone necessary for voice input and facial recognition.

[0140] Step 4:

[0141] The user enters the necessary information for the application (e.g., project name, budget, deadline) using the interface, while their natural facial expressions and voice are captured on the device via the camera and microphone.

[0142] Step 5:

[0143] The device sends user voice and facial expression data along with input information to an emotion engine, which then estimates the user's emotional state in real time. This emotion data is used to detect signs of stress, anxiety, and other emotional states.

[0144] Step 6:

[0145] The server receives data on the user's emotional state and adjusts the application generation process accordingly. For example, if the user shows anxiety, it provides additional information to guide them through the process more clearly.

[0146] Step 7:

[0147] The terminal displays a preview of the generated application form to the user and provides emotionally responsive feedback and suggestions. The interface layout and explanations are adjusted as needed to ensure the user can confidently review the application content.

[0148] Step 8:

[0149] The user reviews the previewed application and enters instructions for any necessary corrections into the terminal. Finally, if they are satisfied with the content of the application, they approve it.

[0150] Step 9:

[0151] The server formally submits approved applications and automatically notifies administrators and relevant departments according to the company's workflow. Simultaneously, user experience evaluations based on sentiment data are also recorded.

[0152] Step 10:

[0153] After an application is approved, the server tracks its progress and provides administrators with a visual overview of the status on a dashboard. This allows administrators to constantly monitor the efficiency of the entire process.

[0154] (Example 2)

[0155] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0156] Traditional application processes require users to accurately input information and create appropriate application forms, which is time-consuming and requires considerable effort. Furthermore, systems that do not consider user emotions can cause them stress and anxiety about the process. As a result, applications can proceed improperly or become inefficient.

[0157] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0158] In this invention, the server includes means for collecting historical data, preprocessing the information to train a generative model, receiving information from the user in an interactive format, and using an emotion analysis engine to infer the user's emotional state based on the input data and adjust the process accordingly. This reduces the user's input effort and enables an efficient and less stressful application process by adjusting the process according to their emotions.

[0159] "Historical data" refers to documents and information collected previously, which are used to train generative models.

[0160] "Preprocessing" refers to the process of organizing, shaping, and transforming raw data so that it can be efficiently handled by machine learning models.

[0161] A "generative model" is a model trained using artificial intelligence technology to automatically generate output documents that meet a specific purpose from a given input.

[0162] "Dialogue format" refers to a method of interaction with users, where information is entered and confirmed in a way that resembles question-and-answer sessions or conversations.

[0163] An "emotion analysis engine" is a system that analyzes and evaluates the emotional state of a user based on their input data—for example, voice, facial expressions, and input speed.

[0164] "Process adjustment" refers to the process of modifying the flow and format of the application process according to the user's needs and circumstances, based on the results of sentiment analysis.

[0165] "Progress tracking" is a management procedure that records the stage of the application process and provides the necessary information to the relevant departments.

[0166] This invention is a system that utilizes historical data and generates AI models to realize an efficient application process. Specifically, the server, terminal, and user elements work together to create a series of processes from data collection, model training, sentiment analysis, document generation, and final application submission.

[0167] The server is responsible for collecting past approval requests and related historical data, and pre-processing them. This makes the data suitable for training a generative AI model. The generative AI model is trained using machine learning techniques to automatically link the input information to the appropriate application form.

[0168] The terminal is a device that receives input from the user and is equipped with an emotion analysis engine. When the user operates the terminal, it senses information such as voice, facial expressions, and input speed in real time and analyzes the emotional state. For example, it uses a camera and microphone to capture facial expressions and voice tone during input.

[0169] The user is the entity that inputs information and submits various applications through a terminal. When the user enters specific prompt text, a generative model constructs the optimal application form from a large amount of data. Subsequently, an environment is provided where the user can review and edit the generated application form.

[0170] As a concrete example, imagine a scenario where a user enters a prompt such as, "I would like guidance on how to proceed with submitting a purchase request for equipment needed for an event scheduled for next month." In this case, the system generates the request form based on appropriate business rules and provides necessary guidance and process adjustments.

[0171] This system is designed to improve the user experience while taking into account the user's emotional state and increasing the overall efficiency of the process.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server collects historical data. Specifically, it extracts past application forms, approval history, and applicant information from the database. This input data is preprocessed to impute missing values ​​and standardize data formats. Finally, a clean dataset is generated and output as training data for an AI model.

[0175] Step 2:

[0176] The server trains a generative AI model using pre-processed data. The model uses pattern mining algorithms to learn features and patterns in the application forms. As a result of the training, a generative artificial intelligence model is created and output as preparation for the next process.

[0177] Step 3:

[0178] The terminal accepts input from the user. When the user starts an application, they input the necessary information in a conversational format, and the terminal generates prompts while sensing the user's voice, facial expressions, and input speed. It also performs sentiment analysis based on the user's input and sends the results to the server.

[0179] Step 4:

[0180] The server processes user input received from the terminal and sentiment analysis results. Using a generative AI model, it generates the optimal application form based on the user input. The output is the generated application form and, if necessary, adjusted feedback based on the sentiment analysis results.

[0181] Step 5:

[0182] The user views the application form generated on their device and edits it as needed. In this step, they review the generated content and relevant feedback, and then print the revised application form. Finally, the user approves the application form they have reviewed and edited.

[0183] Step 6:

[0184] The server formally submits user-approved applications and automatically checks for compliance with business rules. If there are no problems, it sends an approval notification to the progress tracking system and outputs progress data to the relevant departments. This manages the application process and provides feedback to the relevant departments.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] Conventional application processing systems failed to adequately address the emotional burden users experienced when entering information. This could lead to decreased work efficiency and accuracy, and errors such as incorrect input and operational mistakes were more likely to occur, especially in stressful situations. Furthermore, the lack of real-time process optimization based on the emotional state of the workers meant that improving the user experience was a challenge.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes means for collecting and preprocessing past data, means for receiving necessary information from users, means for generating documents based on the received information, and means for recognizing emotional data and adjusting the work process. This makes it possible to optimize the work process according to the emotional burden felt by the user and to proceed with application processing efficiently and accurately.

[0190] "Past data" refers to information and records accumulated up to the present, which serve as foundational material used for system learning and performance improvement.

[0191] A "machine learning model" is an algorithm or system that uses data to learn specific patterns and features, and then makes predictions and decisions in response to new information.

[0192] "User input" refers to the information and data that users provide to the system, which serves as the basic data for document generation and process optimization.

[0193] "Document generation" is the process by which a system automatically creates necessary documents and information based on specified conditions.

[0194] "Emotional data" refers to information that indicates the user's emotional state, and is obtained from sources such as voice, facial expressions, and behavior.

[0195] "Adjusting the work process" means modifying work procedures and operational flows to an optimal form according to the user's emotional state and other conditions.

[0196] This invention utilizes a system in which a server, a terminal, and a user work together. The server is responsible for collecting historical data, preprocessing it, and training a machine learning model. This enables the system to automatically generate documents based on new input information from the user.

[0197] Emotional data is collected through the terminal. The terminal uses hardware such as a camera and microphone to acquire information on the user's facial expressions, voice, and input speed, which is then analyzed by an emotion engine. Based on this, the server determines the user's emotional state and makes adjustments to optimize the work process. For example, if the server determines that the user is experiencing stress, it can simplify the task or provide detailed guidance.

[0198] As a concrete example, consider a scenario where a user is supervising product line work in a factory. If the server determines that the user is in an emotionally difficult situation, it can immediately display messages offering help or recommending breaks through the terminal. In this way, it is possible to provide real-time feedback and support based on the user's emotions, thereby improving work efficiency and safety.

[0199] When operating a generated AI model, prompts such as the following can be used: "Please indicate how to support the user if they express anxiety." Using such prompts allows the system to prepare to provide more appropriate support.

[0200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0201] Step 1:

[0202] The server collects historical data and performs data preprocessing. The input is application data in text format, and necessary features are extracted through denoising and normalization. The output is a dataset in a format suitable for training. This dataset is used to train the machine learning model.

[0203] Step 2:

[0204] The server trains a machine learning model using pre-processed data. The input is the dataset obtained in step 1, and the output is the establishment of a generative AI model for document generation. This AI model plays a role in supporting appropriate document generation based on new input from the user.

[0205] Step 3:

[0206] The device collects information about the user's voice, input speed, and facial expressions. This input is used as data for emotion recognition. Through waveform analysis of the voice data and image analysis of facial expressions, the user's emotional state is estimated using a specific algorithm. The estimated result is obtained as output.

[0207] Step 4:

[0208] The server makes adjustments to optimize the work process based on the emotional state obtained from the terminal. The input is the result of the emotional analysis in step 3, and the output is the adjusted work steps and instructions. Specifically, it generates simplified operating procedures and guides to reduce stress and displays them on the user's screen.

[0209] Step 5:

[0210] The user reviews the generated documents and guides and edits them as needed. The input is the output document from step 4, which is then reviewed and corrected by the user. The output is the final, verified document. At this stage, the user confirms that there are no problems with the document before proceeding to the next step.

[0211] Step 6:

[0212] The server approves the document confirmed by the user and makes a formal submission. The input is the confirmed document obtained in step 5, and the output is a notification to the relevant department and progress data. As a result, the document is processed according to the prescribed process, and the progress is reflected in the management dashboard.

[0213] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0214] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0219] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0220] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0221] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0222] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0223] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0224] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0225] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0227] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0228] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0229] This invention is a system that trains an artificial intelligence model based on past application data and automatically generates approval application forms. A specific embodiment of this system is shown below.

[0230] First, the server collects past approval request data stored within the company. This data is compiled into a dataset and used as training material for an AI model. The dataset includes information such as the type of request, the amount, and the approver.

[0231] Next, if a user needs to submit an application, they use an interface installed on the terminal to enter the required information. This interface is designed to allow users to intuitively input information in an interactive format.

[0232] The server automatically generates approval requests using a generative artificial intelligence model based on information received from the user. In this process, the AI ​​utilizes learned historical data to create the most suitable application content for the input information. It also automatically checks whether the generated application conforms to business rules and makes corrections as needed.

[0233] The generated application form is provided to the user via their terminal, allowing them to review its contents. The user can preview the application and issue editing instructions as needed. This minimizes errors in the application form.

[0234] The final approved application is formally submitted upon user approval. Approved applications are tracked on the server, and notifications are automatically sent to the appropriate department.

