system

Abstract

We provide the system. [Solution] A means of searching for past documents related to business operations from a knowledge database, A method for automatically generating quotation documents using generation AI, A means of sending and displaying the generated quotation document on the user's terminal, A means of receiving revisions from the user terminal and creating the final document, 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 method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] According to this, the "Problems to be Solved by the Invention" and "Means for Solving the Problems" in the patent specification have been created.

[0005] In modern back-office operations, the task of creating templates is frequently performed. However, the conventional manual creation method is time-consuming and labor-intensive, and there is a problem of reduced work efficiency. Also, when using generative AI, security risks increase due to the need to access external data. In view of such a situation, there is a need for means to efficiently and securely generate documents using past knowledge data and within a closed in-house environment.

Means for Solving the Problems

[0006] This invention relates to a system that searches a knowledge database for past documents related to business operations and automatically generates a draft of a new document using a generation AI. This system stores past business documents in a knowledge database and ensures security by accessing them in a closed environment. Furthermore, the generation AI learns the content and structure of past documents and generates new documents based on that. The generated document is sent to the user's terminal, and the final document is completed when the user inputs revisions. This reduces the workload and enables efficient document creation.

[0007] Understood. I have created definitions of key terms to be included in the claims, following the format below.

[0008] ---

[0009] A "knowledge database" is a database that stores past business documents and knowledge, and is used to search for and retrieve necessary information.

[0010] "Past documents related to business operations" refers to documents and reports created in the past that are related to back-office operations.

[0011] "Generative AI" is an artificial intelligence system that learns from past data and automatically generates new documents.

[0012] "Automatically generating quotation documents" refers to the process where AI automatically creates an initial draft of a new document based on user input and referencing similar past data.

[0013] A "user terminal" refers to a computer or device used to access the system.

[0014] A "closed environment" is a secure environment where external access is restricted and data is exchanged only internally.

[0015] A "quotation document" is a document that describes the results and evaluations predicted based on specific information.

[0016] A "template" refers to a fixed format used when creating a document.

[0017] "Filtering" refers to the process of selecting necessary information from search results.

[0018] "Document format" refers to the format (e.g., PDF or Word format) when saving a document.

Brief Explanation of Drawings

[0019] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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.

[0023] 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.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] 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).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0041] ---

[0042] This invention relates to a system for streamlining the creation of drafts in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The following is a natural language description of how this system works.

[0043] In the system of the present invention, the user first accesses the system using a terminal and requests the creation of a draft of a specific business document. Specifically, the user selects an option such as "Create a draft of a failure report" through the system's dedicated interface and enters the necessary information.

[0044] The server receives requests from users and accesses the knowledge database to search for relevant documents from the past. This knowledge database stores a large amount of document data related to back-office operations and is managed in a closed environment, ensuring security. Based on the request, the server filters the data for the specified period and the system in which the problem occurred, extracting the most relevant document data.

[0045] The extracted data is passed to a generation AI. The generation AI automatically generates a new draft based on the content and structure of past documents. This is done by filling in the necessary information based on templates and formats of past incident reports.

[0046] The generated draft is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0047] Finally, the document, after the user has made revisions and additions, is saved on the device. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0048] As a concrete example, consider the workflow when a user creates a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as an overview of the outage, the scope of impact, and the results of the cause investigation. The user receives this draft, adds and modifies details, and completes the final report.

[0049] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations, saving time and effort, and enabling the generation of high-quality documents.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The user logs into the system using their terminal and selects the "Create a draft of the incident report" option. The user then enters information about the period in question and the system where the problem occurred.

[0053] Step 2:

[0054] The terminal sends user input information to the server. The server receives this request and parses its contents.

[0055] Step 3:

[0056] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0057] Step 4:

[0058] The server extracts data and passes it to the generation AI. The generation AI automatically generates a new draft document based on the content and structure of past documents.

[0059] Step 5:

[0060] The AI ​​generates a draft document which is then returned to the server. The server organizes and formats this data and sends it to the user's terminal.

[0061] Step 6:

[0062] The terminal displays the draft document it received to the user. The user uses a text editor to review the document's contents and make corrections or additions as needed.

[0063] Step 7:

[0064] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal then converts this final document to a document format (PDF or Word).

[0065] Step 8:

[0066] The terminal uploads the final document to the server. The server then stores this document again in the knowledge database, making it available as reference data for the future.

[0067] The above outlines the series of processing steps involved in the system generating a draft document and completing the final document. This allows users to efficiently obtain high-quality documents.

[0068] (Example 1)

[0069] 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."

[0070] Traditional document creation processes in back-office operations often involve manual editing and creation, which is time-consuming and labor-intensive, thus creating a need for increased efficiency. Furthermore, document quality tends to vary, making it difficult to maintain consistency and accuracy. This invention aims to solve these problems.

[0071] 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.

[0072] In this invention, the server includes means for a user to request the creation of a specific business document using a terminal; means for the server to receive the request and search and extract relevant past documents from a knowledge database; means for the server to send a prompt message to a generation AI model and automatically generate a draft of a new document; means for sending and displaying the generated draft on the user's terminal; and means for receiving revisions from the user's terminal and creating the final document. This streamlines the time and effort required for document creation and enables the generation of high-quality, consistent documents.

[0073] A "terminal" is a device used by a user to access a system, and usually refers to electronic devices such as computers and smartphones.

[0074] A "user" refers to an individual or group that uses a system to create specific business documents.

[0075] A "server" refers to a central management system that receives requests from users and handles access to knowledge databases and integration with generated AI models.

[0076] A "knowledge database" refers to a database designed to store past business documents and allow for specific searches and extractions.

[0077] A "generative AI model" refers to an artificial intelligence model that learns the content and structure of past documents and automatically generates a draft of a new document based on that learning.

[0078] A "prompt statement" refers to an input statement used to instruct a generative AI model to create a draft of a new document.

[0079] A "draft" is an incomplete document automatically generated by a generative AI model, serving as the foundation for the user to create the final document.

[0080] This invention relates to a system for improving the efficiency of document creation in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The operation and specific examples of this system are described below.

[0081] System Overview

[0082] The system of this invention has the following main functions:

[0083] 1. User input of document creation request

[0084] 2. Server receives requests and extracts data from the knowledge database.

[0085] 3. Generating a draft of a new document using a generative AI model.

[0086] 4. Server-generated draft submission and display

[0087] 5. User review, modification, and addition to the draft.

[0088] 6. Saving the final document and storing it in the database.

[0089] Hardware and software to be used

[0090] Device: A computer or smartphone used by a user.

[0091] Server: A data server used to operate the central management system.

[0092] Knowledge database: A database that stores past business documents.

[0093] Generative AI model: An AI model used for learning and generating documents.

[0094] Operation details

[0095] User input of request

[0096] Users log in to the system using a terminal and request document creation through a dedicated interface. For example, they might select the option to "create a draft of an incident report" and enter necessary information such as the date and time of the incident and the affected systems.

[0097] The server receives requests and extracts data from the knowledge database.

[0098] The server receives requests from users and accesses the knowledge database. It filters past relevant document data from the knowledge database and extracts documents that are highly relevant to the specified period or issue.

[0099] Generating draft documents using a generative AI model.

[0100] Based on the extracted data, the server sends prompt messages to the generative AI model. The generative AI model has learned the content and structure of past documents and automatically generates a draft of a new document based on that.

[0101] Examples of specific prompt messages:

[0102] "Please create a draft of the incident report based on the following data. The incident occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was a system downtime, and the cause is estimated to be server overload."

[0103] Server-generated draft transmission and display

[0104] The generated draft is sent from the server to the user's terminal. The user receives this draft on their terminal and displays it in a dedicated text editor.

[0105] User review, modification, and addition to the draft.

[0106] Users review the draft displayed on their device and make changes or additions as needed. For example, they can input or correct details of new issues or countermeasures.

[0107] Saving the final document and storing it in the database.

[0108] The final document, after revisions and additions have been made, is saved on the device. It is then uploaded to the server and stored in the knowledge database. Users can choose to save the document in PDF or Word format.

[0109] Specific example

[0110] This example illustrates how a user can create a "Report on Last Week's System Outage." The user enters information such as the date and time of the outage and the affected systems, then submits a request. The server searches the knowledge database for relevant outage reports, and a generation AI model creates a draft of a new document. This draft includes an overview of the outage, the scope of its impact, and the results of the root cause investigation. The user receives this draft and adds or modifies details to complete the final report.

[0111] As a result of these processes, the system of the present invention streamlines document creation in back-office operations, saving time and effort, and enabling the generation of high-quality, consistent documents.

[0112] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0113] Step 1:

[0114] The user logs into the system's dedicated interface using a terminal and requests document creation. Specifically, they select the option to "Create a draft of the incident report" and enter information such as the date and time of the incident, the name of the affected system, and a summary. The input data provided is: Date and time of incident "October 5, 2023", Name of affected system "XYZ system", Summary "System down".

[0115] Step 2:

[0116] The server receives a request from the user. Here, the server parses the HTTP POST request and extracts its contents. The extracted data includes information such as the date and time of the failure, the name of the affected system, and a summary. This is stored in an internal data structure and used for the next processing step.

[0117] Step 3:

[0118] The server uses the extracted data to query the knowledge database. It generates an SQL query to search and extract relevant historical document data based on a specified period and system name. As a result of this query, similar incident reports are extracted. For example, it outputs "Historical Incident Report Data".

[0119] Step 4:

[0120] The server creates prompt statements for the generating AI model based on the extracted data. The generating AI model receives past failure report data along with the prompt statements. A specific prompt statement will be used: "Please create a draft failure report based on the following data. The failure occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was system downtime, and the cause is estimated to be server overload." The prompt statements and related document data are provided as input data to the AI ​​model.

[0121] Step 5:

[0122] The generation AI model generates a draft of a new document based on the prompt text and input data. This is a process that automatically creates a new document following the templates and formats of past documents. The generated draft includes information such as the date and time of the failure, the scope of impact, and the results of the root cause investigation. The output is a "generated failure report draft".

[0123] Step 6:

[0124] The server sends the generated draft to the user's terminal in real time. The server sends the generated draft in JSON format to the terminal, and the terminal parses the received JSON data and displays it in a dedicated text editor. Specifically, it sends the "generated draft of the incident report".

[0125] Step 7:

[0126] The user reviews the draft generated in a text editor on their terminal and makes modifications and additions as needed. For example, they input and modify details of new problems, causes, and countermeasures. After the user completes their work, they save the modified document data. The modified and added document information is provided as input data.

[0127] Step 8:

[0128] The user saves the final document, after making any revisions or additions, on their device and then uploads it to the server. The server stores the final document in a knowledge database, making it available as reference data for the future. For example, users can choose to save the document in PDF or Word format. Once the saved final document is stored in the knowledge database, the "finally saved document" is obtained as output data.

[0129] The above outlines the system's processing steps, with each step described in detail, including the specific actions of the input and output.

[0130] (Application Example 1)

[0131] 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."

[0132] Traditional methods for inventory management and sales report creation in physical stores often involve manual processes, requiring significant time and effort, and can lead to data errors and omissions. Furthermore, efficient business operations require fast and accurate document creation, but a suitable system for this purpose has not existed. This invention aims to solve these problems and provide a system for streamlining and automating inventory management and sales report creation in physical stores.

[0133] 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.

[0134] In this invention, the server includes means for searching past documents related to business operations from a knowledge database, means for automatically generating inventory management documents and sales report documents using generation AI, means for transmitting and displaying the generated inventory management documents and sales report documents on a user terminal, and means for receiving revisions from the user terminal and creating the final document. This enables efficient and accurate document creation in physical stores.

[0135] A "knowledge database" is a database that stores past documents related to business operations and is managed in a closed environment.

[0136] "Generative AI" is artificial intelligence that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[0137] "Past documents related to business operations" refers to documents related to back-office operations in physical stores, such as inventory management and sales reports.

[0138] "User terminals" refer to devices such as smartphones and tablets used by employees in physical stores.

[0139] An "inventory management document" is a document used to manage and report the inventory status of products in a physical store.

[0140] A "sales report document" is a report that compiles sales information from physical stores.

[0141] "Correction details" refers to corrections or additional information in the final document sent from the user's terminal.

[0142] A "final document" is a document that has been completed and edited on the user's terminal.

[0143] This invention relates to a system for streamlining and automating inventory management and sales report creation in physical stores. This system primarily consists of a server, user terminals, a knowledge database, and a generating AI. The following specifically describes the operation of this system.

[0144] First, users access the system using user devices such as smartphones or tablets at physical stores. When creating inventory reports or sales reports, users select options such as "Create last month's inventory management report" through a dedicated interface and enter the necessary information, such as the report period and the store ID.

[0145] When the server receives a request from a user, it accesses the knowledge database to search for relevant documents from the past. This knowledge database contains a large amount of past inventory management documents and sales report documents, and is managed in a closed environment accessible only to authorized personnel. Based on the request, the server filters the data for the specified period and store, and extracts the most relevant document data.

[0146] The extracted document data is passed to a generating AI. This AI learns the content and structure of past documents and automatically generates drafts of new inventory management documents and sales report documents based on that learning. For example, it might use a past inventory report template as a base and fill in inventory quantities and sales information for each product item.

[0147] The generated draft is sent from the server to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they can add information about newly arrived products or the impact of special promotions.

[0148] Finally, the document, after the user has made revisions and additions, is saved on the user's terminal. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0149] As a concrete example, let's consider the workflow when a user creates a "last month's inventory report." The user enters the report period and store ID, and submits the request. The server searches and extracts relevant inventory reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as inventory quantity for each product, order history, and sales information. The user receives it, adds and modifies details, and completes the final report.

[0150] An example of a prompt message is: "To create last month's inventory report, generate a draft of the new report based on data from January 1, 2023 to January 31, 2023."

[0151] The above is a detailed description of embodiments of the present invention.

[0152] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0153] Step 1:

[0154] Users access the system using smartphones or tablets in physical stores and submit requests to create necessary business documents (e.g., inventory reports and sales reports). Through a dedicated interface, users input information such as the report's target period and store ID. This input is treated as request data sent to the server.

[0155] Step 2:

[0156] The server analyzes the request data received from the user. Based on conditions such as the type of report entered (inventory report or sales report), the target period, and the store ID, it searches the knowledge database for relevant past documents. Specifically, it filters this data to extract highly relevant past inventory management documents and sales report documents.

