system

Abstract

To provide a system for automatically generating a document according to various fixed formats based on one input data.SOLUTION: The system includes: means for a user to select a fixed format and upload the fixed format to a server; means for the server to analyze the uploaded fixed format and store the analyzed fixed format in a format management database; means for the user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine, extract important information, and store the extracted important information in a database; means for the server to complement information necessary for the fixed format using an AI generated based on the analysis result stored in the database; means for the server to generate a document based on the complemented information and provide the document in a format that can be downloaded by a user; and means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Creating business documents takes a great deal of time and effort, and there is a demand for greater efficiency. Manual creation is particularly inefficient for frequently created standard documents such as contracts, customer proposal materials, and management meeting materials. Furthermore, translation work becomes even more of a burden for international projects that require multilingual support. To solve these issues, a system is needed that can automatically generate documents in a variety of standard formats based on a single input data set. [Means for solving the problem]

[0005] The present invention solves these problems by providing a system that includes: a means for a user to select a standard format and upload it to a server; a means for the server to analyze the uploaded standard format and store it in a format management database; a means for a user to upload original data to the server; a means for the server to analyze the original data using a natural language processing engine, extract important information, and store it in a database; a means for the server to supplement the information necessary for the standard format using a generation AI based on the analysis results stored in the database; a means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and a means for the server to use a multilingual translation API to translate the generated document into the user's desired language and provide the translated document.

[0006] A "standard format" is a document style or template designed for a specific purpose.

[0007] A "server" is a computer system that receives requests from clients and processes data and provides services.

[0008] "User" refers to an individual or corporation that uses the system to create business documents.

[0009] "Original data" refers to data that contains the information that forms the basis of business documents, and generally refers to documents in text format.

[0010] A "natural language processing engine" is an algorithm and software that allows a computer to analyze human language and understand its meaning.

[0011] A "database" is a system for centrally storing data and accessing and managing it as needed.

[0012] "Generative AI" is an artificial intelligence algorithm that automatically generates a specific output based on input data.

[0013] "Document" refers to a document created in a particular format, including formats such as PDFs and Word documents.

[0014] A "translation API" is an interface for an automatic translation service that is provided in a form that can be used by other applications.

[0015] "Multilingual support" refers to the ability to support multiple different languages.

[0016] The "format management database" is a database for organizing, saving, and managing standard formats.

[0017] "Complement" refers to filling in incomplete or missing information to make it complete. [Brief explanation of the drawings]

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

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

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

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

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention is an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. An embodiment of the present invention will be described below.

[0040] First, the user selects and uploads a standard format (e.g., a contract template or a customer proposal template) using a client terminal. The server receives this format, analyzes its structure, and stores it in a format management database. At this stage, the sections and fields within the template are identified and centrally managed.

[0041] Next, the user uploads the source data (e.g., proposals or contracts from suppliers) from the client device. The server receives this source data and uses a natural language processing engine to segment the text, identify sections, extract keywords, etc. The analyzed information is then stored in a database as key points.

[0042] The server uses the generated AI to supplement the necessary information based on the stored analysis data. Specifically, the information stored in the database is properly arranged according to a pre-loaded standard format. The generated AI then modifies or adds data as needed. This supplementation process increases the accuracy of the final document.

[0043] Based on the information provided, the server generates the final document, which is then formatted and formatted according to a standard format and made available for download in an easy-to-view and easy-to-use format (e.g., PDF or Word document).

[0044] It also has a multilingual feature, allowing users to request multilingual support for documents generated from their client devices. The server receives the desired language and uses a translation API to translate each section of the document. The document is then regenerated based on the translated content, and the multilingual version is stored in the database. Users can download the multilingual version of the document from their client devices.

[0045] Specific examples

[0046] Example 1: Generating internal explanatory materials from contracts

[0047] 1. Format Registration:

[0048] Users upload templates for internal explanatory materials from their client terminals to the server.

[0049] The server parses the template and stores it in a format management database.