[0235] This system significantly streamlines the approval process, allowing even less experienced employees to submit applications quickly and accurately. For example, when requesting the purchase of equipment needed for a new project, the user simply enters the equipment name, quantity, and budget, and the system automatically generates and submits the approval request. As a result, it achieves increased operational efficiency and reduced errors.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server collects past internal approval request data from the database and creates a training dataset for the AI ​​model. At this stage, the data is cleaned, incomplete records are removed, and rich information is compiled.

[0239] Step 2:

[0240] The server uses the dataset to train a generative artificial intelligence model. During training, it learns features and patterns used in past applications to build a model with high predictive accuracy.

[0241] Step 3:

[0242] Users enter the necessary information through the terminal's user interface to submit an approval request. This interface provides users with hints and formats to assist with the input process.

[0243] Step 4:

[0244] The terminal prepares the input data collected from the user for transfer to the authorized user, and formats the data, including performing data integrity checks.

[0245] Step 5:

[0246] The server automatically generates approval requests using an artificial intelligence model based on the formatted data. During generation, it verifies that the proposed content conforms to company regulations.

[0247] Step 6:

[0248] The terminal provides the user with a preview of the generated approval request form, allowing them to review the application details. It also includes a user interface that provides clear and easy-to-understand feedback to the user.

[0249] Step 7:

[0250] The user reviews the generated application form and specifies any points that need correction. Based on the feedback, the application is reprocessed.

[0251] Step 8:

[0252] The server formally submits the application after final confirmation and automatically sets up notifications for the relevant approval process. Progress tracking then begins.

[0253] Step 9:

[0254] The server periodically tracks the approval status and progress of applications and reports the status to administrators via a dashboard, including relevant data analysis.

[0255] (Example 1)

[0256] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] In companies and organizations, the document application process is time-consuming and labor-intensive, and prone to errors depending on the applicant's experience and understanding. Furthermore, the approval and progress management processes are time-consuming, making efficiency improvements essential. Another challenge is that the approval process can be delayed if the document content does not conform to business regulations.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes means for collecting historical document data and preprocessing the data to train a generative artificial intelligence model; means for interactively receiving information necessary for an application from an information provider; and means for automatically generating a document based on the received information provider input and the trained generative artificial intelligence model. This automates the document application process, minimizing the effort required from the information provider while enabling accurate and rapid document creation and approval.

[0260] "Past document data" refers to records of documents created and submitted within a company or organization to date, and serves as fundamental data for understanding specific processes and content.

[0261] A "generative artificial intelligence model" is a system that combines algorithms and data structures to generate new documents, trained through machine learning based on collected data.

[0262] An "information provider" is an individual or organization that inputs the information necessary for document applications and plays a role in streamlining operations through system-based document generation.

[0263] "Interactive means of receiving information" refers to an interface or protocol designed to allow users to provide information to a system in a natural way.

[0264] "Means of generating documents" refers to a process or function that automatically creates documents in the appropriate format and content based on input from a recipient information provider and trained artificial intelligence.

[0265] "Business rules" refer to guidelines or standards that must be followed when carrying out business within a company or organization, and the content of the document must conform to these rules.

[0266] An "information display device" refers to a device or system that visually provides information such as the content and progress of generated data and documents, and is used by administrators to understand the situation.

[0267] This invention is a system that utilizes historical document data and automates the document application process using a generative artificial intelligence model. In this system, the server, terminal, and user each play their respective roles, enabling efficient document creation and management.

[0268] The server first collects historical document data stored in the company's internal systems. This data is extracted from the database and preprocessed as a training dataset for the AI ​​model. Specifically, data cleaning and labeling are performed to prepare the data so that the generating AI model can learn properly. This model is often implemented using platforms such as Python or TensorFlow.

[0269] When a document application is required, the user uses a user interface provided on the terminal. This interface operates via a web browser and is designed to allow the user to interactively input application information. After entering the necessary information, the user sends it to the server.

[0270] The server automatically generates documents using a generative AI model based on information received from the user. The model analyzes the user's input information based on past data and proposes the optimal document content. The generated documents are checked by an algorithm to ensure consistency with business regulations, and the content is corrected if necessary.

[0271] The final generated document is displayed to the user via their device, allowing them to review and edit its content. The user previews the document, makes any necessary corrections, and then finally approves and submits it. This process allows users to quickly submit accurate documents through simple on-screen operations.

[0272] As a concrete example, consider a case where a user requests the purchase of equipment for a new project. The user inputs the need for "5 desktop computers and 5 monitors" into the terminal interface. Based on this information, the server uses an AI model to generate an appropriate approval document, which is then formally submitted after user confirmation.

[0273] An example of a prompt message might be, "Please generate the necessary approval request to purchase 10 printers and 20 ink cartridges for a new project." This allows the user to quickly request the generation of the required documents.

[0274] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0275] Step 1:

[0276] The server collects historical document data from internal systems. As input, it retrieves document information from a database. This information includes application type, amount, approver, etc. After data collection, data cleaning is performed to standardize numerical consistency and text formatting. This generates a training dataset for the AI ​​model to learn from.

[0277] Step 2:

[0278] Users enter the necessary application information using an interface on their device. This interface is designed to interactively guide users through information input by prompting them with questions. The specific information users enter includes the purpose of the application, specific items and quantities related to the application, and the budget. This becomes the input data for the interface.

[0279] Step 3:

[0280] The server receives application information submitted by the user and uses it as input to activate a generation AI model. Because the AI ​​model learns patterns based on past data, it generates the optimal application form from the input information. Data processing includes automatic field entry into document templates and customization based on relevant rules. The output of this process is an automatically generated application document.

[0281] Step 4:

[0282] The server checks whether the generated application form complies with the business rules. At this stage, a business rule engine is used to check whether the content of the document conforms to the standard protocol or corporate norms. If a violation is detected, the automatic correction function is used to correct the content. As a result, the final document is completed.

[0283] Step 5:

[0284] The generated final application form is sent from the server to the terminal and displayed to the user. The user can check the content of the application form and make corrections directly on the terminal if necessary. The input at this stage is the user's feedback and additional editing information. After the final confirmation, the user can approve the application form with one click and submit it formally.

[0285] Step 6:

[0286] The server saves the formally approved application form in the database and tracks its progress in the management system. Furthermore, automatic notifications are sent to the relevant departments and responsible persons. The notifications include the application content, approval status, and next actions. This enables all relevant parties to share the latest information and respond appropriately.

[0287] (Application Example 1)

[0288] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0289] In enterprises, the electronic payment application and approval processes are often carried out manually in the past, which is time-consuming and error-prone. In addition, issues such as approval delays and deficiencies in application content lead to a decline in business efficiency. Furthermore, it is difficult for newly recruited employees to handle these processes, and quick and accurate processing is required.

[0290] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes means for collecting past information, preprocessing the information, and training a generative artificial intelligence model; means for receiving content necessary for information processing from the user in an interactive format; and means for automatically generating information documents based on the received user input and the trained generative artificial intelligence model. This enables the automatic generation of electronic payment application forms based on past purchase data, streamlining the approval process and allowing for rapid processing with fewer errors.

[0292] "Past information" refers to data and records related to applications and purchases collected in the past.

[0293] "Preprocessing" refers to the process of organizing and transforming data into a format suitable for training artificial intelligence models.

[0294] A "generative artificial intelligence model" refers to a program that utilizes machine learning to automatically generate informational documents and application forms based on past information.

[0295] "User" refers to the individual or department responsible for inputting information using this system and reviewing and approving the generated information documents.

[0296] "Means of receiving information in an interactive format" refers to an interface that allows the user to interactively input information into the system.

[0297] "Information documents" refer to application forms and settlement documents that are automatically generated based on the information provided by the user.

[0298] The "approval process" refers to a series of steps taken to verify that informational documents are appropriate and to proceed with formal procedures.

[0299] "Means of tracking progress and notifying relevant departments" refers to the function of tracking the processing status of information documents and informing relevant parties in a timely manner.

[0300] To realize this invention, the server first collects historical information, preprocesses it, and trains a generative artificial intelligence model. The server is configured as a database server, storing data on past applications and purchases, and uses this data to train the model. For this training, machine learning libraries such as TensorFlow and PyTorch are used.

[0301] The terminal is responsible for collecting information related to applications and payments from the user. This terminal is equipped with a user interface for receiving information interactively, and is built on a web-based architecture using frameworks such as Flask. Through this interface, the user can input the necessary information and send it to the server.

[0302] The server receives user input data and supplies it to an artificial intelligence model to automatically generate informational documents. The AI ​​model utilizes learned historical data to create optimal documents and performs checks based on business rules. The generated informational documents are displayed to the user via their terminal. The user reviews the generated documents and edits them if necessary. Once the user approves the document, the server tracks the approval process and notifies the relevant departments of the progress. Notifications can be sent via email or chatbot.

[0303] As a concrete example, consider a scenario where an accounting department user submits a purchase request for new software. The user enters the software name, budget, and purpose into the interface. Upon receiving this information, the server's AI model automatically generates an appropriate request form. An example of a prompt message might be: "Based on past request data, please generate an electronic payment request form using the following information: Item to be purchased is X, budget is Y yen, purpose of use is Z." This system streamlines each stage of the electronic payment request process, reduces errors, and ensures a smoother process.

[0304] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0305] Step 1:

[0306] The server collects past information from the database. This includes data on past applications and purchases, and preprocesses this information. As specific operations, the server performs data cleaning and format unification, and formats the data into a form suitable for training a machine learning model. The input is the raw data of the database, and the output is the preprocessed dataset.

[0307] Step 2:

[0308] The server trains a generated artificial intelligence model using the preprocessed dataset. Using TensorFlow as the machine learning library, it learns the patterns contained in the data. The input is the preprocessed dataset, and the output is the trained AI model.

[0309] Step 3:

[0310] The user inputs the information required for the application through the terminal. The terminal is equipped with an interface, and the user can input information in an interactive form. The input here is the application information input by the user, and the output is the user input data sent to the server.

[0311] Step 4:

[0312] The server verifies the input data received from the user and automatically generates an application document based on the trained AI model. The input is the user input data, and the output is the generated information document. At this time, prompt text is used to provide data to the AI model to generate an application form similar to past application data.

[0313] Step 5:

[0314] The terminal displays the generated information document to the user. The user can review the displayed document and edit it as needed. The input here is the generated information document, and the output is the document reflecting the user's review and edits.

[0315] Step 6:

[0316] The user approves an informational document and sends it to the server. The server receives the approved document and notifies the relevant department. This is done using notification functions such as email or chatbots. The input is the user's approved document, and the output is the status update information of the notified relevant department.