[0157] Step 3:

[0158] The server passes the historical document data extracted as search results to the generating AI. The generating AI learns the content and structure of these historical documents and automatically generates a draft of a new document. The input for this step is the extracted document data, and the output is a draft of a newly generated inventory management document or sales report document.

[0159] Step 4:

[0160] The server sends a draft generated by the AI ​​to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed. A dedicated text editor is provided on the user's terminal that allows for modifications and additions. The input is the generated draft document, and the output is the modified / added document.

[0161] Step 5:

[0162] The user saves the final document, after making revisions and additions, from their terminal. The final document is then converted to a specific document format (e.g., PDF or Word) as needed and uploaded to the server. The server then stores the final document back in the knowledge database for future reference. The input is the revised / added document, and the output is the final document stored in the knowledge database.

[0163] The above outlines the specific processing steps for a system that streamlines and automates inventory management and sales reporting in physical stores.

[0164] 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.

[0165] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0166] ---

[0167] This invention relates to a system for streamlining the creation of drafts in back-office operations and for generating documents while considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and by combining them with an emotion engine, it achieves advanced document creation.

[0168] First, the user accesses the system using a terminal and requests the creation of a draft of a specific business document. The user selects an option, such as "Create a draft of an incident report," through the system's dedicated interface and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0169] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0170] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[0171] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0172] Once the user has made revisions and additions, the document is saved on the device as the final document. This final document is converted to a document format (e.g., PDF or Word) as needed. It can also be uploaded to the server, where it is stored again in the knowledge database and used as reference data for the future. At this time, the sentiment data collected by the sentiment engine is also added to the knowledge database, which will help improve the accuracy of future document generation.

[0173] As a concrete example, consider a user creating a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. At this stage, the document's content is adjusted based on the user's emotional data. For example, if the user is feeling stressed, the generated document will be concise and clear, designed to reduce the user's mental burden. The user receives this draft and adds and modifies details to complete the final report.

[0174] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and, by taking user emotions into consideration, enables the creation of higher-quality documents.

[0175] The following describes the processing flow.

[0176] Step 1:

[0177] A user logs into the system using a terminal and requests the creation of a draft of a specific business document. For example, they might select the "Create a draft of an incident report" option and enter information about the period and affected systems. At this time, the emotion engine recognizes the user's emotions in real time from their input actions, voice, and facial expressions, and records this data.

[0178] Step 2:

[0179] The terminal sends user input information and sentiment data to the server. The server receives this request and parses its contents. The request contains basic information for creating a draft and user sentiment data.

[0180] Step 3:

[0181] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0182] Step 4:

[0183] The server passes the extracted data and sentiment data to the generating AI. The generating AI automatically generates a new draft document based on the content and structure of past documents, as well as the user's sentiment data. In this process, the tone and content of the document are adjusted to take sentiment data into consideration.

[0184] Step 5:

[0185] The AI ​​generates a draft document which is then returned to the server. The server reviews this data and sends it to the user's terminal. The document incorporates expressions and structures that are adapted to the user's emotions.

[0186] Step 6:

[0187] The terminal displays a draft document it received to the user. The user reviews the displayed draft document and uses a text editor to modify or add to its contents. For example, they might enter details, causes, and countermeasures for a newly occurring problem.

[0188] Step 7:

[0189] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal converts this final document to a document format (e.g., PDF or Word) and sends it to the server.

[0190] Step 8:

[0191] The server receives the final document and stores it in the knowledge database. The sentiment data collected by the sentiment engine is also added to the knowledge database and used as reference data for future document generation.

[0192] The above outlines the series of processing steps involved in a system incorporating an emotion engine, from generating a draft document to completing the final document. This allows users to obtain high-quality documents efficiently and with minimal psychological burden.

[0193] (Example 2)

[0194] 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".

[0195] Conventional automated document generation systems rely solely on past document data, which limits their ability to generate documents that reflect user emotions. This makes it difficult to provide documents suitable for situations where users are likely to experience stress or for specific emotional states.

[0196] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for searching past documents related to business from a knowledge database, means for automatically generating documents based on user sentiment data using generation AI, and means for transmitting and displaying the generated documents on a user terminal. This makes it possible to automatically generate documents that take user sentiment into consideration.

[0197] A "knowledge database" is a data storage system that stores past business documents and related data and manages them in a closed environment.

[0198] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to learn from past documents and related data, and automatically generates new documents.

[0199] A "user terminal" is a hardware device, such as a computer or mobile device, that a user uses to access and operate a system.

[0200] An "emotion engine" refers to software or algorithms used to analyze and collect user emotional data in real time.

[0201] "Emotional data" refers to data about the user's emotional state collected and analyzed by the emotion engine.

[0202] "Automatic generation" refers to the process by which a generation AI automatically creates new documents based on pre-learned data, using user input and sentiment data.

[0203] A "closed environment" refers to a secure, access-restricted environment that is accessible only to specific users or system administrators.

[0204] "Modification details" refers to data that indicates the additions and changes made by the user to the generated document.

[0205] This invention relates to a system that streamlines document generation in back-office operations and generates high-quality documents by considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and achieves advanced document generation by combining them with an emotion engine.

[0206] System Configuration

[0207] This system uses the following main hardware and software.

[0208] Hardware: Client PCs, mobile devices, server machines

[0209] Software: Sentiment engine (e.g., Sentiment Analysis API), knowledge database (e.g., MySQL®), generative AI (e.g., OpenAI®, GPT-4®), document format conversion tool (e.g., Adobe Acrobat)

[0210] Operating procedures and specific examples

[0211] First, the user accesses the system using a terminal (e.g., a PC or mobile device) and requests the creation of a draft of a specific business document. The user logs into the system's dedicated interface, selects an option such as "Create a draft of an incident report," and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0212] Data transmission and analysis

[0213] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0214] Document generation process

[0215] The extracted data is passed to a generative AI. The generative AI (e.g., OpenAI GPT-4) automatically generates a new draft document based on the content and structure of past documents, as well as the collected sentiment data. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process generates a user-friendly document.

[0216] Document review and correction

[0217] The generated draft document is sent back from the server to the terminal. The terminal receives this data and displays it to the user. For example, if a user is creating a "Report on last week's system failure," they would review the generated draft and modify or add new details about the failure, its cause, and countermeasures using a text editor.

[0218] Saving the final document and closing the process.

[0219] Documents that have been edited or added to by the user are saved on the device as the final document. Documents can be converted to PDF or Word format as needed. They can also be uploaded to the server, where they are stored again in the knowledge database and used as reference data for the future. At this time, sentiment data collected by the sentiment engine is also added to the knowledge database, helping to improve the accuracy of future document generation.

[0220] Example prompt statements

[0221] Here are some examples of specific prompt messages:

[0222] "Please prepare a draft report on the system failure. The failure occurred on October 1, 2023, and the affected system is the sales management system. The cause of the failure was insufficient server memory."

[0223] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and enables the creation of higher-quality documents by taking user emotions into consideration.

[0224] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0225] Step 1:

[0226] The user accesses the system using a terminal and logs into a specialized interface. The user selects an option such as "Create Incident Report" and enters the necessary information. At this time, the emotion engine is executed and collects real-time emotion data by analyzing the user's facial expressions and other factors.

[0227] Input: "Create Incident Report" option, detailed incident information entered by the user, and real-time sentiment data.

[0228] Output: User input information and sentiment data packets.

[0229] Step 2:

[0230] The terminal combines user input information and sentiment data into packets and sends them to the server. These data packets are sent to the server via the internet using a secure protocol (e.g., HTTPS).

[0231] Input: Packets containing user input information and sentiment data.

[0232] Output: Data packets sent to the server.

[0233] Step 3:

[0234] The server analyzes the data packets it receives. Specifically, it extracts request details (e.g., creating an incident report), sentiment data, and input information (e.g., the date and time of the incident and the affected systems).

[0235] Input: Data packet.

[0236] Output: A data object containing parsed request details, sentiment data, and input information.

[0237] Step 4:

[0238] The server searches the knowledge database based on the analysis results and extracts relevant past incident reports. The server generates queries to search past document data and executes them against the knowledge database.

[0239] Input: The parsed data object.

[0240] Output: Dataset of extracted related documents.

[0241] Step 5:

[0242] The server provides extracted document data and sentiment data to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) compares this data with training data and generates a new draft document. Based on the sentiment data, it adjusts the tone and expression of the document.

[0243] Input: Extracted document data and sentiment data.

[0244] Output: The generated draft document.

[0245] Step 6:

[0246] The server sends the generated draft document to the terminal. The generated document is sent to the terminal using a secure protocol and displayed in the user interface.

[0247] Input: The generated draft document.

[0248] Output: Draft document sent to the terminal.

[0249] Step 7:

[0250] Review the draft document received by the user and make any necessary corrections or additions. For example, enter specific details of the problem, its cause, and proposed solutions using a text editor.

[0251] Input: The generated draft document.

[0252] Output: Documents modified or added to by the user.

[0253] Step 8:

[0254] The terminal saves the document as the final version after the user has completed modifications and additions. The document is converted to PDF or Word format as needed. It can also be uploaded to the server and stored again in the knowledge database.

[0255] Input: The last document modified or added to by the user.

[0256] Output: The last saved document, the last document uploaded to the knowledge database.

[0257] Step 9:

[0258] The server adds the final document and sentiment data to the knowledge database. This is expected to improve the accuracy of future document generation processes.

[0259] Input: Last saved document, sentiment data.

[0260] Output: The final document and sentiment data added to the knowledge database.

[0261] (Application Example 2)

[0262] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0263] In modern back-office operations, a significant amount of time and effort is spent on document creation, which is a major challenge. Furthermore, the generated documents often fail to align with user emotions and needs, leading to stress and frustration. This is particularly true for content delivery services, where creating relevant recommendation documents for users is currently difficult.

[0264] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for searching past documents related to the business from a knowledge database, means for automatically generating quotation documents using a generation AI, means for transmitting and displaying the generated quotation documents on a user terminal, means for combining a sentiment engine that collects user sentiment data and reflects it in document generation, and means for the generation AI to set prompt sentences based on sentiment data and generate highly accurate documents. This makes it possible to generate high-quality documents that are adapted to the user's sentiment.

[0265] A "knowledge database" is a database that stores past business documents and is accessed in a closed environment.

[0266] "Generative AI" is an artificial intelligence technology that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[0267] A "user terminal" is a device used by a user to access a system and input information or view documents.

[0268] "Emotional data" refers to data that analyzes and quantifies users' emotions.

[0269] An "emotion engine" is a system component that collects user emotion data and incorporates it into document generation.

[0270] A "prompt" is an instruction given to the AI ​​for document generation, used to determine the direction of document creation.

[0271] The system that realizes this invention mainly consists of three components: a server, a terminal, and a user. Furthermore, by combining it with an emotion engine, it enables advanced document creation.

[0272] First, the user accesses the system using a terminal and requests the creation of a draft for a specific business document. For example, they might select an option such as "Create a recommendation document about recent movies" and enter the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0273] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0274] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[0275] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, when creating a "recommendation document about recent movies," if the user's mood is positive, the generation AI will use a prompt such as "Generate recommendation content about recent movies in a positive tone."

[0276] The program's processing can be explained in natural language as follows:

[0277] The server analyzes the input text from the user using the TextBlob library and calculates the sentiment score. Then, it utilizes the Transformers library of HuggingFace to generate a document by the generative AI model based on the prompt text. In this process, the tone of the document is adapted considering the user's sentiment data.

[0278] As a specific example, for instance, when the user requests "Please recommend movies recently", the sentiment score is calculated using the TextBlob library. If the sentiment score is high, the generated prompt text will be "Please generate recommended content about recent movies in a positive tone". Based on this prompt text, the generative AI generates a recommendation document, which is finally provided to the user.

[0279] The flow of the specific process in Application Example 2 will be described using FIG. 14.

[0280] Flow and specific description of program processing

[0281] Step 1:

[0282] The user accesses the system using a terminal and requests to create a template for a specific business document.

[0283] Input: The user inputs a request such as "Create a recommendation document about recent movies".

[0284] Action: Collect the user's request and necessary information through the interface of the terminal.

[0285] Output: The terminal sends the user's input data (the request content of the document) to the next step.

[0286] Step 2:

[0287] The terminal sends the user's input information and sentiment data to the server.

[0288] Input: User request content and real-time sentiment data from the sentiment engine.

[0289] Operation: The terminal sends this data to the server.

[0290] Output: The server receives user requests and sentiment data.

[0291] Step 3:

[0292] The server searches the knowledge database for past documents related to the business.

[0293] Input: User's request.

[0294] Operation: The server searches the knowledge database and extracts relevant historical document data.

[0295] Output: The server retrieves relevant historical document data.

[0296] Step 4:

[0297] The server passes the acquired historical document data and user sentiment data to the generating AI.

[0298] Input: Past document data, user sentiment data.

[0299] Operation: The server passes the data to the AI ​​that generates it.

[0300] Output: The generation AI receives input data for document generation.

[0301] Step 5:

[0302] The generation AI sets prompt sentences and generates a new draft document based on the content and structure of past documents, as well as collected sentiment data.

[0303] Input: Past document data, user's sentiment data.

[0304] Operation: The generation AI sets a prompt sentence based on the sentiment data and generates a new document.

[0305] Output: The generated draft document.

[0306] Specific data operation: Use the sentiment data to adjust the tone of the document and generate an appropriate prompt sentence (e.g., "Please generate recommended content about recent movies in a positive tone").

[0307] Step 6:

[0308] The generated draft document is sent from the server to the user's terminal.

[0309] Input: The generated draft document.

[0310] Operation: The server sends the document to the user terminal.

[0311] Output: The user terminal receives and displays the document.

[0312] Step 7:

[0313] The user checks the displayed draft document and makes corrections and additions using a text editor if necessary.

[0314] Input: The generated draft document.

[0315] Operation: The user uses a text editor to modify and add to the document.

[0316] Output: The document with corrections and additions completed.

[0317] Step 8:

[0318] The document with corrections and additions made by the user is saved as the final document by the terminal.

[0319] Input: Documents that have been corrected or added to.

[0320] Operation: The terminal saves the final document and converts it to a document format if necessary.

[0321] Output: The final document is saved and formatted as needed.

[0322] This enables the generation of high-quality documents that are adapted to the user's emotions.

[0323] 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.

[0324] 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.

[0325] 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.

[0326] [Second Embodiment]

[0327] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0328] 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.

[0329] 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).

[0330] 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.

[0331] 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.

[0332] 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).

[0333] 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.