[0050] 2. Initial data entry:

[0051] The user uploads contract data from the supplier from the client terminal.

[0052] The server receives the contract data and analyzes it using a natural language processing engine.

[0053] The analyzed information is stored in a database.

[0054] 3. Generative AI Completion:

[0055] Based on the analyzed information, the server supplements the necessary information in the template for internal explanatory materials and places the data.

[0056] 4. Document generation and output:

[0057] The server generates internal explanatory materials based on the supplemented information.

[0058] The user downloads the generated materials from the client terminal.

[0059] Example 2: Generating multilingual materials

[0060] 1. Format Registration:

[0061] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0062] The server parses the template and stores it in a format management database.

[0063] 2. Initial data entry:

[0064] Users upload customer proposal documents written in Japanese from their client terminal.

[0065] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0066] The analyzed information is stored in a database.

[0067] 3. Multilingual Translation:

[0068] The server uses a translation API to translate Japanese information into English.

[0069] 4. Generative AI Completion:

[0070] Based on the translated information, the server complements the necessary information in the English template and places the data.

[0071] 5. Document generation and output:

[0072] The server generates an English version of the customer proposal document based on the supplemented information.

[0073] The user downloads the generated English version of the materials from the client terminal.

[0074] In this way, the present invention provides a system that allows users to easily automatically generate a variety of business documents, greatly improving business efficiency. In addition, the system has multilingual capabilities, making it flexible enough to handle international cases.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[0078] Step 2:

[0079] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[0080] Step 3:

[0081] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[0082] Step 4:

[0083] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[0084] Step 5:

[0085] The server stores the analysis results, and the analyzed information is organized and stored as important points in a database.

[0086] Step 6:

[0087] The server uses a generation AI to complete the information. Based on the analysis results stored in the database and pre-registered standard formats, the server uses a generation AI to complete the necessary information. The generation AI places information that fits into each section of the format and modifies or adds data as necessary.

[0088] Step 7:

[0089] The server generates the document. Based on the information provided, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[0090] Step 8:

[0091] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[0092] Step 9:

[0093] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[0094] Step 10:

[0095] The server translates the document. The server uses a translation API to translate the document into the specified language. The content of each section is automatically translated and the document is regenerated based on the translated content.

[0096] Step 11:

[0097] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[0098] Through the above steps, this system can automatically generate business documents efficiently and quickly, and also supports multiple languages.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Conventionally, creating business documents requires a great deal of effort and time, so there is a demand for a system that supports efficient document creation. Furthermore, when multilingual support is required, individual translations are required, which requires additional effort and time. Therefore, the challenge is to provide a system that can efficiently automatically generate business documents and support multiple languages.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in the database; means for the server to supplement information necessary for the standard format with a generative AI model based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a translation API and provide the translated document. This enables efficient creation of business documents and multilingual support.

[0104] "User" means a person or organization that generates and manages documents using the business document automatic generation system.

[0105] A "standard format" is a pre-set, fixed format or template such as a contract, proposal, or meeting document.

[0106] A "server" is a computer system that works in conjunction with client terminals via a network and provides core functions such as data processing, database management, and document generation.

[0107] The "format management database" is a database for storing and managing uploaded standard formats and related structural information.

[0108] "Original data" refers to unprocessed data before it is generated based on a standard format, such as a contract or proposal from a supplier.

[0109] A "natural language processing engine" is software or algorithms that analyze text data and perform segmentation, section identification, keyword extraction, etc.

[0110] A "database" is a system for centrally storing and managing data such as analyzed information, generated documents, and translation results.

[0111] A "generative AI model" is an artificial intelligence algorithm that generates and complements necessary information based on stored analysis data to create the final document.

[0112] "Translation API" means an application programming interface for automatically translating text written in one language into another language.

[0113] "Documents" are official documents such as contracts, proposals, and meeting materials generated by the server, and are provided in PDF or Word document format.

[0114] "Downloadable format" means a file format (e.g., PDF, Word) that can be easily acquired and viewed by a user using a client terminal.