[0317] Step 7:

[0318] The server tracks the progress of information documents and generates information that can be reported to administrators on a dashboard. The input is approved document data, and the output is a progress report displayed to administrators. This allows the system to understand the overall progress and enables efficient management.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] This invention improves the user experience by combining a system that automatically generates approval requests using a generative artificial intelligence model with an emotion engine that recognizes user emotions. A specific embodiment is described below.

[0321] The server, as before, collects past approval request data and trains a generative artificial intelligence model. The model learns the features and patterns necessary for generating application forms from the past data. This makes it possible to generate the optimal application form based on information directly entered by the user.

[0322] In addition, this system incorporates an emotion engine that recognizes and analyzes the user's emotions to adjust the conversational interface in the application process. When the user enters information, the terminal collects data such as voice, facial expressions, and input speed via the emotion engine. This emotion data is then used to infer the user's emotional state.

[0323] The server analyzes emotional data and, if a user is experiencing stress, assists the process by simplifying the application process or adding explanations to reduce the user's burden. This makes it possible to provide users with the most appropriate feedback in real time.

[0324] For example, when a user submits a purchase request for a new product, if they show signs of anxiety while entering the information, the system will sense their intention and display more detailed step-by-step instructions on the screen. Furthermore, the system will simplify the process when unnecessary steps are required, thereby improving user convenience.

[0325] Finally, once the user reviews and approves the generated application via their device, the server formally submits the application and sends progress data to the administrator's dashboard. This ensures a smooth application process and efficient management across the entire company. The system features a flexible design that optimizes the entire process while taking user experience into consideration.

[0326] The following describes the processing flow.

[0327] Step 1:

[0328] The server collects past internal approval request data from the database and preprocesses the data to create a training dataset for the AI ​​model. This cleans the data and extracts features, preparing it for accurate model learning.

[0329] Step 2:

[0330] The server trains a generative artificial intelligence model using a prepared dataset. This model learns patterns from past application data and has the ability to automatically generate the optimal application form based on user input.

[0331] Step 3:

[0332] The terminal prompts users who wish to apply to enter the necessary information interactively through its user interface. This interface includes devices such as a camera and microphone necessary for voice input and facial recognition.

[0333] Step 4:

[0334] The user enters the necessary information for the application (e.g., project name, budget, deadline) using the interface, while their natural facial expressions and voice are captured on the device via the camera and microphone.

[0335] Step 5:

[0336] The device sends user voice and facial expression data along with input information to an emotion engine, which then estimates the user's emotional state in real time. This emotion data is used to detect signs of stress, anxiety, and other emotional states.

[0337] Step 6:

[0338] The server receives data on the user's emotional state and adjusts the application generation process accordingly. For example, if the user shows anxiety, it provides additional information to guide them through the process more clearly.

[0339] Step 7:

[0340] The terminal displays a preview of the generated application form to the user and provides emotionally responsive feedback and suggestions. The interface layout and explanations are adjusted as needed to ensure the user can confidently review the application content.

[0341] Step 8:

[0342] The user reviews the previewed application and enters instructions for any necessary corrections into the terminal. Finally, if they are satisfied with the content of the application, they approve it.

[0343] Step 9:

[0344] The server formally submits approved applications and automatically notifies administrators and relevant departments according to the company's workflow. Simultaneously, user experience evaluations based on sentiment data are also recorded.

[0345] Step 10:

[0346] After an application is approved, the server tracks its progress and provides administrators with a visual overview of the status on a dashboard. This allows administrators to constantly monitor the efficiency of the entire process.

[0347] (Example 2)

[0348] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0349] Traditional application processes require users to accurately input information and create appropriate application forms, which is time-consuming and requires considerable effort. Furthermore, systems that do not consider user emotions can cause them stress and anxiety about the process. As a result, applications can proceed improperly or become inefficient.

[0350] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0351] In this invention, the server includes means for collecting historical data, preprocessing the information to train a generative model, receiving information from the user in an interactive format, and using an emotion analysis engine to infer the user's emotional state based on the input data and adjust the process accordingly. This reduces the user's input effort and enables an efficient and less stressful application process by adjusting the process according to their emotions.

[0352] "Historical data" refers to documents and information collected previously, which are used to train generative models.

[0353] "Preprocessing" refers to the process of organizing, shaping, and transforming raw data so that it can be efficiently handled by machine learning models.

[0354] A "generative model" is a model trained using artificial intelligence technology to automatically generate output documents that meet a specific purpose from a given input.

[0355] "Dialogue format" refers to a method of interaction with users, where information is entered and confirmed in a way that resembles question-and-answer sessions or conversations.

[0356] An "emotion analysis engine" is a system that analyzes and evaluates the emotional state of a user based on their input data—for example, voice, facial expressions, and input speed.

[0357] "Process adjustment" refers to the process of modifying the flow and format of the application process according to the user's needs and circumstances, based on the results of sentiment analysis.

[0358] "Progress tracking" is a management procedure that records the stage of the application process and provides the necessary information to the relevant departments.

[0359] This invention is a system that utilizes historical data and generates AI models to realize an efficient application process. Specifically, the server, terminal, and user elements work together to create a series of processes from data collection, model training, sentiment analysis, document generation, and final application submission.

[0360] The server is responsible for collecting past approval requests and related historical data, and pre-processing them. This makes the data suitable for training a generative AI model. The generative AI model is trained using machine learning techniques to automatically link the input information to the appropriate application form.

[0361] The terminal is a device that receives input from the user and is equipped with an emotion analysis engine. When the user operates the terminal, it senses information such as voice, facial expressions, and input speed in real time and analyzes the emotional state. For example, it uses a camera and microphone to capture facial expressions and voice tone during input.

[0362] The user is the entity that inputs information and submits various applications through a terminal. When the user enters specific prompt text, a generative model constructs the optimal application form from a large amount of data. Subsequently, an environment is provided where the user can review and edit the generated application form.

[0363] As a concrete example, imagine a scenario where a user enters a prompt such as, "I would like guidance on how to proceed with submitting a purchase request for equipment needed for an event scheduled for next month." In this case, the system generates the request form based on appropriate business rules and provides necessary guidance and process adjustments.

[0364] This system is designed to improve the user experience while taking into account the user's emotional state and increasing the overall efficiency of the process.

[0365] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0366] Step 1:

[0367] The server collects historical data. Specifically, it extracts past application forms, approval history, and applicant information from the database. This input data is preprocessed to impute missing values ​​and standardize data formats. Finally, a clean dataset is generated and output as training data for an AI model.

[0368] Step 2:

[0369] The server trains a generative AI model using pre-processed data. The model uses pattern mining algorithms to learn features and patterns in the application forms. As a result of the training, a generative artificial intelligence model is created and output as preparation for the next process.

[0370] Step 3:

[0371] The terminal accepts input from the user. When the user starts an application, they input the necessary information in a conversational format, and the terminal generates prompts while sensing the user's voice, facial expressions, and input speed. It also performs sentiment analysis based on the user's input and sends the results to the server.

[0372] Step 4:

[0373] The server processes user input received from the terminal and sentiment analysis results. Using a generative AI model, it generates the optimal application form based on the user input. The output is the generated application form and, if necessary, adjusted feedback based on the sentiment analysis results.

[0374] Step 5:

[0375] The user views the application form generated on their device and edits it as needed. In this step, they review the generated content and relevant feedback, and then print the revised application form. Finally, the user approves the application form they have reviewed and edited.

[0376] Step 6:

[0377] The server formally submits user-approved applications and automatically checks for compliance with business rules. If there are no problems, it sends an approval notification to the progress tracking system and outputs progress data to the relevant departments. This manages the application process and provides feedback to the relevant departments.

[0378] (Application Example 2)

[0379] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0380] Conventional application processing systems failed to adequately address the emotional burden users experienced when entering information. This could lead to decreased work efficiency and accuracy, and errors such as incorrect input and operational mistakes were more likely to occur, especially in stressful situations. Furthermore, the lack of real-time process optimization based on the emotional state of the workers meant that improving the user experience was a challenge.

[0381] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0382] In this invention, the server includes means for collecting and preprocessing past data, means for receiving necessary information from users, means for generating documents based on the received information, and means for recognizing emotional data and adjusting the work process. This makes it possible to optimize the work process according to the emotional burden felt by the user and to proceed with application processing efficiently and accurately.

[0383] "Past data" refers to information and records accumulated up to the present, which serve as foundational material used for system learning and performance improvement.

[0384] A "machine learning model" is an algorithm or system that uses data to learn specific patterns and features, and then makes predictions and decisions in response to new information.

[0385] "User input" refers to the information and data that users provide to the system, which serves as the basic data for document generation and process optimization.

[0386] "Document generation" is the process by which a system automatically creates necessary documents and information based on specified conditions.

[0387] "Emotional data" refers to information that indicates the user's emotional state, and is obtained from sources such as voice, facial expressions, and behavior.

[0388] "Adjusting the work process" means modifying work procedures and operational flows to an optimal form according to the user's emotional state and other conditions.

[0389] This invention utilizes a system in which a server, a terminal, and a user work together. The server is responsible for collecting historical data, preprocessing it, and training a machine learning model. This enables the system to automatically generate documents based on new input information from the user.

[0390] Emotional data is collected through the terminal. The terminal uses hardware such as a camera and microphone to acquire information on the user's facial expressions, voice, and input speed, which is then analyzed by an emotion engine. Based on this, the server determines the user's emotional state and makes adjustments to optimize the work process. For example, if the server determines that the user is experiencing stress, it can simplify the task or provide detailed guidance.

[0391] As a concrete example, consider a scenario where a user is supervising product line work in a factory. If the server determines that the user is in an emotionally difficult situation, it can immediately display messages offering help or recommending breaks through the terminal. In this way, it is possible to provide real-time feedback and support based on the user's emotions, thereby improving work efficiency and safety.

[0392] When operating a generated AI model, prompts such as the following can be used: "Please indicate how to support the user if they express anxiety." Using such prompts allows the system to prepare to provide more appropriate support.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The server collects historical data and performs data preprocessing. The input is application data in text format, and necessary features are extracted through denoising and normalization. The output is a dataset in a format suitable for training. This dataset is used to train the machine learning model.

[0396] Step 2:

[0397] The server trains a machine learning model using pre-processed data. The input is the dataset obtained in step 1, and the output is the establishment of a generative AI model for document generation. This AI model plays a role in supporting appropriate document generation based on new input from the user.