[0334] 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.

[0335] 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.

[0336] 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.

[0337] 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.

[0338] 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".

[0339] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0340] ---

[0341] This invention relates to a system for streamlining the creation of drafts in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The following is a natural language description of how this system works.

[0342] In the system of the present invention, the user first accesses the system using a terminal and requests the creation of a draft of a specific business document. Specifically, the user selects an option such as "Create a draft of a failure report" through the system's dedicated interface and enters the necessary information.

[0343] The server receives requests from users and accesses the knowledge database to search for relevant documents from the past. This knowledge database stores a large amount of document data related to back-office operations and is managed in a closed environment, ensuring security. Based on the request, the server filters the data for the specified period and the system in which the problem occurred, extracting the most relevant document data.

[0344] The extracted data is passed to a generation AI. The generation AI automatically generates a new draft based on the content and structure of past documents. This is done by filling in the necessary information based on templates and formats of past incident reports.

[0345] The generated draft is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0346] Finally, the document, after the user has made revisions and additions, is saved on the device. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0347] As a concrete example, consider the workflow when a user creates a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as an overview of the outage, the scope of impact, and the results of the cause investigation. The user receives this draft, adds and modifies details, and completes the final report.

[0348] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations, saving time and effort, and enabling the generation of high-quality documents.

[0349] The following describes the processing flow.

[0350] Step 1:

[0351] The user logs into the system using their terminal and selects the "Create a draft of the incident report" option. The user then enters information about the period in question and the system where the problem occurred.

[0352] Step 2:

[0353] The terminal sends user input information to the server. The server receives this request and parses its contents.

[0354] Step 3:

[0355] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0356] Step 4:

[0357] The server extracts data and passes it to the generation AI. The generation AI automatically generates a new draft document based on the content and structure of past documents.

[0358] Step 5:

[0359] The AI ​​generates a draft document which is then returned to the server. The server organizes and formats this data and sends it to the user's terminal.

[0360] Step 6:

[0361] The terminal displays the draft document it received to the user. The user uses a text editor to review the document's contents and make corrections or additions as needed.

[0362] Step 7:

[0363] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal then converts this final document to a document format (PDF or Word).

[0364] Step 8:

[0365] The terminal uploads the final document to the server. The server then stores this document again in the knowledge database, making it available as reference data for the future.

[0366] The above outlines the series of processing steps involved in the system generating a draft document and completing the final document. This allows users to efficiently obtain high-quality documents.

[0367] (Example 1)

[0368] 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".

[0369] Traditional document creation processes in back-office operations often involve manual editing and creation, which is time-consuming and labor-intensive, thus creating a need for increased efficiency. Furthermore, document quality tends to vary, making it difficult to maintain consistency and accuracy. This invention aims to solve these problems.

[0370] 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.

[0371] In this invention, the server includes means for a user to request the creation of a specific business document using a terminal; means for the server to receive the request and search and extract relevant past documents from a knowledge database; means for the server to send a prompt message to a generation AI model and automatically generate a draft of a new document; means for sending and displaying the generated draft on the user's terminal; and means for receiving revisions from the user's terminal and creating the final document. This streamlines the time and effort required for document creation and enables the generation of high-quality, consistent documents.

[0372] A "terminal" is a device used by a user to access a system, and usually refers to electronic devices such as computers and smartphones.

[0373] A "user" refers to an individual or group that uses a system to create specific business documents.

[0374] A "server" refers to a central management system that receives requests from users and handles access to knowledge databases and integration with generated AI models.

[0375] A "knowledge database" refers to a database designed to store past business documents and allow for specific searches and extractions.

[0376] A "generative AI model" refers to an artificial intelligence model that learns the content and structure of past documents and automatically generates a draft of a new document based on that learning.

[0377] A "prompt statement" refers to an input statement used to instruct a generative AI model to create a draft of a new document.

[0378] A "draft" is an incomplete document automatically generated by a generative AI model, serving as the foundation for the user to create the final document.

[0379] This invention relates to a system for improving the efficiency of document creation in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The operation and specific examples of this system are described below.

[0380] System Overview

[0381] The system of this invention has the following main functions:

[0382] 1. User input of document creation request

[0383] 2. Server receives requests and extracts data from the knowledge database.

[0384] 3. Generating a draft of a new document using a generative AI model.

[0385] 4. Server-generated draft submission and display

[0386] 5. User review, modification, and addition to the draft.

[0387] 6. Saving the final document and storing it in the database.

[0388] Hardware and software to be used

[0389] Device: A computer or smartphone used by a user.

[0390] Server: A data server used to operate the central management system.

[0391] Knowledge database: A database that stores past business documents.

[0392] Generative AI model: An AI model used for learning and generating documents.

[0393] Operation details

[0394] User input of request

[0395] Users log in to the system using a terminal and request document creation through a dedicated interface. For example, they might select the option to "create a draft of an incident report" and enter necessary information such as the date and time of the incident and the affected systems.

[0396] The server receives requests and extracts data from the knowledge database.

[0397] The server receives requests from users and accesses the knowledge database. It filters past relevant document data from the knowledge database and extracts documents that are highly relevant to the specified period or issue.

[0398] Generating draft documents using a generative AI model.

[0399] Based on the extracted data, the server sends prompt messages to the generative AI model. The generative AI model has learned the content and structure of past documents and automatically generates a draft of a new document based on that.

[0400] Examples of specific prompt messages:

[0401] "Please create a draft of the incident report based on the following data. The incident occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was a system downtime, and the cause is estimated to be server overload."

[0402] Server-generated draft transmission and display

[0403] The generated draft is sent from the server to the user's terminal. The user receives this draft on their terminal and displays it in a dedicated text editor.

[0404] User review, modification, and addition to the draft.

[0405] Users review the draft displayed on their device and make changes or additions as needed. For example, they can input or correct details of new issues or countermeasures.

[0406] Saving the final document and storing it in the database.

[0407] The final document, after revisions and additions have been made, is saved on the device. It is then uploaded to the server and stored in the knowledge database. Users can choose to save the document in PDF or Word format.

[0408] Specific example

[0409] This example illustrates how a user can create a "Report on Last Week's System Outage." The user enters information such as the date and time of the outage and the affected systems, then submits a request. The server searches the knowledge database for relevant outage reports, and a generation AI model creates a draft of a new document. This draft includes an overview of the outage, the scope of its impact, and the results of the root cause investigation. The user receives this draft and adds or modifies details to complete the final report.

[0410] As a result of these processes, the system of the present invention streamlines document creation in back-office operations, saving time and effort, and enabling the generation of high-quality, consistent documents.

[0411] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0412] Step 1:

[0413] The user logs into the system's dedicated interface using a terminal and requests document creation. Specifically, they select the option to "Create a draft of the incident report" and enter information such as the date and time of the incident, the name of the affected system, and a summary. The input data provided is: Date and time of incident "October 5, 2023", Name of affected system "XYZ system", Summary "System down".

[0414] Step 2:

[0415] The server receives a request from the user. Here, the server parses the HTTP POST request and extracts its contents. The extracted data includes information such as the date and time of the failure, the name of the affected system, and a summary. This is stored in an internal data structure and used for the next processing step.

[0416] Step 3:

[0417] The server uses the extracted data to query the knowledge database. It generates an SQL query to search and extract relevant historical document data based on a specified period and system name. As a result of this query, similar incident reports are extracted. For example, it outputs "Historical Incident Report Data".

[0418] Step 4:

[0419] The server creates prompt statements for the generating AI model based on the extracted data. The generating AI model receives past failure report data along with the prompt statements. A specific prompt statement will be used: "Please create a draft failure report based on the following data. The failure occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was system downtime, and the cause is estimated to be server overload." The prompt statements and related document data are provided as input data to the AI ​​model.

[0420] Step 5:

[0421] The generation AI model generates a draft of a new document based on the prompt text and input data. This is a process that automatically creates a new document following the templates and formats of past documents. The generated draft includes information such as the date and time of the failure, the scope of impact, and the results of the root cause investigation. The output is a "generated failure report draft".

[0422] Step 6:

[0423] The server sends the generated draft to the user's terminal in real time. The server sends the generated draft to the terminal in JSON format, and the terminal parses the received JSON data and displays it in a dedicated text editor. Specifically, it sends the "generated draft of the incident report".

[0424] Step 7:

[0425] The user reviews the draft generated in a text editor on their terminal and makes modifications and additions as needed. For example, they input and modify details of new problems, causes, and countermeasures. After the user completes their work, they save the modified document data. The modified and added document information is provided as input data.

[0426] Step 8:

[0427] The user saves the final document, after making any revisions or additions, on their device and then uploads it to the server. The server stores the final document in a knowledge database, making it available as reference data for the future. For example, users can choose to save the document in PDF or Word format. Once the saved final document is stored in the knowledge database, the "finally saved document" is obtained as output data.

[0428] The above outlines the system's processing steps, with each step described in detail, including the specific actions of the input and output.

[0429] (Application Example 1)

[0430] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0431] Traditional methods for inventory management and sales report creation in physical stores often involve manual processes, requiring significant time and effort, and can lead to data errors and omissions. Furthermore, efficient business operations require fast and accurate document creation, but a suitable system for this purpose has not existed. This invention aims to solve these problems and provide a system for streamlining and automating inventory management and sales report creation in physical stores.

[0432] 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.

[0433] In this invention, the server includes means for searching past documents related to business operations from a knowledge database, means for automatically generating inventory management documents and sales report documents using generation AI, means for transmitting and displaying the generated inventory management documents and sales report documents on a user terminal, and means for receiving revisions from the user terminal and creating the final document. This enables efficient and accurate document creation in physical stores.

[0434] A "knowledge database" is a database that stores past documents related to business operations and is managed in a closed environment.

[0435] "Generative AI" is artificial intelligence that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[0436] "Past documents related to business operations" refers to documents related to back-office operations in physical stores, such as inventory management and sales reports.

[0437] "User terminals" refer to devices such as smartphones and tablets used by employees in physical stores.

[0438] An "inventory management document" is a document used to manage and report the inventory status of products in a physical store.

[0439] A "sales report document" is a report that compiles sales information from physical stores.

[0440] "Correction details" refers to corrections or additional information in the final document sent from the user's terminal.

[0441] A "final document" is a document that has been completed and edited on the user's terminal.

[0442] This invention relates to a system for streamlining and automating inventory management and sales report creation in physical stores. This system primarily consists of a server, user terminals, a knowledge database, and a generating AI. The following specifically describes the operation of this system.

[0443] First, users access the system using user devices such as smartphones or tablets at physical stores. When creating inventory reports or sales reports, users select options such as "Create last month's inventory management report" through a dedicated interface and enter the necessary information, such as the report period and the store ID.

[0444] When the server receives a request from a user, it accesses the knowledge database to search for relevant documents from the past. This knowledge database contains a large amount of past inventory management documents and sales report documents, and is managed in a closed environment accessible only to authorized personnel. Based on the request, the server filters the data for the specified period and store, and extracts the most relevant document data.

[0445] The extracted document data is passed to a generating AI. This AI learns the content and structure of past documents and automatically generates drafts of new inventory management documents and sales report documents based on that learning. For example, it might use a past inventory report template as a base and fill in inventory quantities and sales information for each product item.

[0446] The generated draft is sent from the server to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they can add information about newly arrived products or the impact of special promotions.

[0447] Finally, the document, after the user has made revisions and additions, is saved on the user's terminal. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0448] As a concrete example, let's consider the workflow when a user creates a "last month's inventory report." The user enters the report period and store ID, and submits the request. The server searches and extracts relevant inventory reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as inventory quantity for each product, order history, and sales information. The user receives it, adds and modifies details, and completes the final report.

[0449] An example of a prompt message is: "To create last month's inventory report, generate a draft of the new report based on data from January 1, 2023 to January 31, 2023."

[0450] The above is a detailed description of embodiments of the present invention.

[0451] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0452] Step 1:

[0453] Users access the system using smartphones or tablets in physical stores and submit requests to create necessary business documents (e.g., inventory reports and sales reports). Through a dedicated interface, users input information such as the report's target period and store ID. This input is treated as request data sent to the server.

[0454] Step 2:

[0455] The server analyzes the request data received from the user. Based on conditions such as the type of report entered (inventory report or sales report), the target period, and the store ID, it searches the knowledge database for relevant past documents. Specifically, it filters this data to extract highly relevant past inventory management documents and sales report documents.

[0456] Step 3:

[0457] The server passes the historical document data extracted as search results to the generating AI. The generating AI learns the content and structure of these historical documents and automatically generates a draft of a new document. The input for this step is the extracted document data, and the output is a draft of a newly generated inventory management document or sales report document.

[0458] Step 4:

[0459] The server sends a draft generated by the AI ​​to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed. A dedicated text editor is provided on the user's terminal that allows for modifications and additions. The input is the generated draft document, and the output is the modified / added document.

[0460] Step 5:

[0461] The user saves the final document, after making revisions and additions, from their terminal. The final document is then converted to a specific document format (e.g., PDF or Word) as needed and uploaded to the server. The server then stores the final document back in the knowledge database for future reference. The input is the revised / added document, and the output is the final document stored in the knowledge database.

[0462] The above outlines the specific processing steps for a system that streamlines and automates inventory management and sales reporting in physical stores.

[0463] 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.

[0464] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0465] ---

[0466] This invention relates to a system for streamlining the creation of drafts in back-office operations and for generating documents while considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and by combining them with an emotion engine, it achieves advanced document creation.

[0467] First, the user accesses the system using a terminal and requests the creation of a draft of a specific business document. The user selects an option, such as "Create a draft of an incident report," through the system's dedicated interface and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0468] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0469] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[0470] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0471] Once the user has made revisions and additions, the document is saved on the device as the final document. This final document is converted to a document format (e.g., PDF or Word) as needed. It can also be uploaded to the server, where it is stored again in the knowledge database and used as reference data for the future. At this time, the sentiment data collected by the sentiment engine is also added to the knowledge database, which will help improve the accuracy of future document generation.

[0472] As a concrete example, consider a user creating a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. At this stage, the document's content is adjusted based on the user's emotional data. For example, if the user is feeling stressed, the generated document will be concise and clear, designed to reduce the user's mental burden. The user receives this draft and adds and modifies details to complete the final report.

[0473] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and, by taking user emotions into consideration, enables the creation of higher-quality documents.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] A user logs into the system using a terminal and requests the creation of a draft of a specific business document. For example, they might select the "Create a draft of an incident report" option and enter information about the period and affected systems. At this time, the emotion engine recognizes the user's emotions in real time from their input actions, voice, and facial expressions, and records this data.