[0115] "Translated Document" means a document that has been translated and reproduced into a desired language using the Translation API.

[0116] "External Plug-ins" are external software components used in conjunction with the Server to add charts and graphs or provide contractual advice.

[0117] The present invention relates to an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. Specific embodiments for carrying out the present invention will be described below.

[0118] User-generated format uploads

[0119] Users select standard formats such as contracts and proposals from their client devices and upload them to the server. The server receives the format and analyzes its structure using a natural language processing engine (e.g., SpaCy, NLTK). The analyzed information is stored in a format management database. At this stage, each section and field within the template is identified and centrally managed.

[0120] Initial data upload and analysis

[0121] The user then uploads the source data (e.g., a contract from a supplier) from the client device to the server. The server receives this data and uses a natural language processing engine to segment the text, identify sections, and extract keywords. The analyzed information is then stored in a database.

[0122] Data Complementation with Generative AI

[0123] The server uses generative AI (e.g., OpenAI GPT) to fill in the necessary information based on the analysis data stored in the database. Specifically, it arranges the information stored in the database appropriately according to a standard format, and the generative AI generates new information to fill in any missing parts.

[0124] Document generation and output

[0125] The server generates the final document based on the input information. This is done using a template engine (e.g., Jinja2) or a document generation library (e.g., ReportLab for PDF, python-docx for Word) to format the document. The generated document is provided in PDF or Word document format, and can be easily downloaded by the user from their client device.

[0126] Multilingual translation support

[0127] This system also has a multilingual translation function, allowing users to request that generated documents be translated into multiple languages. The server receives the desired language and translates the document using a translation API (e.g., Google Translate API). The translated document is regenerated and saved in the database again. Users can download the multilingual version of the document from their client device.

[0128] Specific examples

[0129] Example 1: Generating internal explanatory materials from contracts

[0130] 1. Format Registration:

[0131] Users upload templates for internal explanatory materials from their client terminals to the server.

[0132] The server parses this template and stores it in a format management database.

[0133] 2. Initial data entry:

[0134] The user uploads the contract data from the supplier to the server from the client terminal.

[0135] The server receives the contract data, analyzes it using a natural language processing engine, and stores it in a database.

[0136] 3. Generative AI Completion:

[0137] Based on the analyzed information, the server complements the necessary information in the template for internal explanatory materials and places the data.

[0138] 4. Document generation and output:

[0139] The server generates internal explanatory materials based on the supplemented information.

[0140] The user downloads the generated materials from the client terminal.

[0141] Example 2: Generating multilingual materials

[0142] 1. Format Registration:

[0143] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0144] The server parses this template and stores it in a format management database.

[0145] 2. Initial data entry:

[0146] Users upload customer proposal documents written in Japanese to the server from their client terminals.

[0147] The server receives the proposal materials, analyzes them using a natural language processing engine, and stores them in a database.

[0148] 3. Multilingual Translation:

[0149] The server uses a translation API to translate Japanese information into English.

[0150] 4. Generative AI Completion:

[0151] Based on the translated information, the server complements the necessary information in the English template and places the data.

[0152] 5. Document generation and output:

[0153] The server generates an English version of the customer proposal document based on the supplemented information.

[0154] The user downloads the generated English version of the materials from the client terminal.

[0155] Prompt Sentence Examples

[0156] Follow the generated template to complete the information translated from Japanese to English and generate the final customer proposal. The uploaded Japanese documents are stored in the database. Please follow the format of the template you use and arrange the information appropriately.

[0157] In this way, the present invention dramatically improves the efficiency of users' work and greatly reduces the burden of document preparation and multilingual support.

[0158] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0159] Step 1: Upload a template

[0160] Input: The user uses a client terminal to select a standard format and upload it to the server.

[0161] Specific operation: The user uploads a contract or proposal template from the client terminal. The server receives this template and performs structural analysis.

[0162] Data processing: The server uses a natural language processing engine (e.g. SpaCy) to parse the template text and identify sections and fields.