[0398] Step 3:

[0399] The device collects information about the user's voice, input speed, and facial expressions. This input is used as data for emotion recognition. Through waveform analysis of the voice data and image analysis of facial expressions, the user's emotional state is estimated using a specific algorithm. The estimated result is obtained as output.

[0400] Step 4:

[0401] The server makes adjustments to optimize the work process based on the emotional state obtained from the terminal. The input is the result of the emotional analysis in step 3, and the output is the adjusted work steps and instructions. Specifically, it generates simplified operating procedures and guides to reduce stress and displays them on the user's screen.

[0402] Step 5:

[0403] The user reviews the generated documents and guides and edits them as needed. The input is the output document from step 4, which is then reviewed and corrected by the user. The output is the final, verified document. At this stage, the user confirms that there are no problems with the document before proceeding to the next step.

[0404] Step 6:

[0405] The server approves the document confirmed by the user and makes a formal submission. The input is the confirmed document obtained in step 5, and the output is a notification to the relevant department and progress data. As a result, the document is processed according to the prescribed process, and the progress is reflected in the management dashboard.

[0406] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0407] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0408] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0409] [Third Embodiment]

[0410] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0411] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0412] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0413] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0414] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0416] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0417] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0418] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0419] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0420] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0421] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0422] This invention is a system that trains an artificial intelligence model based on past application data and automatically generates approval application forms. A specific embodiment of this system is shown below.

[0423] First, the server collects past approval request data stored within the company. This data is compiled into a dataset and used as training material for an AI model. The dataset includes information such as the type of request, the amount, and the approver.

[0424] Next, if a user needs to submit an application, they use an interface installed on the terminal to enter the required information. This interface is designed to allow users to intuitively input information in an interactive format.

[0425] The server automatically generates approval requests using a generative artificial intelligence model based on information received from the user. In this process, the AI ​​utilizes learned historical data to create the most suitable application content for the input information. It also automatically checks whether the generated application conforms to business rules and makes corrections as needed.

[0426] The generated application form is provided to the user via their terminal, allowing them to review its contents. The user can preview the application and issue editing instructions as needed. This minimizes errors in the application form.

[0427] The final approved application is formally submitted upon user approval. Approved applications are tracked on the server, and notifications are automatically sent to the appropriate department.

[0428] This system significantly streamlines the approval process, allowing even less experienced employees to submit applications quickly and accurately. For example, when requesting the purchase of equipment needed for a new project, the user simply enters the equipment name, quantity, and budget, and the system automatically generates and submits the approval request. As a result, it achieves increased operational efficiency and reduced errors.

[0429] The following describes the processing flow.

[0430] Step 1:

[0431] The server collects past internal approval request data from the database and creates a training dataset for the AI ​​model. At this stage, the data is cleaned, incomplete records are removed, and rich information is compiled.

[0432] Step 2:

[0433] The server uses the dataset to train a generative artificial intelligence model. During training, it learns features and patterns used in past applications to build a model with high predictive accuracy.

[0434] Step 3:

[0435] Users enter the necessary information through the terminal's user interface to submit an approval request. This interface provides users with hints and formats to assist with the input process.

[0436] Step 4:

[0437] The terminal prepares the input data collected from the user for transfer to the authorized user, and formats the data, including performing data integrity checks.

[0438] Step 5:

[0439] The server automatically generates approval requests using an artificial intelligence model based on the formatted data. During generation, it verifies that the proposed content conforms to company regulations.

[0440] Step 6:

[0441] The terminal provides the user with a preview of the generated approval request form, allowing them to review the application details. It also includes a user interface that provides clear and easy-to-understand feedback to the user.

[0442] Step 7:

[0443] The user reviews the generated application form and specifies any points that need correction. Based on the feedback, the application is reprocessed.

[0444] Step 8:

[0445] The server formally submits the application after final confirmation and automatically sets up notifications for the relevant approval process. Progress tracking then begins.

[0446] Step 9:

[0447] The server periodically tracks the approval status and progress of applications and reports the status to administrators via a dashboard, including relevant data analysis.

[0448] (Example 1)

[0449] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0450] In companies and organizations, the document application process is time-consuming and labor-intensive, and prone to errors depending on the applicant's experience and understanding. Furthermore, the approval and progress management processes are time-consuming, making efficiency improvements essential. Another challenge is that the approval process can be delayed if the document content does not conform to business regulations.

[0451] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0452] In this invention, the server includes means for collecting historical document data and preprocessing the data to train a generative artificial intelligence model; means for interactively receiving information necessary for an application from an information provider; and means for automatically generating a document based on the received information provider input and the trained generative artificial intelligence model. This automates the document application process, minimizing the effort required from the information provider while enabling accurate and rapid document creation and approval.

[0453] "Past document data" refers to records of documents created and submitted within a company or organization to date, and serves as fundamental data for understanding specific processes and content.

[0454] A "generative artificial intelligence model" is a system that combines algorithms and data structures to generate new documents, trained through machine learning based on collected data.

[0455] An "information provider" is an individual or organization that inputs the information necessary for document applications and streamlines operations through system-based document generation.

[0456] "Interactive means of receiving information" refers to an interface or protocol designed to allow users to provide information to a system in a natural way.

[0457] "Means of generating documents" refers to a process or function that automatically creates documents in the appropriate format and content based on input from a recipient information provider and trained artificial intelligence.

[0458] "Business rules" refer to guidelines or standards that must be followed when carrying out business within a company or organization, and the content of the document must conform to these rules.

[0459] An "information display device" refers to a device or system that visually provides information such as the content and progress of generated data and documents, and is used by administrators to understand the situation.

[0460] This invention is a system that utilizes historical document data and automates the document application process using a generative artificial intelligence model. In this system, the server, terminal, and user each play their respective roles, enabling efficient document creation and management.

[0461] The server first collects historical document data stored in the company's internal systems. This data is extracted from the database and preprocessed as a training dataset for the AI ​​model. Specifically, data cleaning and labeling are performed to prepare the data so that the generating AI model can learn properly. This model is often implemented using platforms such as Python or TensorFlow.

[0462] When a document application is required, the user uses a user interface provided on the terminal. This interface operates via a web browser and is designed to allow the user to interactively input application information. After entering the necessary information, the user sends it to the server.

[0463] The server automatically generates documents using a generative AI model based on information received from the user. The model analyzes the user's input information based on past data and proposes the optimal document content. The generated documents are checked by an algorithm to ensure consistency with business regulations, and the content is corrected if necessary.

[0464] The final generated document is displayed to the user via their device, allowing them to review and edit its content. The user previews the document, makes any necessary corrections, and then finally approves and submits it. This process allows users to quickly submit accurate documents through simple on-screen operations.

[0465] As a concrete example, consider a case where a user requests the purchase of equipment for a new project. The user inputs the need for "5 desktop computers and 5 monitors" into the terminal interface. Based on this information, the server uses an AI model to generate an appropriate approval document, which is then formally submitted after user confirmation.

[0466] An example of a prompt message might be, "Please generate the necessary approval request to purchase 10 printers and 20 ink cartridges for a new project." This allows the user to quickly request the generation of the required documents.

[0467] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0468] Step 1:

[0469] The server collects historical document data from internal systems. As input, it retrieves document information from a database. This information includes application type, amount, approver, etc. After data collection, data cleaning is performed to standardize numerical consistency and text formatting. This generates a training dataset for the AI ​​model to learn from.

[0470] Step 2:

[0471] Users enter the necessary application information using an interface on their device. This interface is designed to interactively guide users through information input by prompting them with questions. The specific information users enter includes the purpose of the application, specific items and quantities related to the application, and the budget. This becomes the input data for the interface.

[0472] Step 3:

[0473] The server receives application information submitted by the user and uses it as input to activate a generation AI model. Because the AI ​​model learns patterns based on past data, it generates the optimal application form from the input information. Data processing includes automatic field entry into document templates and customization based on relevant rules. The output of this process is an automatically generated application document.

[0474] Step 4:

[0475] The server checks whether the generated application form conforms to business rules. At this stage, the business rules engine is used to verify that the document content matches standard protocols and company norms. If violations are detected, the content is corrected using the automatic correction function. This completes the final document.

[0476] Step 5:

[0477] The final generated application form is sent from the server to the terminal and displayed to the user. The user can review the application form and make corrections directly on the terminal as needed. Input at this stage consists of user feedback and additional editing information. After final confirmation, the user approves and officially submits the application form with a single click.

[0478] Step 6:

[0479] The server stores formally approved applications in a database and tracks their progress using a management system. Furthermore, it automatically sends notifications to relevant departments and personnel. These notifications include the application details, approval status, and next actions. This ensures that all stakeholders share the latest information and can respond appropriately.

[0480] (Application Example 1)

[0481] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0482] Traditionally, electronic payment application and approval processes in companies are often performed manually, making them time-consuming and prone to errors. Furthermore, delays in approval and incomplete application content can reduce operational efficiency. Additionally, these processes are difficult for new employees to handle, requiring speed and accuracy.

[0483] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0484] In this invention, the server includes means for collecting past information, preprocessing the information, and training a generative artificial intelligence model; means for receiving content necessary for information processing from the user in an interactive format; and means for automatically generating information documents based on the received user input and the trained generative artificial intelligence model. This enables the automatic generation of electronic payment application forms based on past purchase data, streamlining the approval process and allowing for rapid processing with fewer errors.

[0485] "Past information" refers to data and records related to applications and purchases collected in the past.

[0486] "Preprocessing" refers to the process of organizing and transforming data into a format suitable for training artificial intelligence models.

[0487] A "generative artificial intelligence model" refers to a program that utilizes machine learning to automatically generate informational documents and application forms based on past information.

[0488] "User" refers to the individual or department responsible for inputting information using this system and reviewing and approving the generated information documents.

[0489] "Means of receiving information in an interactive format" refers to an interface that allows the user to interactively input information into the system.

[0490] "Information documents" refer to application forms and settlement documents that are automatically generated based on the information provided by the user.

[0491] The "approval process" refers to a series of steps taken to verify that informational documents are appropriate and to proceed with formal procedures.

[0492] "Means of tracking progress and notifying relevant departments" refers to the function of tracking the processing status of information documents and informing relevant parties in a timely manner.

[0493] To realize this invention, the server first collects historical information, preprocesses it, and trains a generative artificial intelligence model. The server is configured as a database server, storing data on past applications and purchases, and uses this data to train the model. For this training, machine learning libraries such as TensorFlow and PyTorch are used.

[0494] The terminal is responsible for collecting information related to applications and payments from the user. This terminal is equipped with a user interface for receiving information interactively, and is built on a web-based architecture using frameworks such as Flask. Through this interface, the user can input the necessary information and send it to the server.