[0477] Step 2:

[0478] The terminal sends user input information and sentiment data to the server. The server receives this request and parses its contents. The request contains basic information for creating a draft and user sentiment data.

[0479] Step 3:

[0480] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0481] Step 4:

[0482] The server passes the extracted data and sentiment data to the generating AI. The generating AI automatically generates a new draft document based on the content and structure of past documents, as well as the user's sentiment data. In this process, the tone and content of the document are adjusted to take sentiment data into consideration.

[0483] Step 5:

[0484] The AI ​​generates a draft document which is then returned to the server. The server reviews this data and sends it to the user's terminal. The document incorporates expressions and structures that are adapted to the user's emotions.

[0485] Step 6:

[0486] The terminal displays a draft document it received to the user. The user reviews the displayed draft document and uses a text editor to modify or add to its contents. For example, they might enter details, causes, and countermeasures for a newly occurring problem.

[0487] Step 7:

[0488] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal converts this final document to a document format (e.g., PDF or Word) and sends it to the server.

[0489] Step 8:

[0490] The server receives the final document and stores it in the knowledge database. The sentiment data collected by the sentiment engine is also added to the knowledge database and used as reference data for future document generation.

[0491] The above outlines the series of processing steps involved in a system incorporating an emotion engine, from generating a draft document to completing the final document. This allows users to obtain high-quality documents efficiently and with minimal psychological burden.

[0492] (Example 2)

[0493] 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".

[0494] Conventional automated document generation systems rely solely on past document data, which limits their ability to generate documents that reflect user emotions. This makes it difficult to provide documents suitable for situations where users are likely to experience stress or for specific emotional states.

[0495] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for searching past documents related to business from a knowledge database, means for automatically generating documents based on user sentiment data using generation AI, and means for transmitting and displaying the generated documents on a user terminal. This makes it possible to automatically generate documents that take user sentiment into consideration.

[0496] A "knowledge database" is a data storage system that stores past business documents and related data and manages them in a closed environment.

[0497] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to learn from past documents and related data, and automatically generates new documents.

[0498] A "user terminal" is a hardware device, such as a computer or mobile device, that a user uses to access and operate a system.

[0499] An "emotion engine" refers to software or algorithms used to analyze and collect user emotional data in real time.

[0500] "Emotional data" refers to data about the user's emotional state collected and analyzed by the emotion engine.

[0501] "Automatic generation" refers to the process by which a generation AI automatically creates new documents based on pre-learned data, using user input and sentiment data.

[0502] A "closed environment" refers to a secure, access-restricted environment that is accessible only to specific users or system administrators.

[0503] "Modification details" refers to data that indicates the additions and changes made by the user to the generated document.

[0504] This invention relates to a system that streamlines document generation in back-office operations and generates high-quality documents by considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and achieves advanced document generation by combining them with an emotion engine.

[0505] System Configuration

[0506] This system uses the following main hardware and software.

[0507] Hardware: Client PCs, mobile devices, server machines

[0508] Software: Sentiment engines (e.g., Sentiment Analysis API), knowledge databases (e.g., MySQL), generative AI (e.g., OpenAI GPT-4), document format conversion tools (e.g., Adobe Acrobat)

[0509] Operating procedures and specific examples

[0510] First, the user accesses the system using a terminal (e.g., a PC or mobile device) and requests the creation of a draft of a specific business document. The user logs into the system's dedicated interface, selects an option such as "Create a draft of an incident report," and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0511] Data transmission and analysis

[0512] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0513] Document generation process

[0514] The extracted data is passed to a generative AI. The generative AI (e.g., OpenAI GPT-4) automatically generates a new draft document based on the content and structure of past documents, as well as the collected sentiment data. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process generates a user-friendly document.

[0515] Document review and correction

[0516] The generated draft document is sent back from the server to the terminal. The terminal receives this data and displays it to the user. For example, if a user is creating a "Report on last week's system failure," they would review the generated draft and modify or add new details about the failure, its cause, and countermeasures using a text editor.

[0517] Saving the final document and closing the process.

[0518] Documents that have been edited or added to by the user are saved on the device as the final document. Documents can be converted to PDF or Word format as needed. They can also be uploaded to the server, where they are stored again in the knowledge database and used as reference data for the future. At this time, sentiment data collected by the sentiment engine is also added to the knowledge database, helping to improve the accuracy of future document generation.

[0519] Example prompt statements

[0520] Here are some examples of specific prompt messages:

[0521] "Please prepare a draft report on the system failure. The failure occurred on October 1, 2023, and the affected system is the sales management system. The cause of the failure was insufficient server memory."

[0522] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and enables the creation of higher-quality documents by taking user emotions into consideration.

[0523] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0524] Step 1:

[0525] The user accesses the system using a terminal and logs into a specialized interface. The user selects an option such as "Create Incident Report" and enters the necessary information. At this time, the emotion engine is executed and collects real-time emotion data by analyzing the user's facial expressions and other factors.

[0526] Input: "Create Incident Report" option, detailed incident information entered by the user, and real-time sentiment data.

[0527] Output: User input information and sentiment data packets.

[0528] Step 2:

[0529] The terminal combines user input information and sentiment data into packets and sends them to the server. These data packets are sent to the server via the internet using a secure protocol (e.g., HTTPS).

[0530] Input: Packets containing user input information and sentiment data.

[0531] Output: Data packets sent to the server.

[0532] Step 3:

[0533] The server analyzes the data packets it receives. Specifically, it extracts request details (e.g., creating an incident report), sentiment data, and input information (e.g., the date and time of the incident and the affected systems).

[0534] Input: Data packet.

[0535] Output: A data object containing parsed request details, sentiment data, and input information.

[0536] Step 4:

[0537] The server searches the knowledge database based on the analysis results and extracts relevant past incident reports. The server generates queries to search past document data and executes them against the knowledge database.

[0538] Input: The parsed data object.

[0539] Output: A dataset of extracted related documents.

[0540] Step 5:

[0541] The server provides extracted document data and sentiment data to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) compares this data with training data and generates a new draft document. Based on the sentiment data, it adjusts the tone and expression of the document.

[0542] Input: Extracted document data and sentiment data.

[0543] Output: The generated draft document.

[0544] Step 6:

[0545] The server sends the generated draft document to the terminal. The generated document is sent to the terminal using a secure protocol and displayed in the user interface.

[0546] Input: The generated draft document.

[0547] Output: Draft document sent to the terminal.

[0548] Step 7:

[0549] Review the draft document received by the user and make any necessary corrections or additions. For example, enter specific details of the problem, its cause, and proposed solutions using a text editor.

[0550] Input: The generated draft document.

[0551] Output: Documents modified or added to by the user.

[0552] Step 8:

[0553] The terminal saves the document as the final version after the user has completed modifications and additions. The document is converted to PDF or Word format as needed. It can also be uploaded to the server and stored again in the knowledge database.

[0554] Input: The last document modified or added to by the user.

[0555] Output: The last saved document, the last document uploaded to the knowledge database.

[0556] Step 9:

[0557] The server adds the final document and sentiment data to the knowledge database. This is expected to improve the accuracy of future document generation processes.

[0558] Input: Last saved document, sentiment data.

[0559] Output: The final document and sentiment data added to the knowledge database.

[0560] (Application Example 2)

[0561] 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."

[0562] In modern back-office operations, a significant amount of time and effort is spent on document creation, which is a major challenge. Furthermore, the generated documents often fail to align with user emotions and needs, leading to stress and frustration. This is particularly true for content delivery services, where creating relevant recommendation documents for users is currently difficult.

[0563] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for searching past documents related to the business from a knowledge database, means for automatically generating quotation documents using a generation AI, means for transmitting and displaying the generated quotation documents on a user terminal, means for combining a sentiment engine that collects user sentiment data and reflects it in document generation, and means for the generation AI to set prompt sentences based on sentiment data and generate highly accurate documents. This makes it possible to generate high-quality documents that are adapted to the user's sentiment.

[0564] A "knowledge database" is a database that stores past business documents and is accessed in a closed environment.

[0565] "Generative AI" is an artificial intelligence technology that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[0566] A "user terminal" is a device used by a user to access a system and input information or view documents.

[0567] "Emotional data" refers to data that analyzes and quantifies users' emotions.

[0568] An "emotion engine" is a system component that collects user emotion data and incorporates it into document generation.

[0569] A "prompt" is an instruction given to the AI ​​for document generation, used to determine the direction of document creation.

[0570] The system that realizes this invention mainly consists of three components: a server, a terminal, and a user. Furthermore, by combining it with an emotion engine, it enables advanced document creation.

[0571] First, the user accesses the system using a terminal and requests the creation of a draft for a specific business document. For example, they might select an option such as "Create a recommendation document about recent movies" and enter the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0572] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0573] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[0574] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, when creating a "recommendation document about recent movies," if the user's mood is positive, the generation AI will use a prompt such as "Generate recommendation content about recent movies in a positive tone."

[0575] The program's processing can be explained in natural language as follows:

[0576] The server uses the TextBlob library to analyze user input text and calculate a sentiment score. Then, using the HuggingFace Transformers library, a generative AI model generates a document based on the prompt text. This process adapts the document's tone to take the user's sentiment data into account.

[0577] As a concrete example, if a user requests "Please recommend some recent movies," the TextBlob library is used to calculate a sentiment score. If the sentiment score is high, the generated prompt will be "Please generate recommended content about recent movies in a positive tone." Based on this prompt, the generation AI creates a recommendation document, which is then ultimately provided to the user.

[0578] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0579] Program processing flow and detailed explanation

[0580] Step 1:

[0581] Users access the system using a terminal and request the creation of a draft for a specific business document.

[0582] Input: The user enters a request such as "Create a recommendation document about recent movies."

[0583] Operation: Collects user requests and necessary information through the terminal interface.

[0584] Output: The terminal sends the user's input data (document request content) to the next step.

[0585] Step 2:

[0586] The device sends user input information and sentiment data to the server.

[0587] Input: User request content and real-time sentiment data from the sentiment engine.

[0588] Operation: The terminal sends this data to the server.

[0589] Output: The server receives user requests and sentiment data.

[0590] Step 3:

[0591] The server searches the knowledge database for past documents related to the business.

[0592] Input: User's request.

[0593] Operation: The server searches the knowledge database and extracts relevant historical document data.

[0594] Output: The server retrieves relevant historical document data.

[0595] Step 4:

[0596] The server passes the acquired historical document data and user sentiment data to the generating AI.

[0597] Input: Past document data, user sentiment data.

[0598] Operation: The server passes the data to the AI ​​that generates it.

[0599] Output: The generation AI receives input data for document generation.

[0600] Step 5:

[0601] The generation AI sets prompt sentences and generates a new draft document based on the content and structure of past documents, as well as collected sentiment data.

[0602] Input: Past document data, user sentiment data.

[0603] Operation: The generating AI sets prompt sentences based on sentiment data and generates a new document.

[0604] Output: The generated draft document.

[0605] Specific data calculations: Use sentiment data to adjust the tone of a document and generate appropriate prompt sentences (e.g., "Generate recommended content about recent movies in a positive tone").

[0606] Step 6:

[0607] The generated draft document is sent from the server to the user's terminal.

[0608] Input: The generated draft document.

[0609] Operation: The server sends the document to the user's terminal.

[0610] Output: The user terminal receives and displays the document.

[0611] Step 7:

[0612] The user reviews the displayed draft document and makes modifications or additions as needed using a text editor.

[0613] Input: The generated draft document.

[0614] Operation: The user modifies and adds to the document using a text editor.

[0615] Output: The document after corrections and additions have been completed.

[0616] Step 8:

[0617] Once the user has completed any modifications or additions to the document, it will be saved on the device as the final document.

[0618] Input: Documents that have been corrected or added to.

[0619] Operation: The terminal saves the final document and converts it to a document format if necessary.

[0620] Output: The final document is saved and formatted as needed.

[0621] This enables the generation of high-quality documents that are adapted to the user's emotions.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] [Third Embodiment]

[0626] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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".

[0638] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0639] ---

[0640] This invention relates to a system for streamlining the creation of drafts in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The following is a natural language description of how this system works.

[0641] In the system of the present invention, the user first accesses the system using a terminal and requests the creation of a draft of a specific business document. Specifically, the user selects an option such as "Create a draft of a failure report" through the system's dedicated interface and enters the necessary information.

[0642] The server receives requests from users and accesses the knowledge database to search for relevant documents from the past. This knowledge database stores a large amount of document data related to back-office operations and is managed in a closed environment, ensuring security. Based on the request, the server filters the data for the specified period and the system in which the problem occurred, extracting the most relevant document data.

[0643] The extracted data is passed to a generation AI. The generation AI automatically generates a new draft based on the content and structure of past documents. This is done by filling in the necessary information based on templates and formats of past incident reports.

[0644] The generated draft is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0645] Finally, the document, after the user has made revisions and additions, is saved on the device. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0646] As a concrete example, consider the workflow when a user creates a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as an overview of the outage, the scope of impact, and the results of the cause investigation. The user receives this draft, adds and modifies details, and completes the final report.

[0647] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations, saving time and effort, and enabling the generation of high-quality documents.

[0648] The following describes the processing flow.

[0649] Step 1:

[0650] The user logs into the system using their terminal and selects the "Create a draft of the incident report" option. The user then enters information about the period in question and the system where the problem occurred.

[0651] Step 2:

[0652] The terminal sends user input information to the server. The server receives this request and parses its contents.

[0653] Step 3:

[0654] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0655] Step 4:

[0656] The server extracts data and passes it to the generation AI. The generation AI automatically generates a new draft document based on the content and structure of past documents.

[0657] Step 5:

[0658] The AI ​​generates a draft document which is then returned to the server. The server organizes and formats this data and sends it to the user's terminal.

[0659] Step 6:

[0660] The terminal displays the draft document it received to the user. The user uses a text editor to review the document's contents and make corrections or additions as needed.

[0661] Step 7:

[0662] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal then converts this final document to a document format (PDF or Word).

[0663] Step 8:

[0664] The terminal uploads the final document to the server. The server then stores this document again in the knowledge database, making it available as reference data for the future.

[0665] The above outlines the series of processing steps involved in the system generating a draft document and completing the final document. This allows users to efficiently obtain high-quality documents.

[0666] (Example 1)

[0667] 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."