[0163] Output: The parsed format information is saved in the format management database.

[0164] Step 2: Upload raw data

[0165] Input: The user uploads raw data from the client terminal to the server.

[0166] Specific operation: The user uploads raw data (original data) such as contracts and proposals from the client terminal. The server receives this data and begins analyzing it.

[0167] Data processing: The server uses a natural language processing engine to segment the text, identify sections, and extract keywords.

[0168] Output: The parsed information is stored in a database.

[0169] Step 3: Data enrichment with generative AI

[0170] Input: The server obtains the information that needs to be completed based on the analysis results stored in the database.

[0171] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT) to complete the information required for the standard format based on the stored analysis data.

[0172] Data processing: The server properly places the information retrieved from the database into the template, and the generating AI generates any missing parts.

[0173] Output: The completed information is temporarily saved and used to generate the final document.

[0174] Step 4: Document generation

[0175] Input: The server receives instructions to generate the final document based on the completed information.

[0176] Specific operation: The server generates documents using a template engine (e.g., Jinja2) and a document generation library (e.g., ReportLab for PDF, python-docx for Word).

[0177] Data processing: Based on the supplemented information, the data is formatted according to a standard format and the final document is created.

[0178] Output: The final generated document is saved in PDF or Word format and can be downloaded by the user.

[0179] Step 5: Multilingual Translation (Optional)

[0180] Input: A user requests multilingual support, and the server complies.

[0181] Specific operation: The user requests multilingual support for the generated document from the client device. The server receives the desired language and translates it using a translation API (e.g., Google Translate API).

[0182] Data processing: The server translates each section of the document into the desired language and recreates the document in the new language.

[0183] Output: The translated documents are stored in a database and are available for users to download.

[0184] (Application example 1)

[0185] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0186] Improving the efficiency of business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) at logistics centers is a major challenge. Manual document creation is time-consuming and can lead to accuracy issues and human error. Furthermore, multilingual support is essential for international operations, which also involves tedious work. Against this backdrop, there is a growing need for a system that can quickly and accurately generate report documents based on standard formats and that can also support multiple languages.

[0187] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0188] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and save it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and save it in a database; means for the server to supplement information necessary for the standard format using a generation artificial intelligence based on the analysis results saved in the database; means for the server to generate documents based on the supplemented information and provide the documents in a format that the user can download; means for the server to translate the generated documents into a desired language using a multilingual translation API and provide the translated documents; and means for generating reports, inventory reports, and delivery plan reports for logistics business processes. This enables report documents to be generated quickly and accurately at logistics centers, and makes it easy to support multiple languages.

[0189] A "standard format" is a standard document template created based on a predetermined structure or format.

[0190] A "server" is a computer system that processes and provides data in response to requests from client terminals on a network.

[0191] A "natural language processing engine" is software that contains a set of algorithms and models that allow computers to understand, analyze, and generate human language.

[0192] The "format management database" is a database system that systematically stores and manages standard formats and analyzed data.

[0193] "Raw data" refers to raw data or information generated at the work site.

[0194] "Generative AI" is an AI that has the ability to generate and complement new information based on input data.

[0195] A "multilingual translation API" is a program interface for performing automatic translation between different languages.

[0196] A "logistics business process" is a series of business procedures at a logistics center, such as managing incoming and outgoing goods, inventory management, and delivery planning.

[0197] A "report" is a document that organizes and describes detailed information about each process in logistics operations.

[0198] An "inventory report" is a document used to report the quantity and status of products and materials currently held at a logistics center.

[0199] A "delivery plan report" is a document that describes plans, schedules, delivery procedures, etc. for product delivery.

[0200] This invention is a system that automatically generates documents for business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) in a logistics center. This system includes components such as a server, client terminals (e.g., smartphones, head-mounted displays), and a database.

[0201] System configuration

[0202] 1. Client Terminal

[0203] A device that allows a user to select a standard format and upload it to a server. Examples of such devices include smartphones and head-mounted displays.