[0495] The server receives user input data and supplies it to an artificial intelligence model to automatically generate informational documents. The AI ​​model utilizes learned historical data to create optimal documents and performs checks based on business rules. The generated informational documents are displayed to the user via their terminal. The user reviews the generated documents and edits them if necessary. Once the user approves the document, the server tracks the approval process and notifies the relevant departments of the progress. Notifications can be sent via email or chatbot.

[0496] As a concrete example, consider a scenario where an accounting department user submits a purchase request for new software. The user enters the software name, budget, and purpose into the interface. Upon receiving this information, the server's AI model automatically generates an appropriate request form. An example of a prompt message might be: "Based on past request data, please generate an electronic payment request form using the following information: Item to be purchased is X, budget is Y yen, purpose of use is Z." This system streamlines each stage of the electronic payment request process, reduces errors, and ensures a smoother process.

[0497] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0498] Step 1:

[0499] The server collects historical information from the database. This includes data on past applications and purchases, and this information is preprocessed. Specifically, the server cleanses and standardizes the data, shaping it into a format suitable for training machine learning models. The input is the raw data from the database, and the output is a preprocessed dataset.

[0500] Step 2:

[0501] The server trains a generative artificial intelligence model using a preprocessed dataset. TensorFlow is used as the machine learning library to learn patterns in the data. The input is the preprocessed dataset, and the output is the trained AI model.

[0502] Step 3:

[0503] The user enters the necessary information for the application through a terminal. The terminal is equipped with an interface, allowing the user to input information interactively. The input here is the application information entered by the user, and the output is the user input data sent to the server.

[0504] Step 4:

[0505] The server validates the input data received from the user and automatically generates an application document based on a trained AI model. The input is user input data, and the output is the generated information document. At this time, data is provided to the AI ​​model using prompt statements, and an application form similar to past application data is generated.

[0506] Step 5:

[0507] The terminal displays the generated information document to the user. The user can review the displayed document and edit it as needed. The input here is the generated information document, and the output is the document reflecting the user's review and edits.

[0508] Step 6:

[0509] The user approves an informational document and sends it to the server. The server receives the approved document and notifies the relevant department. This is done using notification functions such as email or chatbots. The input is the user's approved document, and the output is the status update information of the notified relevant department.

[0510] Step 7:

[0511] The server tracks the progress of information documents and generates information that can be reported to administrators on a dashboard. The input is approved document data, and the output is a progress report displayed to administrators. This allows the system to understand the overall progress and enables efficient management.

[0512] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0513] This invention improves the user experience by combining a system that automatically generates approval requests using a generative artificial intelligence model with an emotion engine that recognizes user emotions. A specific embodiment is described below.

[0514] The server, as before, collects past approval request data and trains a generative artificial intelligence model. The model learns the features and patterns necessary for generating application forms from the past data. This makes it possible to generate the optimal application form based on information directly entered by the user.

[0515] In addition, this system incorporates an emotion engine that recognizes and analyzes the user's emotions to adjust the conversational interface in the application process. When the user enters information, the terminal collects data such as voice, facial expressions, and input speed via the emotion engine. This emotion data is then used to infer the user's emotional state.

[0516] The server analyzes emotional data and, if a user is experiencing stress, assists the process by simplifying the application process or adding explanations to reduce the user's burden. This makes it possible to provide users with the most appropriate feedback in real time.

[0517] For example, when a user submits a purchase request for a new product, if they show signs of anxiety while entering the information, the system will sense their intention and display more detailed step-by-step instructions on the screen. Furthermore, the system will simplify the process when unnecessary steps are required, thereby improving user convenience.

[0518] Finally, once the user reviews and approves the generated application via their device, the server formally submits the application and sends progress data to the administrator's dashboard. This ensures a smooth application process and efficient management across the entire company. The system features a flexible design that optimizes the entire process while taking user experience into consideration.

[0519] The following describes the processing flow.

[0520] Step 1:

[0521] The server collects past internal approval request data from the database and preprocesses the data to create a training dataset for the AI ​​model. This cleans the data and extracts features, preparing it for accurate model learning.

[0522] Step 2:

[0523] The server trains a generative artificial intelligence model using a prepared dataset. This model learns patterns from past application data and has the ability to automatically generate the optimal application form based on user input.

[0524] Step 3:

[0525] The terminal prompts users who wish to apply to enter necessary information interactively through its user interface. This interface includes devices such as a camera and microphone necessary for voice input and facial recognition.

[0526] Step 4:

[0527] The user enters the necessary information for the application (e.g., project name, budget, deadline) using the interface, while their natural facial expressions and voice are captured on the device via the camera and microphone.

[0528] Step 5:

[0529] The device sends user voice and facial expression data along with input information to an emotion engine, which then estimates the user's emotional state in real time. This emotion data is used to detect signs of stress, anxiety, and other emotional states.

[0530] Step 6:

[0531] The server receives data on the user's emotional state and adjusts the application generation process accordingly. For example, if the user shows anxiety, it provides additional information to guide them through the process more clearly.

[0532] Step 7:

[0533] The terminal displays a preview of the generated application form to the user and provides emotionally responsive feedback and suggestions. The interface layout and explanations are adjusted as needed to ensure the user can confidently review the application content.

[0534] Step 8:

[0535] The user reviews the previewed application and enters instructions for any necessary corrections into the terminal. Finally, if they are satisfied with the content of the application, they approve it.

[0536] Step 9:

[0537] The server formally submits approved applications and automatically notifies administrators and relevant departments according to the company's workflow. Simultaneously, user experience evaluations based on sentiment data are also recorded.

[0538] Step 10:

[0539] After an application is approved, the server tracks its progress and provides administrators with a visual overview of the status on a dashboard. This allows administrators to constantly monitor the efficiency of the entire process.

[0540] (Example 2)

[0541] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0542] Traditional application processes require users to accurately input information and create appropriate application forms, which is time-consuming and requires considerable effort. Furthermore, systems that do not consider user emotions can cause them stress and anxiety about the process. As a result, applications can proceed improperly or become inefficient.

[0543] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0544] In this invention, the server includes means for collecting historical data, preprocessing the information to train a generative model, receiving information from the user in an interactive format, and using an emotion analysis engine to infer the user's emotional state based on the input data and adjust the process accordingly. This reduces the user's input effort and enables an efficient and less stressful application process by adjusting the process according to their emotions.

[0545] "Historical data" refers to documents and information collected previously, which are used to train generative models.

[0546] "Preprocessing" refers to the process of organizing, shaping, and transforming raw data so that it can be efficiently handled by machine learning models.

[0547] A "generative model" is a model trained using artificial intelligence technology to automatically generate output documents that meet a specific purpose from a given input.

[0548] "Dialogue format" refers to a method of interaction with users, where information is entered and confirmed in a way that resembles question-and-answer sessions or conversations.

[0549] An "emotion analysis engine" is a system that analyzes and evaluates the emotional state of a user based on their input data—for example, voice, facial expressions, and input speed.

[0550] "Process adjustment" refers to the process of modifying the flow and format of the application process according to the user's needs and circumstances, based on the results of sentiment analysis.

[0551] "Progress tracking" is a management procedure that records the stage of the application process and provides the necessary information to the relevant departments.

[0552] This invention is a system that utilizes historical data and generates AI models to realize an efficient application process. Specifically, the server, terminal, and user elements work together to create a series of processes from data collection, model training, sentiment analysis, document generation, and final application submission.

[0553] The server is responsible for collecting past approval requests and related historical data, and pre-processing them. This makes the data suitable for training a generative AI model. The generative AI model is trained using machine learning techniques to automatically link the input information to the appropriate application form.

[0554] The terminal is a device that receives input from the user and is equipped with an emotion analysis engine. When the user operates the terminal, it senses information such as voice, facial expressions, and input speed in real time and analyzes the emotional state. For example, it uses a camera and microphone to capture facial expressions and voice tone during input.

[0555] The user is the entity that inputs information and submits various applications through a terminal. When the user enters specific prompt text, a generative model constructs the optimal application form from a large amount of data. Subsequently, an environment is provided where the user can review and edit the generated application form.

[0556] As a concrete example, imagine a scenario where a user enters a prompt such as, "I would like guidance on how to proceed with submitting a purchase request for equipment needed for an event scheduled for next month." In this case, the system generates the request form based on appropriate business rules and provides necessary guidance and process adjustments.

[0557] This system is designed to improve the user experience while taking into account the user's emotional state and increasing the overall efficiency of the process.

[0558] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0559] Step 1:

[0560] The server collects historical data. Specifically, it extracts past application forms, approval history, and applicant information from the database. This input data is preprocessed to impute missing values ​​and standardize data formats. Finally, a clean dataset is generated and output as training data for an AI model.

[0561] Step 2:

[0562] The server trains a generative AI model using pre-processed data. The model uses pattern mining algorithms to learn features and patterns in the application forms. As a result of the training, a generative artificial intelligence model is created and output as preparation for the next process.

[0563] Step 3:

[0564] The terminal accepts input from the user. When the user starts an application, they input the necessary information in a conversational format, and the terminal generates prompts while sensing the user's voice, facial expressions, and input speed. It also performs sentiment analysis based on the user's input and sends the results to the server.

[0565] Step 4:

[0566] The server processes user input received from the terminal and sentiment analysis results. Using a generative AI model, it generates the optimal application form based on the user input. The output is the generated application form and, if necessary, adjusted feedback based on the sentiment analysis results.

[0567] Step 5:

[0568] The user views the application form generated on their device and edits it as needed. In this step, they review the generated content and relevant feedback, and then print the revised application form. Finally, the user approves the application form they have reviewed and edited.

[0569] Step 6:

[0570] The server formally submits user-approved applications and automatically checks for compliance with business rules. If there are no problems, it sends an approval notification to the progress tracking system and outputs progress data to the relevant departments. This manages the application process and provides feedback to the relevant departments.

[0571] (Application Example 2)

[0572] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0573] Conventional application processing systems failed to adequately address the emotional burden users experienced when entering information. This could lead to decreased work efficiency and accuracy, and errors such as incorrect input and operational mistakes were more likely to occur, especially in stressful situations. Furthermore, the lack of real-time process optimization based on the emotional state of the workers meant that improving the user experience was a challenge.

[0574] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0575] In this invention, the server includes means for collecting and preprocessing past data, means for receiving necessary information from users, means for generating documents based on the received information, and means for recognizing emotional data and adjusting the work process. This makes it possible to optimize the work process according to the emotional burden felt by the user and to proceed with application processing efficiently and accurately.