[0668] Traditional document creation processes in back-office operations often involve manual editing and creation, which is time-consuming and labor-intensive, thus creating a need for increased efficiency. Furthermore, document quality tends to vary, making it difficult to maintain consistency and accuracy. This invention aims to solve these problems.

[0669] 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.

[0670] In this invention, the server includes means for a user to request the creation of a specific business document using a terminal; means for the server to receive the request and search and extract relevant past documents from a knowledge database; means for the server to send a prompt message to a generation AI model and automatically generate a draft of a new document; means for sending and displaying the generated draft on the user's terminal; and means for receiving revisions from the user's terminal and creating the final document. This streamlines the time and effort required for document creation and enables the generation of high-quality, consistent documents.

[0671] A "terminal" is a device used by a user to access a system, and usually refers to electronic devices such as computers and smartphones.

[0672] A "user" refers to an individual or group that uses a system to create specific business documents.

[0673] A "server" refers to a central management system that receives requests from users and handles access to knowledge databases and integration with generated AI models.

[0674] A "knowledge database" refers to a database designed to store past business documents and allow for specific searches and extractions.

[0675] A "generative AI model" refers to an artificial intelligence model that learns the content and structure of past documents and automatically generates a draft of a new document based on that learning.

[0676] A "prompt statement" refers to an input statement used to instruct a generative AI model to create a draft of a new document.

[0677] A "draft" is an incomplete document automatically generated by a generative AI model, serving as the foundation for the user to create the final document.

[0678] This invention relates to a system for improving the efficiency of document creation in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The operation and specific examples of this system are described below.

[0679] System Overview

[0680] The system of this invention has the following main functions:

[0681] 1. User input of document creation request

[0682] 2. Server receives requests and extracts data from the knowledge database.

[0683] 3. Generating a draft of a new document using a generative AI model.

[0684] 4. Server-generated draft submission and display

[0685] 5. User review, modification, and addition to the draft.

[0686] 6. Saving the final document and storing it in the database.

[0687] Hardware and software to be used

[0688] Device: A computer or smartphone used by a user.

[0689] Server: A data server used to operate the central management system.

[0690] Knowledge database: A database that stores past business documents.

[0691] Generative AI model: An AI model used for learning and generating documents.

[0692] Operation details

[0693] User input of request

[0694] Users log in to the system using a terminal and request document creation through a dedicated interface. For example, they might select the option to "create a draft of an incident report" and enter necessary information such as the date and time of the incident and the affected systems.

[0695] The server receives requests and extracts data from the knowledge database.

[0696] The server receives requests from users and accesses the knowledge database. It filters past relevant document data from the knowledge database and extracts documents that are highly relevant to the specified period or issue.

[0697] Generating draft documents using a generative AI model.

[0698] Based on the extracted data, the server sends prompt messages to the generative AI model. The generative AI model has learned the content and structure of past documents and automatically generates a draft of a new document based on that.

[0699] Examples of specific prompt messages:

[0700] "Please create a draft of the incident report based on the following data. The incident occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was a system downtime, and the cause is estimated to be server overload."

[0701] Server-generated draft transmission and display

[0702] The generated draft is sent from the server to the user's terminal. The user receives this draft on their terminal and displays it in a dedicated text editor.

[0703] User review, modification, and addition to the draft.

[0704] Users review the draft displayed on their device and make changes or additions as needed. For example, they can input or correct details of new issues or countermeasures.

[0705] Saving the final document and storing it in the database.

[0706] The final document, after revisions and additions have been made, is saved on the device. It is then uploaded to the server and stored in the knowledge database. Users can choose to save the document in PDF or Word format.

[0707] Specific example

[0708] This example illustrates how a user can create a "Report on Last Week's System Outage." The user enters information such as the date and time of the outage and the affected systems, then submits a request. The server searches the knowledge database for relevant outage reports, and a generation AI model creates a draft of a new document. This draft includes an overview of the outage, the scope of its impact, and the results of the root cause investigation. The user receives this draft and adds or modifies details to complete the final report.

[0709] As a result of these processes, the system of the present invention streamlines document creation in back-office operations, saving time and effort, and enabling the generation of high-quality, consistent documents.

[0710] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0711] Step 1:

[0712] The user logs into the system's dedicated interface using a terminal and requests document creation. Specifically, they select the option to "Create a draft of the incident report" and enter information such as the date and time of the incident, the name of the affected system, and a summary. The input data provided is: Date and time of incident "October 5, 2023", Name of affected system "XYZ system", Summary "System down".

[0713] Step 2:

[0714] The server receives a request from the user. Here, the server parses the HTTP POST request and extracts its contents. The extracted data includes information such as the date and time of the failure, the name of the affected system, and a summary. This is stored in an internal data structure and used for the next processing step.

[0715] Step 3:

[0716] The server uses the extracted data to query the knowledge database. It generates an SQL query to search and extract relevant historical document data based on a specified period and system name. As a result of this query, similar incident reports are extracted. For example, it outputs "Historical Incident Report Data".

[0717] Step 4:

[0718] The server creates prompt statements for the generating AI model based on the extracted data. The generating AI model receives past failure report data along with the prompt statements. A specific prompt statement will be used: "Please create a draft failure report based on the following data. The failure occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was system downtime, and the cause is estimated to be server overload." The prompt statements and related document data are provided as input data to the AI ​​model.

[0719] Step 5:

[0720] The generation AI model generates a draft of a new document based on the prompt text and input data. This is a process that automatically creates a new document following the templates and formats of past documents. The generated draft includes information such as the date and time of the failure, the scope of impact, and the results of the root cause investigation. The output is a "generated failure report draft".

[0721] Step 6:

[0722] The server sends the generated draft to the user's terminal in real time. The server sends the generated draft to the terminal in JSON format, and the terminal parses the received JSON data and displays it in a dedicated text editor. Specifically, it sends the "generated draft of the incident report".

[0723] Step 7:

[0724] The user reviews the draft generated in a text editor on their terminal and makes modifications and additions as needed. For example, they input and modify details of new problems, causes, and countermeasures. After the user completes their work, they save the modified document data. The modified and added document information is provided as input data.

[0725] Step 8:

[0726] The user saves the final document, after making any revisions or additions, on their device and then uploads it to the server. The server stores the final document in a knowledge database, making it available as reference data for the future. For example, users can choose to save the document in PDF or Word format. Once the saved final document is stored in the knowledge database, the "finally saved document" is obtained as output data.

[0727] The above outlines the system's processing steps, with each step described in detail, including the specific actions of the input and output.

[0728] (Application Example 1)

[0729] 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."

[0730] Traditional methods for inventory management and sales report creation in physical stores often involve manual processes, requiring significant time and effort, and can lead to data errors and omissions. Furthermore, efficient business operations require fast and accurate document creation, but a suitable system for this purpose has not existed. This invention aims to solve these problems and provide a system for streamlining and automating inventory management and sales report creation in physical stores.

[0731] 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.

[0732] In this invention, the server includes means for searching past documents related to business operations from a knowledge database, means for automatically generating inventory management documents and sales report documents using generation AI, means for transmitting and displaying the generated inventory management documents and sales report documents on a user terminal, and means for receiving revisions from the user terminal and creating the final document. This enables efficient and accurate document creation in physical stores.

[0733] A "knowledge database" is a database that stores past documents related to business operations and is managed in a closed environment.

[0734] "Generative AI" is artificial intelligence that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[0735] "Past documents related to business operations" refers to documents related to back-office operations in physical stores, such as inventory management and sales reports.

[0736] "User terminals" refer to devices such as smartphones and tablets used by employees in physical stores.

[0737] An "inventory management document" is a document used to manage and report the inventory status of products in a physical store.

[0738] A "sales report document" is a report that compiles sales information from physical stores.

[0739] "Correction details" refers to corrections or additional information in the final document sent from the user's terminal.

[0740] A "final document" is a document that has been completed and edited on the user's terminal.

[0741] This invention relates to a system for streamlining and automating inventory management and sales report creation in physical stores. This system primarily consists of a server, user terminals, a knowledge database, and a generating AI. The following specifically describes the operation of this system.

[0742] First, users access the system using user devices such as smartphones or tablets at physical stores. When creating inventory reports or sales reports, users select options such as "Create last month's inventory management report" through a dedicated interface and enter the necessary information, such as the report period and the store ID.

[0743] When the server receives a request from a user, it accesses the knowledge database to search for relevant documents from the past. This knowledge database contains a large amount of past inventory management documents and sales report documents, and is managed in a closed environment accessible only to authorized personnel. Based on the request, the server filters the data for the specified period and store, and extracts the most relevant document data.

[0744] The extracted document data is passed to a generating AI. This AI learns the content and structure of past documents and automatically generates drafts of new inventory management documents and sales report documents based on that learning. For example, it might use a past inventory report template as a base and fill in inventory quantities and sales information for each product item.

[0745] The generated draft is sent from the server to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they can add information about newly arrived products or the impact of special promotions.

[0746] Finally, the document, after the user has made revisions and additions, is saved on the user's terminal. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0747] As a concrete example, let's consider the workflow when a user creates a "last month's inventory report." The user enters the report period and store ID, and submits the request. The server searches and extracts relevant inventory reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as inventory quantity for each product, order history, and sales information. The user receives it, adds and modifies details, and completes the final report.

[0748] An example of a prompt message is: "To create last month's inventory report, generate a draft of the new report based on data from January 1, 2023 to January 31, 2023."

[0749] The above is a detailed description of embodiments of the present invention.

[0750] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0751] Step 1:

[0752] Users access the system using smartphones or tablets in physical stores and submit requests to create necessary business documents (e.g., inventory reports and sales reports). Through a dedicated interface, users input information such as the report's target period and store ID. This input is treated as request data sent to the server.

[0753] Step 2:

[0754] The server analyzes the request data received from the user. Based on conditions such as the type of report entered (inventory report or sales report), the target period, and the store ID, it searches the knowledge database for relevant past documents. Specifically, it filters this data to extract highly relevant past inventory management documents and sales report documents.

[0755] Step 3:

[0756] The server passes the historical document data extracted as search results to the generating AI. The generating AI learns the content and structure of these historical documents and automatically generates a draft of a new document. The input for this step is the extracted document data, and the output is a draft of a newly generated inventory management document or sales report document.

[0757] Step 4:

[0758] The server sends a draft generated by the AI ​​to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed. A dedicated text editor is provided on the user's terminal that allows for modifications and additions. The input is the generated draft document, and the output is the modified / added document.

[0759] Step 5:

[0760] The user saves the final document, after making revisions and additions, from their terminal. The final document is then converted to a specific document format (e.g., PDF or Word) as needed and uploaded to the server. The server then stores the final document back in the knowledge database for future reference. The input is the revised / added document, and the output is the final document stored in the knowledge database.

[0761] The above outlines the specific processing steps for a system that streamlines and automates inventory management and sales reporting in physical stores.

[0762] 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.

[0763] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0764] ---

[0765] This invention relates to a system for streamlining the creation of drafts in back-office operations and for generating documents while considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and by combining them with an emotion engine, it achieves advanced document creation.

[0766] First, the user accesses the system using a terminal and requests the creation of a draft of a specific business document. The user selects an option, such as "Create a draft of an incident report," through the system's dedicated interface and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0767] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0768] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[0769] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0770] Once the user has made revisions and additions, the document is saved on the device as the final document. This final document is converted to a document format (e.g., PDF or Word) as needed. It can also be uploaded to the server, where it is stored again in the knowledge database and used as reference data for the future. At this time, the sentiment data collected by the sentiment engine is also added to the knowledge database, which will help improve the accuracy of future document generation.

[0771] As a concrete example, consider a user creating a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. At this stage, the document's content is adjusted based on the user's emotional data. For example, if the user is feeling stressed, the generated document will be concise and clear, designed to reduce the user's mental burden. The user receives this draft and adds and modifies details to complete the final report.

[0772] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and, by taking user emotions into consideration, enables the creation of higher-quality documents.

[0773] The following describes the processing flow.

[0774] Step 1:

[0775] A user logs into the system using a terminal and requests the creation of a draft of a specific business document. For example, they might select the "Create a draft of an incident report" option and enter information about the period and affected systems. At this time, the emotion engine recognizes the user's emotions in real time from their input actions, voice, and facial expressions, and records this data.

[0776] Step 2:

[0777] The terminal sends user input information and sentiment data to the server. The server receives this request and parses its contents. The request contains basic information for creating a draft and user sentiment data.

[0778] Step 3:

[0779] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0780] Step 4:

[0781] The server passes the extracted data and sentiment data to the generating AI. The generating AI automatically generates a new draft document based on the content and structure of past documents, as well as the user's sentiment data. In this process, the tone and content of the document are adjusted to take sentiment data into consideration.

[0782] Step 5:

[0783] The AI ​​generates a draft document which is then returned to the server. The server reviews this data and sends it to the user's terminal. The document incorporates expressions and structures that are adapted to the user's emotions.

[0784] Step 6:

[0785] The terminal displays a draft document it received to the user. The user reviews the displayed draft document and uses a text editor to modify or add to its contents. For example, they might enter details, causes, and countermeasures for a newly occurring problem.

[0786] Step 7:

[0787] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal converts this final document to a document format (e.g., PDF or Word) and sends it to the server.

[0788] Step 8:

[0789] The server receives the final document and stores it in the knowledge database. The sentiment data collected by the sentiment engine is also added to the knowledge database and used as reference data for future document generation.

[0790] The above outlines the series of processing steps involved in a system incorporating an emotion engine, from generating a draft document to completing the final document. This allows users to obtain high-quality documents efficiently and with minimal psychological burden.

[0791] (Example 2)

[0792] 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."

[0793] Conventional automated document generation systems rely solely on past document data, which limits their ability to generate documents that reflect user emotions. This makes it difficult to provide documents suitable for situations where users are likely to experience stress or for specific emotional states.

[0794] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for searching past documents related to business from a knowledge database, means for automatically generating documents based on user sentiment data using generation AI, and means for transmitting and displaying the generated documents on a user terminal. This makes it possible to automatically generate documents that take user sentiment into consideration.

[0795] A "knowledge database" is a data storage system that stores past business documents and related data and manages them in a closed environment.

[0796] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to learn from past documents and related data, and automatically generates new documents.

[0797] A "user terminal" is a hardware device, such as a computer or mobile device, that a user uses to access and operate a system.

[0798] An "emotion engine" refers to software or algorithms used to analyze and collect user emotional data in real time.

[0799] "Emotional data" refers to data about the user's emotional state collected and analyzed by the emotion engine.