[0204] 2. Server

[0205] The server analyzes the uploaded standard format and stores it in a format management database. It also analyzes the raw data uploaded by users using a natural language processing engine (e.g., SpaCy, NLTK), extracts important information, and stores it in the database.

[0206] The server uses a generation AI (e.g., GPT-3) to fill in the information required for a standard format based on the stored analysis results and generate the final document. This generated document is provided to the user in PDF or Word document format.

[0207] The server uses a multilingual translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language and provide the translated document to the user.

[0208] 3. Database

[0209] The two main roles are played by the format management database and the analysis database: the former is used for storing the standard formats, and the latter is used to store the raw analyzed data.

[0210] Workflow

[0211] 1. Format registration

[0212] Users upload templates for inventory reports and stock reports from their client terminals to the server, which analyzes them and stores them in a format management database.

[0213] 2. Entering initial data

[0214] Users upload raw data (e.g., product inventory lists) generated at the logistics center from their client terminals. The server analyzes the data using a natural language processing engine and stores important information in an analysis database.

[0215] 3. Complementation by generative AI

[0216] Based on the analyzed information, the server complements the information required for the standard format and arranges the data appropriately.

[0217] 4. Document generation and output

[0218] The server generates reports, inventory reports, etc. based on the supplemented information. Users can download the generated reports in PDF or Word format from their client terminals.

[0219] 5. Multilingual support

[0220] The server uses a translation API to translate the generated document into the desired language and provides the translated document to the user.

[0221] Examples and prompts

[0222] Example: Generating inventory reports at a distribution center

[0223] The user uploads a standard format inventory report template to the server, and sends the latest inventory list to the server as raw data. The server analyzes this using natural language processing, extracts the necessary information, and then uses generative AI to complete the report and generate the final document.

[0224] Example prompt sentence:

[0225] Input: warehouse_data.csv

[0226] Output: Generate a detailed stock report based on the given data.

[0227] As described above, the present invention significantly improves the operational efficiency of a logistics center and realizes the accurate and rapid generation of reports.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] The user uses a client terminal to select a standard format for a stock entry / exit report or inventory report and upload it to the server. A format file (e.g., Excel or Word) is used as input. The server analyzes the received format file, identifies its structure and fields, and saves them in a format management database. This standardizes the format, making subsequent data processing easier.

[0231] Step 2:

[0232] The user uploads raw data (e.g., product inventory lists and shipping instructions) generated at the logistics center from a client terminal. CSV files, Excel files, etc. are used as input. The server receives this raw data and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). Text segmentation, section identification, keyword extraction, etc. are performed, and important information is stored in an analysis database. This organizes the necessary data and puts it in an easily usable format.

[0233] Step 3:

[0234] The server uses a generative AI (e.g., GPT-3) based on the analysis data to fill in the information required for the standard format. The information stored in the analysis database is used as input. Based on this data, the generative AI automatically fills in any missing parts and places the appropriate data in the standard format. This process brings the report closer to completion.

[0235] Step 4:

[0236] The server generates the final document based on the supplemented information. The output is in a format that the user can select, such as PDF or Word document. The server generates this document and provides it in a format that the user can download from their client device. This allows users to quickly obtain high-quality reports.

[0237] Step 5:

[0238] To support multiple languages, the server uses a translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language. The input requires the text content of the generated document and the desired translation language. Using the translation API, accurate translation is performed for each required section, and the translated document is saved on the server. Finally, the multilingual version of the document is made available for download from the client device.

[0239] Step 6:

[0240] For the final supplemented information and generated documents, if required by the user, the server can provide visual analysis information using third-party plug-ins (e.g., Microsoft Graph) that add charts and graphs. The supplemented information and underlying data are used as input, allowing the user to obtain additional information that is useful for gaining a deeper understanding of their business.

[0241] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0242] The present invention combines an emotion engine that recognizes user emotions in an automatic business document generation system. This system efficiently generates business documents and provides output that responds to the user's emotions, providing a more personalized experience.