[0576] "Past data" refers to information and records accumulated up to the present, which serve as foundational material used for system learning and performance improvement.

[0577] A "machine learning model" is an algorithm or system that uses data to learn specific patterns and features, and then makes predictions and decisions in response to new information.

[0578] "User input" refers to the information and data that users provide to the system, which serves as the basic data for document generation and process optimization.

[0579] "Document generation" is the process by which a system automatically creates necessary documents and information based on specified conditions.

[0580] "Emotional data" refers to information that indicates the user's emotional state, and is obtained from sources such as voice, facial expressions, and behavior.

[0581] "Adjusting the work process" means modifying work procedures and operational flows to an optimal form according to the user's emotional state and other conditions.

[0582] This invention utilizes a system in which a server, a terminal, and a user work together. The server is responsible for collecting historical data, preprocessing it, and training a machine learning model. This enables the system to automatically generate documents based on new input information from the user.

[0583] Emotional data is collected through the terminal. The terminal uses hardware such as a camera and microphone to acquire information on the user's facial expressions, voice, and input speed, which is then analyzed by an emotion engine. Based on this, the server determines the user's emotional state and makes adjustments to optimize the work process. For example, if the server determines that the user is experiencing stress, it can simplify the task or provide detailed guidance.

[0584] As a concrete example, consider a scenario where a user is supervising product line work in a factory. If the server determines that the user is in an emotionally difficult situation, it can immediately display messages offering help or recommending breaks through the terminal. In this way, it is possible to provide real-time feedback and support based on the user's emotions, thereby improving work efficiency and safety.

[0585] When operating a generated AI model, prompts such as the following can be used: "Please indicate how to support the user if they express anxiety." Using such prompts allows the system to prepare to provide more appropriate support.

[0586] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0587] Step 1:

[0588] The server collects historical data and performs data preprocessing. The input is application data in text format, and necessary features are extracted through denoising and normalization. The output is a dataset in a format suitable for training. This dataset is used to train the machine learning model.

[0589] Step 2:

[0590] The server trains a machine learning model using pre-processed data. The input is the dataset obtained in step 1, and the output is the establishment of a generative AI model for document generation. This AI model plays a role in supporting appropriate document generation based on new input from the user.

[0591] Step 3:

[0592] The device collects information about the user's voice, input speed, and facial expressions. This input is used as data for emotion recognition. Through waveform analysis of the voice data and image analysis of facial expressions, the user's emotional state is estimated using a specific algorithm. The estimated result is obtained as output.

[0593] Step 4:

[0594] The server makes adjustments to optimize the work process based on the emotional state obtained from the terminal. The input is the result of the emotional analysis in step 3, and the output is the adjusted work steps and instructions. Specifically, it generates simplified operating procedures and guides to reduce stress and displays them on the user's screen.

[0595] Step 5:

[0596] The user reviews the generated documents and guides and edits them as needed. The input is the output document from step 4, which is then reviewed and corrected by the user. The output is the final, verified document. At this stage, the user confirms that there are no problems with the document before proceeding to the next step.

[0597] Step 6:

[0598] The server approves the document confirmed by the user and makes a formal submission. The input is the confirmed document obtained in step 5, and the output is a notification to the relevant department and progress data. As a result, the document is processed according to the prescribed process, and the progress is reflected in the management dashboard.

[0599] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0600] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0601] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0602] [Fourth Embodiment]

[0603] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0604] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0605] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0606] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0607] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0608] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0609] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0610] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0611] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0612] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0613] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0614] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0615] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0616] This invention is a system that trains an artificial intelligence model based on past application data and automatically generates approval application forms. A specific embodiment of this system is shown below.

[0617] First, the server collects past approval request data stored within the company. This data is compiled into a dataset and used as training material for an AI model. The dataset includes information such as the type of request, the amount, and the approver.

[0618] Next, if a user needs to submit an application, they use an interface installed on the terminal to enter the required information. This interface is designed to allow users to intuitively input information in an interactive format.

[0619] The server automatically generates approval requests using a generative artificial intelligence model based on information received from the user. In this process, the AI ​​utilizes learned historical data to create the most suitable application content for the input information. It also automatically checks whether the generated application conforms to business rules and makes corrections as needed.

[0620] The generated application form is provided to the user via their terminal, allowing them to review its contents. The user can preview the application and issue editing instructions as needed. This minimizes errors in the application form.

[0621] The final approved application is formally submitted upon user approval. Approved applications are tracked on the server, and notifications are automatically sent to the appropriate department.

[0622] This system significantly streamlines the approval process, allowing even less experienced employees to submit applications quickly and accurately. For example, when requesting the purchase of equipment needed for a new project, the user simply enters the equipment name, quantity, and budget, and the system automatically generates and submits the approval request. As a result, it achieves increased operational efficiency and reduced errors.

[0623] The following describes the processing flow.

[0624] Step 1:

[0625] The server collects past internal approval request data from the database and creates a training dataset for the AI ​​model. At this stage, the data is cleaned, incomplete records are removed, and rich information is compiled.

[0626] Step 2:

[0627] The server uses the dataset to train a generative artificial intelligence model. During training, it learns features and patterns used in past applications to build a model with high predictive accuracy.

[0628] Step 3:

[0629] Users enter the necessary information through the terminal's user interface to submit an approval request. This interface provides users with hints and formats to assist with the input process.

[0630] Step 4:

[0631] The terminal prepares the input data collected from the user for transfer to the authorized user, and formats the data, including performing data integrity checks.

[0632] Step 5:

[0633] The server automatically generates approval requests using an artificial intelligence model based on the formatted data. During generation, it verifies that the proposed content conforms to company regulations.

[0634] Step 6:

[0635] The terminal provides the user with a preview of the generated approval request form, allowing them to review the application details. It also includes a user interface that provides clear and easy-to-understand feedback to the user.

[0636] Step 7:

[0637] The user reviews the generated application form and specifies any points that need correction. Based on the feedback, the application is reprocessed.

[0638] Step 8:

[0639] The server formally submits the application after final confirmation and automatically sets up notifications for the relevant approval process. Progress tracking then begins.

[0640] Step 9:

[0641] The server periodically tracks the approval status and progress of applications and reports the status to administrators via a dashboard, including relevant data analysis.

[0642] (Example 1)

[0643] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0644] In companies and organizations, the document application process is time-consuming and labor-intensive, and prone to errors depending on the applicant's experience and understanding. Furthermore, the approval and progress management processes are time-consuming, making efficiency improvements essential. Another challenge is that the approval process can be delayed if the document content does not conform to business regulations.

[0645] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0646] In this invention, the server includes means for collecting historical document data and preprocessing the data to train a generative artificial intelligence model; means for interactively receiving information necessary for an application from an information provider; and means for automatically generating a document based on the received information provider input and the trained generative artificial intelligence model. This automates the document application process, minimizing the effort required from the information provider while enabling accurate and rapid document creation and approval.

[0647] "Past document data" refers to records of documents created and submitted within a company or organization to date, and serves as fundamental data for understanding specific processes and content.

[0648] A "generative artificial intelligence model" is a system that combines algorithms and data structures to generate new documents, trained through machine learning based on collected data.

[0649] An "information provider" is an individual or organization that inputs the information necessary for document applications and streamlines operations through system-based document generation.

[0650] "Interactive means of receiving information" refers to an interface or protocol designed to allow users to provide information to a system in a natural way.

[0651] "Means of generating documents" refers to a process or function that automatically creates documents in the appropriate format and content based on input from a recipient information provider and trained artificial intelligence.

[0652] "Business rules" refer to guidelines or standards that must be followed when carrying out business within a company or organization, and the content of the document must conform to these rules.

[0653] An "information display device" refers to a device or system that visually provides information such as the content and progress of generated data and documents, and is used by administrators to understand the situation.

[0654] This invention is a system that utilizes historical document data and automates the document application process using a generative artificial intelligence model. In this system, the server, terminal, and user each play their respective roles, enabling efficient document creation and management.

[0655] The server first collects historical document data stored in the company's internal systems. This data is extracted from the database and preprocessed as a training dataset for the AI ​​model. Specifically, data cleaning and labeling are performed to prepare the data so that the generating AI model can learn properly. This model is often implemented using platforms such as Python or TensorFlow.

[0656] When a document application is required, the user uses a user interface provided on the terminal. This interface operates via a web browser and is designed to allow the user to interactively input application information. After entering the necessary information, the user submits it to the server.

[0657] The server automatically generates documents using a generative AI model based on information received from the user. The model analyzes the user's input information based on past data and proposes the optimal document content. The generated documents are checked by an algorithm to ensure consistency with business regulations, and the content is corrected if necessary.

[0658] The final generated document is displayed to the user via their device, allowing them to review and edit its content. The user previews the document, makes any necessary corrections, and then finally approves and submits it. This process allows users to quickly submit accurate documents through simple on-screen operations.

[0659] As a concrete example, consider a case where a user requests the purchase of equipment for a new project. The user inputs the need for "5 desktop computers and 5 monitors" into the terminal interface. Based on this information, the server uses an AI model to generate an appropriate approval document, which is then formally submitted after user confirmation.

[0660] An example of a prompt message might be, "Please generate the necessary approval request to purchase 10 printers and 20 ink cartridges for a new project." This allows the user to quickly request the generation of the required documents.

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1:

[0663] The server collects historical document data from internal systems. As input, it retrieves document information from a database. This information includes application type, amount, approver, etc. After data collection, data cleaning is performed to standardize numerical consistency and text formatting. This generates a training dataset for the AI ​​model to learn from.

[0664] Step 2:

[0665] Users enter the necessary application information using an interface on their device. This interface is designed to interactively guide users through information input by prompting them with questions. The specific information users enter includes the purpose of the application, specific items and quantities related to the application, and the budget. This becomes the input data for the interface.

[0666] Step 3:

[0667] The server receives application information submitted by the user and uses it as input to activate a generation AI model. Because the AI ​​model learns patterns based on past data, it generates the optimal application form from the input information. Data processing includes automatic field entry into document templates and customization based on relevant rules. The output of this process is an automatically generated application document.

[0668] Step 4:

[0669] The server checks whether the generated application form conforms to business rules. At this stage, the business rules engine is used to verify that the document content matches standard protocols and company norms. If violations are detected, the content is corrected using the automatic correction function. This completes the final document.

[0670] Step 5:

[0671] The final generated application form is sent from the server to the terminal and displayed to the user. The user can review the application form and make corrections directly on the terminal as needed. Input at this stage consists of user feedback and additional editing information. After final confirmation, the user approves and officially submits the application form with a single click.