[0800] "Automatic generation" refers to the process by which a generation AI automatically creates new documents based on pre-learned data, using user input and sentiment data.

[0801] A "closed environment" refers to a secure, access-restricted environment that is accessible only to specific users or system administrators.

[0802] "Modification details" refers to data that indicates the additions and changes made by the user to the generated document.

[0803] This invention relates to a system that streamlines document generation in back-office operations and generates high-quality documents by considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and achieves advanced document generation by combining them with an emotion engine.

[0804] System Configuration

[0805] This system uses the following main hardware and software.

[0806] Hardware: Client PCs, mobile devices, server machines

[0807] Software: Sentiment engines (e.g., Sentiment Analysis API), knowledge databases (e.g., MySQL), generative AI (e.g., OpenAI GPT-4), document format conversion tools (e.g., Adobe Acrobat)

[0808] Operating procedures and specific examples

[0809] First, the user accesses the system using a terminal (e.g., a PC or mobile device) and requests the creation of a draft of a specific business document. The user logs into the system's dedicated interface, selects an option such as "Create a draft of an incident report," and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0810] Data transmission and analysis

[0811] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0812] Document generation process

[0813] The extracted data is passed to a generative AI. The generative AI (e.g., OpenAI GPT-4) automatically generates a new draft document based on the content and structure of past documents, as well as the collected sentiment data. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process generates a user-friendly document.

[0814] Document review and correction

[0815] The generated draft document is sent back from the server to the terminal. The terminal receives this data and displays it to the user. For example, if a user is creating a "Report on last week's system failure," they would review the generated draft and modify or add new details about the failure, its cause, and countermeasures using a text editor.

[0816] Saving the final document and closing the process.

[0817] Documents that have been edited or added to by the user are saved on the device as the final document. Documents can be converted to PDF or Word format as needed. They can also be uploaded to the server, where they are stored again in the knowledge database and used as reference data for the future. At this time, sentiment data collected by the sentiment engine is also added to the knowledge database, helping to improve the accuracy of future document generation.

[0818] Example prompt statements

[0819] Here are some examples of specific prompt messages:

[0820] "Please prepare a draft report on the system failure. The failure occurred on October 1, 2023, and the affected system is the sales management system. The cause of the failure was insufficient server memory."

[0821] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and enables the creation of higher-quality documents by taking user emotions into consideration.

[0822] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0823] Step 1:

[0824] The user accesses the system using a terminal and logs into a specialized interface. The user selects an option such as "Create Incident Report" and enters the necessary information. At this time, the emotion engine is executed and collects real-time emotion data by analyzing the user's facial expressions and other factors.

[0825] Input: "Create Incident Report" option, detailed incident information entered by the user, and real-time sentiment data.

[0826] Output: User input information and sentiment data packets.

[0827] Step 2:

[0828] The terminal combines user input information and sentiment data into packets and sends them to the server. These data packets are sent to the server via the internet using a secure protocol (e.g., HTTPS).

[0829] Input: Packets containing user input information and sentiment data.

[0830] Output: Data packets sent to the server.

[0831] Step 3:

[0832] The server analyzes the data packets it receives. Specifically, it extracts request details (e.g., creating an incident report), sentiment data, and input information (e.g., the date and time of the incident and the affected systems).

[0833] Input: Data packet.

[0834] Output: A data object containing parsed request details, sentiment data, and input information.

[0835] Step 4:

[0836] The server searches the knowledge database based on the analysis results and extracts relevant past incident reports. The server generates queries to search past document data and executes them against the knowledge database.

[0837] Input: The parsed data object.

[0838] Output: Dataset of extracted related documents.

[0839] Step 5:

[0840] The server provides extracted document data and sentiment data to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) compares this data with training data and generates a new draft document. Based on the sentiment data, it adjusts the tone and expression of the document.

[0841] Input: Extracted document data and sentiment data.

[0842] Output: The generated draft document.

[0843] Step 6:

[0844] The server sends the generated draft document to the terminal. The generated document is sent to the terminal using a secure protocol and displayed in the user interface.

[0845] Input: The generated draft document.

[0846] Output: Draft document sent to the terminal.

[0847] Step 7:

[0848] Review the draft document received by the user and make any necessary corrections or additions. For example, enter specific details of the problem, its cause, and proposed solutions using a text editor.

[0849] Input: The generated draft document.

[0850] Output: Documents modified or added to by the user.

[0851] Step 8:

[0852] The terminal saves the document as the final version after the user has completed modifications and additions. The document is converted to PDF or Word format as needed. It can also be uploaded to the server and stored again in the knowledge database.

[0853] Input: The last document modified or added to by the user.

[0854] Output: The last saved document, the last document uploaded to the knowledge database.

[0855] Step 9:

[0856] The server adds the final document and sentiment data to the knowledge database. This is expected to improve the accuracy of future document generation processes.

[0857] Input: Last saved document, sentiment data.

[0858] Output: The final document and sentiment data added to the knowledge database.

[0859] (Application Example 2)

[0860] 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."

[0861] In modern back-office operations, a significant amount of time and effort is spent on document creation, which is a major challenge. Furthermore, the generated documents often fail to align with user emotions and needs, leading to stress and frustration. This is particularly true for content delivery services, where creating relevant recommendation documents for users is currently difficult.

[0862] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for searching past documents related to the business from a knowledge database, means for automatically generating quotation documents using a generation AI, means for transmitting and displaying the generated quotation documents on a user terminal, means for combining a sentiment engine that collects user sentiment data and reflects it in document generation, and means for the generation AI to set prompt sentences based on sentiment data and generate highly accurate documents. This makes it possible to generate high-quality documents that are adapted to the user's sentiment.

[0863] A "knowledge database" is a database that stores past business documents and is accessed in a closed environment.

[0864] "Generative AI" is an artificial intelligence technology that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[0865] A "user terminal" is a device used by a user to access a system and input information or view documents.

[0866] "Emotional data" refers to data that analyzes and quantifies users' emotions.

[0867] An "emotion engine" is a system component that collects user emotion data and incorporates it into document generation.

[0868] A "prompt" is an instruction given to the AI ​​for document generation, used to determine the direction of document creation.

[0869] The system that realizes this invention mainly consists of three components: a server, a terminal, and a user. Furthermore, by combining it with an emotion engine, it enables advanced document creation.

[0870] First, the user accesses the system using a terminal and requests the creation of a draft for a specific business document. For example, they might select an option such as "Create a recommendation document about recent movies" and enter the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[0871] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[0872] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[0873] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, when creating a "recommendation document about recent movies," if the user's mood is positive, the generation AI will use a prompt such as "Generate recommendation content about recent movies in a positive tone."

[0874] The program's processing can be explained in natural language as follows:

[0875] The server uses the TextBlob library to analyze user input text and calculate a sentiment score. Then, using the HuggingFace Transformers library, a generative AI model generates a document based on the prompt text. This process adapts the document's tone to take the user's sentiment data into account.

[0876] As a concrete example, if a user requests "Please recommend some recent movies," the TextBlob library is used to calculate a sentiment score. If the sentiment score is high, the generated prompt will be "Please generate recommended content about recent movies in a positive tone." Based on this prompt, the generation AI creates a recommendation document, which is then ultimately provided to the user.

[0877] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0878] Program processing flow and detailed explanation

[0879] Step 1:

[0880] Users access the system using a terminal and request the creation of a draft for a specific business document.

[0881] Input: The user enters a request such as "Create a recommendation document about recent movies."

[0882] Operation: Collects user requests and necessary information through the terminal interface.

[0883] Output: The terminal sends the user's input data (document request content) to the next step.

[0884] Step 2:

[0885] The device sends user input information and sentiment data to the server.

[0886] Input: User request content and real-time sentiment data from the sentiment engine.

[0887] Operation: The terminal sends this data to the server.

[0888] Output: The server receives user requests and sentiment data.

[0889] Step 3:

[0890] The server searches the knowledge database for past documents related to the business.

[0891] Input: User's request.

[0892] Operation: The server searches the knowledge database and extracts relevant historical document data.

[0893] Output: The server retrieves relevant historical document data.

[0894] Step 4:

[0895] The server passes the acquired historical document data and user sentiment data to the generating AI.

[0896] Input: Past document data, user sentiment data.

[0897] Operation: The server passes the data to the AI ​​that generates it.

[0898] Output: The generation AI receives input data for document generation.

[0899] Step 5:

[0900] The generation AI sets prompt sentences and generates a new draft document based on the content and structure of past documents, as well as collected sentiment data.

[0901] Input: Past document data, user sentiment data.

[0902] Operation: The generating AI sets prompt sentences based on sentiment data and generates a new document.

[0903] Output: The generated draft document.

[0904] Specific data calculations: Use sentiment data to adjust the tone of a document and generate appropriate prompt sentences (e.g., "Generate recommended content about recent movies in a positive tone").

[0905] Step 6:

[0906] The generated draft document is sent from the server to the user's terminal.

[0907] Input: The generated draft document.

[0908] Operation: The server sends the document to the user's terminal.

[0909] Output: The user terminal receives and displays the document.

[0910] Step 7:

[0911] The user reviews the displayed draft document and makes modifications or additions as needed using a text editor.

[0912] Input: The generated draft document.

[0913] Operation: The user modifies and adds to the document using a text editor.

[0914] Output: The document after corrections and additions have been completed.

[0915] Step 8:

[0916] Once the user has completed any modifications or additions to the document, it will be saved on the device as the final document.

[0917] Input: Documents that have been corrected or added to.

[0918] Operation: The terminal saves the final document and converts it to a document format if necessary.

[0919] Output: The final document is saved and formatted as needed.

[0920] This enables the generation of high-quality documents that are adapted to the user's emotions.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] [Fourth Embodiment]

[0925] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0926] 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.

[0927] 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).

[0928] 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.

[0929] 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.

[0930] 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).

[0931] 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.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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".

[0938] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[0939] ---

[0940] This invention relates to a system for streamlining the creation of drafts in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The following is a natural language description of how this system works.

[0941] In the system of the present invention, the user first accesses the system using a terminal and requests the creation of a draft of a specific business document. Specifically, the user selects an option such as "Create a draft of a failure report" through the system's dedicated interface and enters the necessary information.

[0942] The server receives requests from users and accesses the knowledge database to search for relevant documents from the past. This knowledge database stores a large amount of document data related to back-office operations and is managed in a closed environment, ensuring security. Based on the request, the server filters the data for the specified period and the system in which the problem occurred, extracting the most relevant document data.

[0943] The extracted data is passed to a generation AI. The generation AI automatically generates a new draft based on the content and structure of past documents. This is done by filling in the necessary information based on templates and formats of past incident reports.

[0944] The generated draft is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[0945] Finally, the document, after the user has made revisions and additions, is saved on the device. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[0946] As a concrete example, consider the workflow when a user creates a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as an overview of the outage, the scope of impact, and the results of the cause investigation. The user receives this draft, adds and modifies details, and completes the final report.

[0947] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations, saving time and effort, and enabling the generation of high-quality documents.

[0948] The following describes the processing flow.

[0949] Step 1:

[0950] The user logs into the system using their terminal and selects the "Create a draft of the incident report" option. The user then enters information about the period in question and the system where the problem occurred.

[0951] Step 2:

[0952] The terminal sends user input information to the server. The server receives this request and parses its contents.

[0953] Step 3:

[0954] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[0955] Step 4:

[0956] The server extracts data and passes it to the generation AI. The generation AI automatically generates a new draft document based on the content and structure of past documents.

[0957] Step 5:

[0958] The AI ​​generates a draft document which is then returned to the server. The server organizes and formats this data and sends it to the user's terminal.

[0959] Step 6:

[0960] The terminal displays the draft document it received to the user. The user uses a text editor to review the document's contents and make corrections or additions as needed.

[0961] Step 7:

[0962] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal then converts this final document to a document format (PDF or Word).

[0963] Step 8:

[0964] The terminal uploads the final document to the server. The server then stores this document again in the knowledge database, making it available as reference data for the future.

[0965] The above outlines the series of processing steps involved in the system generating a draft document and completing the final document. This allows users to efficiently obtain high-quality documents.

[0966] (Example 1)

[0967] 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".

[0968] Traditional document creation processes in back-office operations often involve manual editing and creation, which is time-consuming and labor-intensive, thus creating a need for increased efficiency. Furthermore, document quality tends to vary, making it difficult to maintain consistency and accuracy. This invention aims to solve these problems.

[0969] 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.

[0970] In this invention, the server includes means for a user to request the creation of a specific business document using a terminal; means for the server to receive the request and search and extract relevant past documents from a knowledge database; means for the server to send a prompt message to a generation AI model and automatically generate a draft of a new document; means for sending and displaying the generated draft on the user's terminal; and means for receiving revisions from the user's terminal and creating the final document. This streamlines the time and effort required for document creation and enables the generation of high-quality, consistent documents.

[0971] A "terminal" is a device used by a user to access a system, and usually refers to electronic devices such as computers and smartphones.

[0972] A "user" refers to an individual or group that uses a system to create specific business documents.

[0973] A "server" refers to a central management system that receives requests from users and handles access to knowledge databases and integration with generated AI models.

[0974] A "knowledge database" refers to a database designed to store past business documents and allow for specific searches and extractions.

[0975] A "generative AI model" refers to an artificial intelligence model that learns the content and structure of past documents and automatically generates a draft of a new document based on that learning.

[0976] A "prompt statement" refers to an input statement used to instruct a generative AI model to create a draft of a new document.

[0977] A "draft" is an incomplete document automatically generated by a generative AI model, serving as the foundation for the user to create the final document.

[0978] This invention relates to a system for improving the efficiency of document creation in back-office operations. This system primarily consists of three components: a server, a terminal, and a user. The operation and specific examples of this system are described below.

[0979] System Overview

[0980] The system of this invention has the following main functions:

[0981] 1. User input of document creation request

[0982] 2. Server receives requests and extracts data from the knowledge database.

[0983] 3. Generating a draft of a new document using a generative AI model.

[0984] 4. Server-generated draft submission and display

[0985] 5. User review, modification, and addition to the draft.

[0986] 6. Saving the final document and storing it in the database.

[0987] Hardware and software to use

[0988] Device: A computer or smartphone used by a user.

[0989] Server: A data server used to operate the central management system.

[0990] Knowledge database: A database that stores past business documents.

[0991] Generative AI model: An AI model used for learning and generating documents.