[0672] Step 6:

[0673] The server stores formally approved applications in a database and tracks their progress using a management system. Furthermore, it automatically sends notifications to relevant departments and personnel. These notifications include the application details, approval status, and next actions. This ensures that all stakeholders share the latest information and can respond appropriately.

[0674] (Application Example 1)

[0675] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0676] Traditionally, electronic payment application and approval processes in companies are often performed manually, making them time-consuming and prone to errors. Furthermore, delays in approval and incomplete application content can reduce operational efficiency. Additionally, these processes are difficult for new employees to handle, requiring speed and accuracy.

[0677] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0678] In this invention, the server includes means for collecting past information, preprocessing the information, and training a generative artificial intelligence model; means for receiving content necessary for information processing from the user in an interactive format; and means for automatically generating information documents based on the received user input and the trained generative artificial intelligence model. This enables the automatic generation of electronic payment application forms based on past purchase data, streamlining the approval process and allowing for rapid processing with fewer errors.

[0679] "Past information" refers to data and records related to applications and purchases collected in the past.

[0680] "Preprocessing" refers to the process of organizing and transforming data into a format suitable for training artificial intelligence models.

[0681] A "generative artificial intelligence model" refers to a program that utilizes machine learning to automatically generate informational documents and application forms based on past information.

[0682] "User" refers to the individual or department responsible for inputting information using this system and reviewing and approving the generated information documents.

[0683] "Means of receiving information in an interactive format" refers to an interface that allows the user to interactively input information into the system.

[0684] "Information documents" refer to application forms and settlement documents that are automatically generated based on the information provided by the user.

[0685] The "approval process" refers to a series of steps taken to verify that informational documents are appropriate and to proceed with formal procedures.

[0686] "Means of tracking progress and notifying relevant departments" refers to the function of tracking the processing status of information documents and informing relevant parties in a timely manner.

[0687] To realize this invention, the server first collects historical information, preprocesses it, and trains a generative artificial intelligence model. The server is configured as a database server, storing data on past applications and purchases, and uses this data to train the model. For this training, machine learning libraries such as TensorFlow and PyTorch are used.

[0688] The terminal is responsible for collecting information related to applications and payments from the user. This terminal is equipped with a user interface for receiving information interactively, and is built on a web-based architecture using frameworks such as Flask. Through this interface, the user can input the necessary information and send it to the server.

[0689] The server receives user input data and supplies it to an artificial intelligence model to automatically generate informational documents. The AI ​​model utilizes learned historical data to create optimal documents and performs checks based on business rules. The generated informational documents are displayed to the user via their terminal. The user reviews the generated documents and edits them if necessary. Once the user approves the document, the server tracks the approval process and notifies the relevant departments of the progress. Notifications can be sent via email or chatbot.

[0690] As a concrete example, consider a scenario where an accounting department user submits a purchase request for new software. The user enters the software name, budget, and purpose into the interface. Upon receiving this information, the server's AI model automatically generates an appropriate request form. An example of a prompt message might be: "Based on past request data, please generate an electronic payment request form using the following information: Item to be purchased is X, budget is Y yen, purpose of use is Z." This system streamlines each stage of the electronic payment request process, reduces errors, and ensures a smoother process.

[0691] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0692] Step 1:

[0693] The server collects historical information from the database. This includes data on past applications and purchases, and this information is preprocessed. Specifically, the server cleanses and standardizes the data, shaping it into a format suitable for training machine learning models. The input is the raw data from the database, and the output is a preprocessed dataset.

[0694] Step 2:

[0695] The server trains a generative artificial intelligence model using a preprocessed dataset. TensorFlow is used as the machine learning library to learn patterns in the data. The input is the preprocessed dataset, and the output is the trained AI model.

[0696] Step 3:

[0697] The user enters the necessary information for the application through a terminal. The terminal is equipped with an interface, allowing the user to input information interactively. The input here is the application information entered by the user, and the output is the user input data sent to the server.

[0698] Step 4:

[0699] The server validates the input data received from the user and automatically generates an application document based on a trained AI model. The input is user input data, and the output is the generated information document. At this time, data is provided to the AI ​​model using prompt statements, and an application form similar to past application data is generated.

[0700] Step 5:

[0701] The terminal displays the generated information document to the user. The user can review the displayed document and edit it as needed. The input here is the generated information document, and the output is the document reflecting the user's review and edits.

[0702] Step 6:

[0703] The user approves an informational document and sends it to the server. The server receives the approved document and notifies the relevant department. This is done using notification functions such as email or chatbots. The input is the user's approved document, and the output is the status update information of the notified relevant department.

[0704] Step 7:

[0705] The server tracks the progress of information documents and generates information that can be reported to administrators on a dashboard. The input is approved document data, and the output is a progress report displayed to administrators. This allows the system to understand the overall progress and enables efficient management.

[0706] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0707] This invention improves the user experience by combining a system that automatically generates approval requests using a generative artificial intelligence model with an emotion engine that recognizes user emotions. A specific embodiment is described below.

[0708] The server, as before, collects past approval request data and trains a generative artificial intelligence model. The model learns the features and patterns necessary for generating application forms from the past data. This makes it possible to generate the optimal application form based on information directly entered by the user.

[0709] In addition, this system incorporates an emotion engine that recognizes and analyzes the user's emotions to adjust the conversational interface in the application process. When the user enters information, the terminal collects data such as voice, facial expressions, and input speed via the emotion engine. This emotion data is then used to infer the user's emotional state.

[0710] The server analyzes emotional data and, if a user is experiencing stress, assists the process by simplifying the application process or adding explanations to reduce the user's burden. This makes it possible to provide users with the most appropriate feedback in real time.

[0711] For example, when a user submits a purchase request for a new product, if they show signs of anxiety while entering the information, the system will sense their intention and display more detailed step-by-step instructions on the screen. Furthermore, the system will simplify the process when unnecessary steps are required, thereby improving user convenience.

[0712] Finally, once the user reviews and approves the generated application via their device, the server formally submits the application and sends progress data to the administrator's dashboard. This ensures a smooth application process and efficient management across the entire company. The system features a flexible design that optimizes the entire process while taking user experience into consideration.

[0713] The following describes the processing flow.

[0714] Step 1:

[0715] The server collects past internal approval request data from the database and preprocesses the data to create a training dataset for the AI ​​model. This cleans the data and extracts features, preparing it for accurate model learning.

[0716] Step 2:

[0717] The server trains a generative artificial intelligence model using a prepared dataset. This model learns patterns from past application data and has the ability to automatically generate the optimal application form based on user input.

[0718] Step 3:

[0719] The terminal prompts users who wish to apply to enter the necessary information interactively through its user interface. This interface includes devices such as a camera and microphone necessary for voice input and facial recognition.

[0720] Step 4:

[0721] The user enters the necessary information for the application (e.g., project name, budget, deadline) using the interface, while their natural facial expressions and voice are captured on the device via the camera and microphone.

[0722] Step 5:

[0723] The device sends user voice and facial expression data along with input information to an emotion engine, which then estimates the user's emotional state in real time. This emotion data is used to detect signs of stress, anxiety, and other emotional states.

[0724] Step 6:

[0725] The server receives data on the user's emotional state and adjusts the application generation process accordingly. For example, if the user shows anxiety, it provides additional information to guide them through the process more clearly.

[0726] Step 7:

[0727] The terminal displays a preview of the generated application form to the user and provides emotionally responsive feedback and suggestions. The interface layout and explanations are adjusted as needed to ensure the user can confidently review the application content.

[0728] Step 8:

[0729] The user reviews the previewed application and enters instructions for any necessary corrections into the terminal. Finally, if they are satisfied with the content of the application, they approve it.

[0730] Step 9:

[0731] The server formally submits approved applications and automatically notifies administrators and relevant departments according to the company's workflow. Simultaneously, user experience evaluations based on sentiment data are also recorded.

[0732] Step 10:

[0733] After an application is approved, the server tracks its progress and provides administrators with a visual overview of the status on a dashboard. This allows administrators to constantly monitor the efficiency of the entire process.

[0734] (Example 2)

[0735] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0736] Traditional application processes require users to accurately input information and create appropriate application forms, which is time-consuming and requires considerable effort. Furthermore, systems that do not consider user emotions can cause them stress and anxiety about the process. As a result, applications can proceed improperly or become inefficient.

[0737] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0738] In this invention, the server includes means for collecting historical data, preprocessing the information to train a generative model, receiving information from the user in an interactive format, and using an emotion analysis engine to infer the user's emotional state based on the input data and adjust the process accordingly. This reduces the user's input effort and enables an efficient and less stressful application process by adjusting the process according to their emotions.

[0739] "Historical data" refers to documents and information collected previously, which are used to train generative models.

[0740] "Preprocessing" refers to the process of organizing, shaping, and transforming raw data so that it can be efficiently handled by machine learning models.

[0741] A "generative model" is a model trained using artificial intelligence technology to automatically generate output documents that meet a specific purpose from a given input.

[0742] "Dialogue format" refers to a method of interaction with users, where information is entered and confirmed in a way that resembles question-and-answer sessions or conversations.

[0743] An "emotion analysis engine" is a system that analyzes and evaluates the emotional state of a user based on their input data—for example, voice, facial expressions, and input speed.

[0744] "Process adjustment" refers to the process of modifying the flow and format of the application process according to the user's needs and circumstances, based on the results of sentiment analysis.

[0745] "Progress tracking" is a management procedure that records the stage of the application process and provides the necessary information to the relevant departments.

[0746] This invention is a system that utilizes historical data and generates AI models to realize an efficient application process. Specifically, the server, terminal, and user elements work together to create a series of processes from data collection, model training, sentiment analysis, document generation, and final application submission.

[0747] The server is responsible for collecting past approval requests and related historical data, and pre-processing them. This makes the data suitable for training a generative AI model. The generative AI model is trained using machine learning techniques to automatically link the input information to the appropriate application form.

[0748] The terminal is a device that receives input from the user and is equipped with an emotion analysis engine. When the user operates the terminal, it senses information such as voice, facial expressions, and input speed in real time and analyzes the emotional state. For example, it uses a camera and microphone to capture facial expressions and voice tone during input.

[0749] The user is the entity that inputs information and submits various applications through a terminal. When the user enters specific prompt text, a generative model constructs the optimal application form from a large amount of data. Subsequently, an environment is provided where the user can review and edit the generated application form.