[0992] Operation details

[0993] User input of request

[0994] Users log in to the system using a terminal and request document creation through a dedicated interface. For example, they might select the option to "create a draft of an incident report" and enter necessary information such as the date and time of the incident and the affected systems.

[0995] The server receives requests and extracts data from the knowledge database.

[0996] The server receives requests from users and accesses the knowledge database. It filters past relevant document data from the knowledge database and extracts documents that are highly relevant to the specified period or issue.

[0997] Generating draft documents using a generative AI model.

[0998] Based on the extracted data, the server sends prompt messages to the generative AI model. The generative AI model has learned the content and structure of past documents and automatically generates a draft of a new document based on that.

[0999] Examples of specific prompt messages:

[1000] "Please create a draft of the incident report based on the following data. The incident occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was a system downtime, and the cause is estimated to be server overload."

[1001] Server-generated draft transmission and display

[1002] The generated draft is sent from the server to the user's terminal. The user receives this draft on their terminal and displays it in a dedicated text editor.

[1003] User review, modification, and addition to the draft.

[1004] Users review the draft displayed on their device and make changes or additions as needed. For example, they can input or correct details of new issues or countermeasures.

[1005] Saving the final document and storing it in the database.

[1006] The final document, after revisions and additions have been made, is saved on the device. It is then uploaded to the server and stored in the knowledge database. Users can choose to save the document in PDF or Word format.

[1007] Specific example

[1008] This example illustrates how a user can create a "Report on Last Week's System Outage." The user enters information such as the date and time of the outage and the affected systems, then submits a request. The server searches the knowledge database for relevant outage reports, and a generation AI model creates a draft of a new document. This draft includes an overview of the outage, the scope of its impact, and the results of the root cause investigation. The user receives this draft and adds or modifies details to complete the final report.

[1009] As a result of these processes, the system of the present invention streamlines document creation in back-office operations, saving time and effort, and enabling the generation of high-quality, consistent documents.

[1010] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1011] Step 1:

[1012] The user logs into the system's dedicated interface using a terminal and requests document creation. Specifically, they select the option to "Create a draft of the incident report" and enter information such as the date and time of the incident, the name of the affected system, and a summary. The input data provided is: Date and time of incident "October 5, 2023", Name of affected system "XYZ system", Summary "System down".

[1013] Step 2:

[1014] The server receives a request from the user. Here, the server parses the HTTP POST request and extracts its contents. The extracted data includes information such as the date and time of the failure, the name of the affected system, and a summary. This is stored in an internal data structure and used for the next processing step.

[1015] Step 3:

[1016] The server uses the extracted data to query the knowledge database. It generates an SQL query to search and extract relevant historical document data based on a specified period and system name. As a result of this query, similar incident reports are extracted. For example, it outputs "Historical Incident Report Data".

[1017] Step 4:

[1018] The server creates prompt statements for the generating AI model based on the extracted data. The generating AI model receives past failure report data along with the prompt statements. A specific prompt statement will be used: "Please create a draft failure report based on the following data. The failure occurred on October 5, 2023, the affected system was the XYZ system, the main symptom was system downtime, and the cause is estimated to be server overload." The prompt statements and related document data are provided as input data to the AI ​​model.

[1019] Step 5:

[1020] The generation AI model generates a draft of a new document based on the prompt text and input data. This is a process that automatically creates a new document following the templates and formats of past documents. The generated draft includes information such as the date and time of the failure, the scope of impact, and the results of the root cause investigation. The output is a "generated failure report draft".

[1021] Step 6:

[1022] The server sends the generated draft to the user's terminal in real time. The server sends the generated draft to the terminal in JSON format, and the terminal parses the received JSON data and displays it in a dedicated text editor. Specifically, it sends the "generated draft of the incident report".

[1023] Step 7:

[1024] The user reviews the draft generated in a text editor on their terminal and makes modifications and additions as needed. For example, they input and modify details of new problems, causes, and countermeasures. After the user completes their work, they save the modified document data. The modified and added document information is provided as input data.

[1025] Step 8:

[1026] The user saves the final document, after making any revisions or additions, on their device and then uploads it to the server. The server stores the final document in a knowledge database, making it available as reference data for the future. For example, users can choose to save the document in PDF or Word format. Once the saved final document is stored in the knowledge database, the "finally saved document" is obtained as output data.

[1027] The above outlines the system's processing steps, with each step described in detail, including the specific actions of the input and output.

[1028] (Application Example 1)

[1029] 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".

[1030] Traditional methods for inventory management and sales report creation in physical stores often involve manual processes, requiring significant time and effort, and can lead to data errors and omissions. Furthermore, efficient business operations require fast and accurate document creation, but a suitable system for this purpose has not existed. This invention aims to solve these problems and provide a system for streamlining and automating inventory management and sales report creation in physical stores.

[1031] 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.

[1032] In this invention, the server includes means for searching past documents related to business operations from a knowledge database, means for automatically generating inventory management documents and sales report documents using generation AI, means for transmitting and displaying the generated inventory management documents and sales report documents on a user terminal, and means for receiving revisions from the user terminal and creating the final document. This enables efficient and accurate document creation in physical stores.

[1033] A "knowledge database" is a database that stores past documents related to business operations and is managed in a closed environment.

[1034] "Generative AI" is artificial intelligence that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[1035] "Past documents related to business operations" refers to documents related to back-office operations in physical stores, such as inventory management and sales reports.

[1036] "User terminals" refer to devices such as smartphones and tablets used by employees in physical stores.

[1037] An "inventory management document" is a document used to manage and report the inventory status of products in a physical store.

[1038] A "sales report document" is a report that compiles sales information from physical stores.

[1039] "Correction details" refers to corrections or additional information in the final document sent from the user's terminal.

[1040] A "final document" is a document that has been completed and edited on the user's terminal.

[1041] This invention relates to a system for streamlining and automating inventory management and sales report creation in physical stores. This system primarily consists of a server, user terminals, a knowledge database, and a generating AI. The following specifically describes the operation of this system.

[1042] First, users access the system using user devices such as smartphones or tablets at physical stores. When creating inventory reports or sales reports, users select options such as "Create last month's inventory management report" through a dedicated interface and enter the necessary information, such as the report period and the store ID.

[1043] When the server receives a request from a user, it accesses the knowledge database to search for relevant documents from the past. This knowledge database contains a large amount of past inventory management documents and sales report documents, and is managed in a closed environment accessible only to authorized personnel. Based on the request, the server filters the data for the specified period and store, and extracts the most relevant document data.

[1044] The extracted document data is passed to a generating AI. This AI learns the content and structure of past documents and automatically generates drafts of new inventory management documents and sales report documents based on that learning. For example, it might use a past inventory report template as a base and fill in inventory quantities and sales information for each product item.

[1045] The generated draft is sent from the server to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed using a text editor. For example, they can add information about newly arrived products or the impact of special promotions.

[1046] Finally, the document, after the user has made revisions and additions, is saved on the user's terminal. This final document is converted to a document format (e.g., PDF or Word) as needed and managed within the system. It can also be uploaded to the server to be stored in the knowledge database and used as reference data for the future.

[1047] As a concrete example, let's consider the workflow when a user creates a "last month's inventory report." The user enters the report period and store ID, and submits the request. The server searches and extracts relevant inventory reports from the knowledge database, and a generation AI creates a new draft. This draft includes information such as inventory quantity for each product, order history, and sales information. The user receives it, adds and modifies details, and completes the final report.

[1048] An example of a prompt message is: "To create last month's inventory report, generate a draft of the new report based on data from January 1, 2023 to January 31, 2023."

[1049] The above is a detailed description of embodiments of the present invention.

[1050] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1051] Step 1:

[1052] Users access the system using smartphones or tablets in physical stores and submit requests to create necessary business documents (e.g., inventory reports and sales reports). Through a dedicated interface, users input information such as the report's target period and store ID. This input is treated as request data sent to the server.

[1053] Step 2:

[1054] The server analyzes the request data received from the user. Based on conditions such as the type of report entered (inventory report or sales report), the target period, and the store ID, it searches the knowledge database for relevant past documents. Specifically, it filters this data to extract highly relevant past inventory management documents and sales report documents.

[1055] Step 3:

[1056] The server passes the historical document data extracted as search results to the generating AI. The generating AI learns the content and structure of these historical documents and automatically generates a draft of a new document. The input for this step is the extracted document data, and the output is a draft of a newly generated inventory management document or sales report document.

[1057] Step 4:

[1058] The server sends a draft generated by the AI ​​to the user's terminal. The user's terminal receives this data and displays it to the user. The user reviews the received draft and makes modifications or additions as needed. A dedicated text editor is provided on the user's terminal that allows for modifications and additions. The input is the generated draft document, and the output is the modified / added document.

[1059] Step 5:

[1060] The user saves the final document, after making revisions and additions, from their terminal. The final document is then converted to a specific document format (e.g., PDF or Word) as needed and uploaded to the server. The server then stores the final document back in the knowledge database for future reference. The input is the revised / added document, and the output is the final document stored in the knowledge database.

[1061] The above outlines the specific processing steps for a system that streamlines and automates inventory management and sales reporting in physical stores.

[1062] 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.

[1063] Understood. Below, I have prepared the "Modes for Carrying Out the Invention" section of the specification based on the claims.

[1064] ---

[1065] This invention relates to a system for streamlining the creation of drafts in back-office operations and for generating documents while considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and by combining them with an emotion engine, it achieves advanced document creation.

[1066] First, the user accesses the system using a terminal and requests the creation of a draft of a specific business document. The user selects an option, such as "Create a draft of an incident report," through the system's dedicated interface and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[1067] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[1068] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[1069] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, they might enter details of a new problem, its cause, and countermeasures.

[1070] Once the user has made revisions and additions, the document is saved on the device as the final document. This final document is converted to a document format (e.g., PDF or Word) as needed. It can also be uploaded to the server, where it is stored again in the knowledge database and used as reference data for the future. At this time, the sentiment data collected by the sentiment engine is also added to the knowledge database, which will help improve the accuracy of future document generation.

[1071] As a concrete example, consider a user creating a "Report on Last Week's System Outage." The user inputs information such as the date and time of the outage and the affected systems, and submits a request. The server searches and extracts relevant outage reports from the knowledge database, and a generation AI creates a new draft. At this stage, the document's content is adjusted based on the user's emotional data. For example, if the user is feeling stressed, the generated document will be concise and clear, designed to reduce the user's mental burden. The user receives this draft and adds and modifies details to complete the final report.

[1072] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and, by taking user emotions into consideration, enables the creation of higher-quality documents.

[1073] The following describes the processing flow.

[1074] Step 1:

[1075] A user logs into the system using a terminal and requests the creation of a draft of a specific business document. For example, they might select the "Create a draft of an incident report" option and enter information about the period and affected systems. At this time, the emotion engine recognizes the user's emotions in real time from their input actions, voice, and facial expressions, and records this data.

[1076] Step 2:

[1077] The terminal sends user input information and sentiment data to the server. The server receives this request and parses its contents. The request contains basic information for creating a draft and user sentiment data.

[1078] Step 3:

[1079] The server accesses the knowledge database and searches for past failure reports related to the specified period and target system. It then extracts highly relevant data from the search results.

[1080] Step 4:

[1081] The server passes the extracted data and sentiment data to the generating AI. The generating AI automatically generates a new draft document based on the content and structure of past documents, as well as the user's sentiment data. In this process, the tone and content of the document are adjusted to take sentiment data into consideration.

[1082] Step 5:

[1083] The AI ​​generates a draft document which is then returned to the server. The server reviews this data and sends it to the user's terminal. The document incorporates expressions and structures that are adapted to the user's emotions.

[1084] Step 6:

[1085] The terminal displays a draft document it received to the user. The user reviews the displayed draft document and uses a text editor to modify or add to its contents. For example, they might enter details, causes, and countermeasures for a newly occurring problem.

[1086] Step 7:

[1087] The user saves the document after making revisions and additions, and confirms it as the final document. The terminal converts this final document to a document format (e.g., PDF or Word) and sends it to the server.

[1088] Step 8:

[1089] The server receives the final document and stores it in the knowledge database. The sentiment data collected by the sentiment engine is also added to the knowledge database and used as reference data for future document generation.

[1090] The above outlines the series of processing steps involved in a system incorporating an emotion engine, from generating a draft document to completing the final document. This allows users to obtain high-quality documents efficiently and with minimal psychological burden.

[1091] (Example 2)

[1092] 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".

[1093] Conventional automated document generation systems rely solely on past document data, which limits their ability to generate documents that reflect user emotions. This makes it difficult to provide documents suitable for situations where users are likely to experience stress or for specific emotional states.

[1094] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for searching past documents related to business from a knowledge database, means for automatically generating documents based on user sentiment data using generation AI, and means for transmitting and displaying the generated documents on a user terminal. This makes it possible to automatically generate documents that take user sentiment into consideration.

[1095] A "knowledge database" is a data storage system that stores past business documents and related data and manages them in a closed environment.

[1096] "Generative AI" is an artificial intelligence technology that uses machine learning algorithms to learn from past documents and related data, and automatically generates new documents.

[1097] A "user terminal" is a hardware device, such as a computer or mobile device, that a user uses to access and operate a system.

[1098] An "emotion engine" refers to software or algorithms used to analyze and collect user emotional data in real time.

[1099] "Emotional data" refers to data about the user's emotional state collected and analyzed by the emotion engine.

[1100] "Automatic generation" refers to the process by which a generation AI automatically creates new documents based on pre-learned data, using user input and sentiment data.

[1101] A "closed environment" refers to a secure, access-restricted environment that is accessible only to specific users or system administrators.

[1102] "Modification details" refers to data that indicates the additions and changes made by the user to the generated document.

[1103] This invention relates to a system that streamlines document generation in back-office operations and generates high-quality documents by considering user emotions. This system mainly consists of three components: a server, a terminal, and a user, and achieves advanced document generation by combining them with an emotion engine.

[1104] System Configuration

[1105] This system uses the following main hardware and software.

[1106] Hardware: Client PCs, mobile devices, server machines

[1107] Software: Sentiment engines (e.g., Sentiment Analysis API), knowledge databases (e.g., MySQL), generative AI (e.g., OpenAI GPT-4), document format conversion tools (e.g., Adobe Acrobat)

[1108] Operating procedures and specific examples

[1109] First, the user accesses the system using a terminal (e.g., a PC or mobile device) and requests the creation of a draft of a specific business document. The user logs into the system's dedicated interface, selects an option such as "Create a draft of an incident report," and enters the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[1110] Data transmission and analysis

[1111] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment. Based on the request content and sentiment data, the server extracts highly relevant document data.

[1112] Document generation process

[1113] The extracted data is passed to a generative AI. The generative AI (e.g., OpenAI GPT-4) automatically generates a new draft document based on the content and structure of past documents, as well as the collected sentiment data. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process generates a user-friendly document.

[1114] Document review and correction

[1115] The generated draft document is sent back from the server to the terminal. The terminal receives this data and displays it to the user. For example, if a user is creating a "Report on last week's system failure," they would review the generated draft and modify or add new details about the failure, its cause, and countermeasures using a text editor.

[1116] Saving the final document and closing the process.

[1117] Documents that have been edited or added to by the user are saved on the device as the final document. Documents can be converted to PDF or Word format as needed. They can also be uploaded to the server, where they are stored again in the knowledge database and used as reference data for the future. At this time, sentiment data collected by the sentiment engine is also added to the knowledge database, helping to improve the accuracy of future document generation.

[1118] Example prompt statements

[1119] Here are some examples of specific prompt messages:

[1120] "Please prepare a draft report on the system failure. The failure occurred on October 1, 2023, and the affected system is the sales management system. The cause of the failure was insufficient server memory."

[1121] In this way, the present invention is a system that improves the efficiency of document creation in back-office operations and enables the creation of higher-quality documents by taking user emotions into consideration.

[1122] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1123] Step 1:

[1124] The user accesses the system using a terminal and logs into a specialized interface. The user selects an option such as "Create Incident Report" and enters the necessary information. At this time, the emotion engine is executed and collects real-time emotion data by analyzing the user's facial expressions and other factors.

[1125] Input: "Create Incident Report" option, detailed incident information entered by the user, and real-time sentiment data.

[1126] Output: User input information and sentiment data packets.

[1127] Step 2:

[1128] The terminal combines user input information and sentiment data into packets and sends them to the server. These data packets are sent to the server via the internet using a secure protocol (e.g., HTTPS).

[1129] Input: Packets containing user input information and sentiment data.

[1130] Output: Data packets sent to the server.

[1131] Step 3:

[1132] The server analyzes the data packets it receives. Specifically, it extracts request details (e.g., creating an incident report), sentiment data, and input information (e.g., the date and time of the incident and the affected systems).

[1133] Input: Data packet.

[1134] Output: A data object containing parsed request details, sentiment data, and input information.

[1135] Step 4:

[1136] The server searches the knowledge database based on the analysis results and extracts relevant past incident reports. The server generates queries to search past document data and executes them against the knowledge database.

[1137] Input: The parsed data object.

[1138] Output: Dataset of extracted related documents.

[1139] Step 5:

[1140] The server provides extracted document data and sentiment data to a generative AI model. The generative AI model (e.g., OpenAI GPT-4) compares this data with training data and generates a new draft document. Based on the sentiment data, it adjusts the tone and expression of the document.

[1141] Input: Extracted document data and sentiment data.

[1142] Output: The generated draft document.

[1143] Step 6:

[1144] The server sends the generated draft document to the terminal. The generated document is sent to the terminal using a secure protocol and displayed in the user interface.

[1145] Input: The generated draft document.

[1146] Output: Draft document sent to the terminal.

[1147] Step 7:

[1148] Review the draft document received by the user and make any necessary corrections or additions. For example, enter specific details of the problem, its cause, and proposed solutions using a text editor.

[1149] Input: The generated draft document.

[1150] Output: Documents modified or added to by the user.

[1151] Step 8:

[1152] The terminal saves the document as the final version after the user has completed modifications and additions. The document is converted to PDF or Word format as needed. It can also be uploaded to the server and stored again in the knowledge database.

[1153] Input: The last document modified or added to by the user.

[1154] Output: The last saved document, the last document uploaded to the knowledge database.

[1155] Step 9:

[1156] The server adds the final document and sentiment data to the knowledge database. This is expected to improve the accuracy of future document generation processes.

[1157] Input: Last saved document, sentiment data.

[1158] Output: The final document and sentiment data added to the knowledge database.

[1159] (Application Example 2)

[1160] 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".

[1161] In modern back-office operations, a significant amount of time and effort is spent on document creation, which is a major challenge. Furthermore, the generated documents often fail to align with user emotions and needs, leading to stress and frustration. This is particularly true for content delivery services, where creating relevant recommendation documents for users is currently difficult.

[1162] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for searching past documents related to the business from a knowledge database, means for automatically generating quotation documents using a generation AI, means for transmitting and displaying the generated quotation documents on a user terminal, means for combining a sentiment engine that collects user sentiment data and reflects it in document generation, and means for the generation AI to set prompt sentences based on sentiment data and generate highly accurate documents. This makes it possible to generate high-quality documents that are adapted to the user's sentiment.

[1163] A "knowledge database" is a database that stores past business documents and is accessed in a closed environment.

[1164] "Generative AI" is an artificial intelligence technology that learns the content and structure of past documents and automatically generates new documents based on that knowledge.

[1165] A "user terminal" is a device used by a user to access a system and input information or view documents.

[1166] "Emotional data" refers to data that analyzes and quantifies users' emotions.

[1167] An "emotion engine" is a system component that collects user emotion data and incorporates it into document generation.

[1168] A "prompt" is an instruction given to the AI ​​for document generation, used to determine the direction of document creation.

[1169] The system that realizes this invention mainly consists of three components: a server, a terminal, and a user. Furthermore, by combining it with an emotion engine, it enables advanced document creation.

[1170] First, the user accesses the system using a terminal and requests the creation of a draft for a specific business document. For example, they might select an option such as "Create a recommendation document about recent movies" and enter the necessary information. During this process, the emotion engine recognizes the user's emotions in real time and collects that data.

[1171] Next, the terminal sends the user's input information and sentiment data to the server. The server receives and analyzes this request and searches for relevant data in the knowledge database. The knowledge database stores past relevant document data and is managed in a closed environment to ensure security. Based on the request content and sentiment data, the server extracts highly relevant document data.

[1172] The extracted data is passed to a generative AI. Based on the content and structure of past documents, as well as the collected sentiment data, the generative AI automatically generates a new draft document. Based on the sentiment data, the document's tone and content are adjusted to suit the user's emotions. This process results in a more user-friendly document.

[1173] The generated draft document is sent from the server to the user's terminal. The terminal receives this data and displays it to the user. The user reviews the displayed draft document and makes corrections or additions as needed using a text editor. For example, when creating a "recommendation document about recent movies," if the user's mood is positive, the generation AI will use a prompt such as "Generate recommendation content about recent movies in a positive tone."

[1174] The program's processing can be explained in natural language as follows:

[1175] The server uses the TextBlob library to analyze user input text and calculate a sentiment score. Then, using the HuggingFace Transformers library, a generative AI model generates a document based on the prompt text. This process adapts the document's tone to take the user's sentiment data into account.

[1176] As a concrete example, if a user requests "Please recommend some recent movies," the TextBlob library is used to calculate a sentiment score. If the sentiment score is high, the generated prompt will be "Please generate recommended content about recent movies in a positive tone." Based on this prompt, the generation AI creates a recommendation document, which is then ultimately provided to the user.

[1177] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1178] Program processing flow and detailed explanation

[1179] Step 1:

[1180] Users access the system using a terminal and request the creation of a draft for a specific business document.

[1181] Input: The user enters a request such as "Create a recommendation document about recent movies."

[1182] Operation: Collects user requests and necessary information through the terminal interface.

[1183] Output: The terminal sends the user's input data (document request content) to the next step.

[1184] Step 2:

[1185] The device sends user input information and sentiment data to the server.

[1186] Input: User request content and real-time sentiment data from the sentiment engine.

[1187] Operation: The terminal sends this data to the server.

[1188] Output: The server receives user requests and sentiment data.

[1189] Step 3:

[1190] The server searches the knowledge database for past documents related to the business.

[1191] Input: User's request.

[1192] Operation: The server searches the knowledge database and extracts relevant historical document data.

[1193] Output: The server retrieves relevant historical document data.

[1194] Step 4:

[1195] The server passes the acquired historical document data and user sentiment data to the generating AI.

[1196] Input: Past document data, user sentiment data.

[1197] Operation: The server passes the data to the AI ​​that generates it.

[1198] Output: The generation AI receives input data for document generation.

[1199] Step 5:

[1200] The generation AI sets prompt sentences and generates a new draft document based on the content and structure of past documents, as well as collected sentiment data.

[1201] Input: Past document data, user sentiment data.

[1202] Operation: The generating AI sets prompt sentences based on sentiment data and generates a new document.

[1203] Output: The generated draft document.

[1204] Specific data calculations: Use sentiment data to adjust the tone of a document and generate appropriate prompt sentences (e.g., "Generate recommended content about recent movies in a positive tone").

[1205] Step 6:

[1206] The generated draft document is sent from the server to the user's terminal.

[1207] Input: The generated draft document.

[1208] Operation: The server sends the document to the user's terminal.

[1209] Output: The user terminal receives and displays the document.

[1210] Step 7:

[1211] The user reviews the displayed draft document and makes modifications or additions as needed using a text editor.

[1212] Input: The generated draft document.

[1213] Operation: The user modifies and adds to the document using a text editor.

[1214] Output: The document after corrections and additions have been completed.

[1215] Step 8:

[1216] Once the user has completed any modifications or additions to the document, it will be saved on the device as the final document.

[1217] Input: Documents that have been corrected or added to.

[1218] Operation: The terminal saves the final document and converts it to a document format if necessary.

[1219] Output: The final document is saved and formatted as needed.

[1220] This enables the generation of high-quality documents that are adapted to the user's emotions.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] 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.

[1229] 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."

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] The following is further disclosed regarding the embodiments described above.

[1243] Understood. I have prepared the claims according to the following format.

[1244] (Claim 1)

[1245] A means of searching for past documents related to business operations from a knowledge database,

[1246] A method for automatically generating quotation documents using generation AI,

[1247] A means of sending and displaying the generated quotation document on the user's terminal,

[1248] A means of receiving revisions from the user terminal and creating the final document,

[1249] A system that includes this.

[1250] (Claim 2)

[1251] The system according to claim 1, wherein the knowledge database stores past business documents and is accessed in a closed environment.

[1252] (Claim 3)

[1253] The system according to claim 1, wherein the generating AI learns the content and structure of past documents and creates a new estimate document based on that.

[1254] "Example 1"

[1255] (Claim 1)

[1256] A means by which a user can request the creation of a specific business document using a terminal,

[1257] The server receives a request and has a means to search and extract relevant past documents from the knowledge database.

[1258] A means by which the server sends prompt text to the generation AI model and automatically generates a draft of a new document,

[1259] A means of sending the generated draft to the user's terminal and displaying it,

[1260] A means of receiving revisions from the user terminal and creating the final document,

[1261] A system that includes this.

[1262] (Claim 2)

[1263] The system according to claim 1, wherein the knowledge database stores past business documents and is accessed in a closed environment.

[1264] (Claim 3)

[1265] The system according to claim 1, wherein a generative AI model learns the content and structure of past documents and creates a draft of a new document based on that.

[1266] "Application Example 1"

[1267] Processing procedure

[1268] The original claims relate to a system that includes document retrieval from a knowledge database, automatic generation by AI, receiving display and modification data from a user terminal, and final document creation.

[1269] 2. Extract the novel aspects of the technology from the explanation of the application examples.

[1270] The application example focused on inventory management and drafting sales reports, specifically using smart devices to operate in a physical store. This demonstrated the processes of inventory management and sales report creation in detail.

[1271] The new invention will encompass not only back-office operations but also processes for inventory management and sales report creation in physical stores.

[1272] (Claim 1)

[1273] A means of searching for past documents related to business operations from a knowledge database,

[1274] A method for automatically generating inventory management documents and sales report documents using generation AI,

[1275] A means of sending and displaying generated inventory management documents and sales report documents on the user's terminal,

[1276] A means of receiving revisions from the user terminal and creating the final document,

[1277] A system that includes this.

[1278] (Claim 2)

[1279] The system according to claim 1, wherein the knowledge database stores past business documents and is accessed in a closed environment.

[1280] (Claim 3)

[1281] The system according to claim 1, wherein the generating AI learns the content and structure of past documents and creates new inventory management documents and sales report documents based on that.

[1282] Output condition check

[1283] I wrote the above text following the format.

[1284] "Example 2 of combining an emotion engine"

[1285] (Claim 1)

[1286] A means of searching for past documents related to business operations from a knowledge database,

[1287] A means of automatically generating documents based on user sentiment data using generative AI,

[1288] A means of sending and displaying the generated document on the user's terminal,

[1289] A means of receiving revisions from the user terminal and creating the final document,

[1290] A means of collecting user emotional data using an emotion engine,

[1291] A means of adding emotional data to a knowledge database,

[1292] A system that includes this.

[1293] (Claim 2)

[1294] The system according to claim 1, wherein the knowledge database stores past business documents and sentiment data and is accessed in a closed environment.

[1295] (Claim 3)

[1296] The system according to claim 1, wherein the generating AI learns the content, structure, and sentiment data of past documents and creates a new document based on that.

[1297] "Application example 2 of combining emotional engines"

[1298] (Claim 1)

[1299] A means of searching for past documents related to business operations from a knowledge database,

[1300] A method for automatically generating quotation documents using generation AI,

[1301] A means of sending and displaying the generated quotation document on the user's terminal,

[1302] A means of receiving revisions from the user terminal and creating the final document,

[1303] A method that combines a sentiment engine that collects user sentiment data and reflects it in document generation,

[1304] A method for generating documents with high accuracy by having a generation AI set prompt sentences based on sentiment data,

[1305] A system that includes this.

[1306] (Claim 2)

[1307] The system according to claim 1, wherein the knowledge database stores past business documents and is accessed in a closed environment.

[1308] (Claim 3)

[1309] The system according to claim 1, wherein the generating AI learns the content and structure of past documents, creates a new estimate document based on that, and further adjusts the content of the document based on sentiment data. [Explanation of Symbols]

[1310] 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 searching for past documents related to business operations from a knowledge database, A method for automatically generating quotation documents using generation AI, A means for sending and displaying the generated quotation document on the user's terminal, A means of receiving revisions from the user's terminal and creating the final document, A system that includes this.

2. The system according to claim 1, wherein the knowledge database stores past business documents and is accessed in a closed environment.

3. The system according to claim 1, wherein the generating AI learns the content and structure of past documents and creates a new estimate document based on that.

Images