[0750] As a concrete example, imagine a scenario where a user enters a prompt such as, "I would like guidance on how to proceed with submitting a purchase request for equipment needed for an event scheduled for next month." In this case, the system generates the request form based on appropriate business rules and provides necessary guidance and process adjustments.

[0751] This system is designed to improve the user experience while taking into account the user's emotional state and increasing the overall efficiency of the process.

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] The server collects historical data. Specifically, it extracts past application forms, approval history, and applicant information from the database. This input data is preprocessed to impute missing values ​​and standardize data formats. Finally, a clean dataset is generated and output as training data for an AI model.

[0755] Step 2:

[0756] The server trains a generative AI model using pre-processed data. The model uses pattern mining algorithms to learn features and patterns in the application forms. As a result of the training, a generative artificial intelligence model is created and output as preparation for the next process.

[0757] Step 3:

[0758] The terminal accepts input from the user. When the user starts an application, they input the necessary information in a conversational format, and the terminal generates prompts while sensing the user's voice, facial expressions, and input speed. It also performs sentiment analysis based on the user's input and sends the results to the server.

[0759] Step 4:

[0760] The server processes user input received from the terminal and sentiment analysis results. Using a generative AI model, it generates the optimal application form based on the user input. The output is the generated application form and, if necessary, adjusted feedback based on the sentiment analysis results.

[0761] Step 5:

[0762] The user views the application form generated on their device and edits it as needed. In this step, they review the generated content and relevant feedback, and then print the revised application form. Finally, the user approves the application form they have reviewed and edited.

[0763] Step 6:

[0764] The server formally submits user-approved applications and automatically checks for compliance with business rules. If there are no problems, it sends an approval notification to the progress tracking system and outputs progress data to the relevant departments. This manages the application process and provides feedback to the relevant departments.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] Conventional application processing systems failed to adequately address the emotional burden users experienced when entering information. This could lead to decreased work efficiency and accuracy, and errors such as incorrect input and operational mistakes were more likely to occur, especially in stressful situations. Furthermore, the lack of real-time process optimization based on the emotional state of the workers meant that improving the user experience was a challenge.

[0768] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0769] In this invention, the server includes means for collecting and preprocessing past data, means for receiving necessary information from users, means for generating documents based on the received information, and means for recognizing emotional data and adjusting the work process. This makes it possible to optimize the work process according to the emotional burden felt by the user and to proceed with application processing efficiently and accurately.

[0770] "Past data" refers to information and records accumulated up to the present, which serve as foundational material used for system learning and performance improvement.

[0771] A "machine learning model" is an algorithm or system that uses data to learn specific patterns and features, and then makes predictions and decisions in response to new information.

[0772] "User input" refers to the information and data that users provide to the system, which serves as the basic data for document generation and process optimization.

[0773] "Document generation" is the process by which a system automatically creates necessary documents and information based on specified conditions.

[0774] "Emotional data" refers to information that indicates the user's emotional state, and is obtained from sources such as voice, facial expressions, and behavior.

[0775] "Adjusting the work process" means modifying work procedures and operational flows to an optimal form according to the user's emotional state and other conditions.

[0776] This invention utilizes a system in which a server, a terminal, and a user work together. The server is responsible for collecting historical data, preprocessing it, and training a machine learning model. This enables the system to automatically generate documents based on new input information from the user.

[0777] Emotional data is collected through the terminal. The terminal uses hardware such as a camera and microphone to acquire information on the user's facial expressions, voice, and input speed, which is then analyzed by an emotion engine. Based on this, the server determines the user's emotional state and makes adjustments to optimize the work process. For example, if the server determines that the user is experiencing stress, it can simplify the task or provide detailed guidance.

[0778] As a concrete example, consider a scenario where a user is supervising product line work in a factory. If the server determines that the user is in an emotionally difficult situation, it can immediately display messages offering help or recommending breaks through the terminal. In this way, it is possible to provide real-time feedback and support based on the user's emotions, thereby improving work efficiency and safety.

[0779] When operating a generated AI model, prompts such as the following can be used: "Please indicate how to support the user if they express anxiety." Using such prompts allows the system to prepare to provide more appropriate support.

[0780] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0781] Step 1:

[0782] The server collects historical data and performs data preprocessing. The input is application data in text format, and necessary features are extracted through denoising and normalization. The output is a dataset in a format suitable for training. This dataset is used to train the machine learning model.

[0783] Step 2:

[0784] The server trains a machine learning model using pre-processed data. The input is the dataset obtained in step 1, and the output is the establishment of a generative AI model for document generation. This AI model plays a role in supporting appropriate document generation based on new input from the user.

[0785] Step 3:

[0786] The device collects information about the user's voice, input speed, and facial expressions. This input is used as data for emotion recognition. Through waveform analysis of the voice data and image analysis of facial expressions, the user's emotional state is estimated using a specific algorithm. The estimated result is obtained as output.

[0787] Step 4:

[0788] The server makes adjustments to optimize the work process based on the emotional state obtained from the terminal. The input is the result of the emotional analysis in step 3, and the output is the adjusted work steps and instructions. Specifically, it generates simplified operating procedures and guides to reduce stress and displays them on the user's screen.

[0789] Step 5:

[0790] The user reviews the generated documents and guides and edits them as needed. The input is the output document from step 4, which is then reviewed and corrected by the user. The output is the final, verified document. At this stage, the user confirms that there are no problems with the document before proceeding to the next step.

[0791] Step 6:

[0792] The server approves the document confirmed by the user and makes a formal submission. The input is the confirmed document obtained in step 5, and the output is a notification to the relevant department and progress data. As a result, the document is processed according to the prescribed process, and the progress is reflected in the management dashboard.

[0793] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0794] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0795] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0796] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0797] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0798] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0799] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0800] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0801] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0802] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0803] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0804] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0805] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0806] 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.

[0807] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0808] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0809] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0810] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0811] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0812] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0813] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0814] The following is further disclosed regarding the embodiments described above.

[0815] (Claim 1)

[0816] A means of collecting past application data, preprocessing the data, and training a generated artificial intelligence model,

[0817] A means of receiving information necessary for an application from the user in an interactive format,

[0818] A means for automatically generating an application form based on received user input and a trained generative artificial intelligence model,

[0819] A means to display the generated application form to the user and enable review and editing,

[0820] A means of finally approving and submitting the application form that the user has reviewed,

[0821] A means to automatically track the progress after the application is approved and notify the relevant departments,

[0822] A system that includes this.

[0823] (Claim 2)

[0824] The system according to claim 1, which has a function to check whether the contents of an application form are in accordance with business rules and to correct the contents as necessary.

[0825] (Claim 3)

[0826] The system according to claim 1, comprising a function to generate data that allows administrators to report the progress of an application on a dashboard.

[0827] "Example 1"

[0828] (Claim 1)

[0829] A means of collecting historical document data, preprocessing the data, and training a generative artificial intelligence model,

[0830] A means of receiving information necessary for the application from the information provider in a dialogue format,

[0831] A means for automatically generating documents based on received information provider input and a trained generative artificial intelligence model,

[0832] A means of displaying the generated document to the information provider and enabling review and editing,

[0833] The means by which the information provider has reviewed the documents and ultimately approved and submitted them,

[0834] A means to automatically track progress and notify relevant departments after document approval,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, which has a function to check whether the content of a document is consistent with business regulations and to correct the content as necessary.

[0838] (Claim 3)

[0839] The system according to claim 1, comprising a function to generate data that can be reported to an administrator on an information display device regarding the progress of a document.

[0840] "Application Example 1"

[0841] (Claim 1)

[0842] A means of collecting past information, preprocessing the information, and training a generative artificial intelligence model,

[0843] A means of receiving information necessary for processing from the user in an interactive format,

[0844] A means for automatically generating information documents based on received user input and a trained generative artificial intelligence model,

[0845] A means for displaying the generated information document to the user and enabling review and editing,

[0846] A means for the user to finally approve and submit the information documents they have reviewed,

[0847] A means to automatically track progress and notify relevant departments after approval of information documents,

[0848] A means of automatically generating electronic payment application forms based on past purchase data and managing the approval process,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, which includes a function to check whether the content of an informational document matches business conditions and to correct the content as necessary.

[0852] (Claim 3)

[0853] The system according to claim 1, comprising a function to generate information that can be reported to an administrator on a display screen regarding the progress of information documents.

[0854] "Example 2 of combining an emotion engine"

[0855] (Claim 1)

[0856] A means of collecting historical data, preprocessing the information, and training a generative model,

[0857] A means of receiving information from users in an interactive format,

[0858] A means for automatically generating documents based on received user input and a trained generative model,

[0859] A means to display the generated document to the user and enable review and editing,

[0860] A means for users to finally approve and submit the documents they have reviewed,

[0861] A means of using an emotion analysis engine to infer the user's emotional state based on input data and adjust the process accordingly,

[0862] A means to automatically track progress and notify relevant departments after document approval,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which includes a function to check whether the content of a document is consistent with business rules and to correct the content as necessary.

[0866] (Claim 3)

[0867] The system according to claim 1, comprising a function to generate data that can be reported to an administrator on a display screen regarding the progress of a document.

[0868] "Application example 2 when combining with an emotional engine"

[0869] (Claim 1)

[0870] Methods for collecting historical data, preprocessing the data, and training machine learning models,

[0871] A means of receiving necessary information from users in an interactive format,

[0872] A means for automatically generating documents based on received user input and a trained machine learning model,

[0873] A means to display the generated document to the user and enable review and modification,

[0874] A means for users to finally approve and submit the documents they have reviewed,

[0875] A means to automatically track progress and notify relevant departments after document approval,

[0876] A means of recognizing workers' emotional data and adjusting the work process,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, which includes a function to check whether the content of the generated document is consistent with the business regulations and to correct the content as necessary.

[0880] (Claim 3)

[0881] The system according to claim 1, comprising a function to generate data that can be reported to the administrator on an administration screen regarding the progress of a document. [Explanation of Symbols]

[0882] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past application data, preprocessing the data, and training a generated artificial intelligence model, A means of receiving information necessary for an application from the user in an interactive format, A means for automatically generating an application form based on received user input and a trained generative artificial intelligence model, A means to display the generated application form to the user and enable review and editing, A means of finally approving and submitting the application form that the user has reviewed, A means to automatically track the progress after the application is approved and notify the relevant departments, A system that includes this.

2. The system according to claim 1, which has a function to check whether the contents of an application form are in accordance with business rules and to correct the contents as necessary.

3. The system according to claim 1, comprising a function to generate data that allows administrators to report the progress of application forms on a dashboard.

Images