[0243] First, the user selects a template using a client terminal and uploads it to the server. The server analyzes the uploaded template, understands its structure, and stores it in the format management database. This allows the system to manage the sections and fields within the template.

[0244] Next, the user uploads the source data (e.g., a contract or proposal) from the client terminal. The server analyzes this source data using a natural language processing engine. It performs text segmentation, section identification, keyword extraction, etc., and stores the analyzed information in a database. Up to this point, the process is the same as in conventional technology.

[0245] As a feature of the present invention, the server further employs an emotion engine. The emotion engine recognizes the user's emotion based on the raw data and input data from the user. For example, it analyzes the user's emotional state (e.g., joy, anger, sadness) from the tone and style of the text entered by the user. The recognized emotion is stored in a database and used for subsequent processing.

[0246] The generation AI uses this emotional information to complement the information needed in the standard format. Specifically, it complements the information with a tone and writing style that matches the user's emotions. For example, if the user indicates a "positive" tone, the generated document will also be adjusted to be written in a positive tone.

[0247] The server generates the final document based on the input information, formatting it, and presents it to the user in a format that is easy to view and use (e.g., PDF or Word document).

[0248] It also has multilingual support, allowing users to request documents in their preferred language from their client device. The server uses a translation API to translate the document into the desired language. The translation content is also adjusted based on the user's emotional information.

[0249] Specific examples

[0250] Example 1: Generating internal explanatory materials from contracts

[0251] 1. Format Registration:

[0252] Users upload templates for internal explanatory materials from their client terminals to the server.

[0253] The server parses the template and stores it in a format management database.

[0254] 2. Initial data entry:

[0255] The user uploads contract data from the supplier from the client terminal.

[0256] The server receives the contract data and analyzes it using a natural language processing engine.

[0257] The analyzed information is stored in a database.

[0258] 3. Emotion recognition:

[0259] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[0260] 4. Generative AI Completion:

[0261] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[0262] 5. Document generation and output:

[0263] The server generates internal explanatory materials based on the supplemented information.

[0264] The user downloads the generated materials from the client terminal.

[0265] Example 2: Generating multilingual materials

[0266] 1. Format Registration:

[0267] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0268] The server parses the template and stores it in a format management database.

[0269] 2. Initial data entry:

[0270] Users upload customer proposal documents written in Japanese from their client terminal.

[0271] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0272] The analyzed information is stored in a database.

[0273] 3. Emotion recognition:

[0274] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[0275] 4. Multilingual Translation:

[0276] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[0277] 5. Document generation and output:

[0278] The server generates an English version of the customer proposal document based on the supplemented information.

[0279] The user downloads the generated English version of the materials from the client terminal.

[0280] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[0281] The processing flow will be explained below.

[0282] Step 1:

[0283] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[0284] Step 2:

[0285] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[0286] Step 3:

[0287] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[0288] Step 4:

[0289] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[0290] Step 5:

[0291] The server uses an emotion engine to recognize emotions. The server analyzes the user's emotions using the emotion engine based on the raw data and the user's input text. The analysis results are assigned as emotion tags such as "joy," "anger," and "sadness."

[0292] Step 6:

[0293] The server stores the analysis results, and the analyzed information and emotion tags are organized and stored as important points in a database.

[0294] Step 7:

[0295] The server uses a generation AI to complete the information. The server completes the information required for the standard format based on the analysis results and emotion tags stored in the database. The generation AI places data that reflects the emotion information in each section of the format.

[0296] Step 8:

[0297] The server generates the document. Based on the input information and sentiment tags, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[0298] Step 9:

[0299] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[0300] Step 10:

[0301] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[0302] Step 11:

[0303] The server translates the document. The server uses a translation API to translate the document into the specified language. It automatically translates the content of each section and adjusts the translation to reflect the recognized sentiment information.

[0304] Step 12:

[0305] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[0306] Example 2

[0307] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0308] Conventional business document generation systems can automatically generate documents based on standard formats, but lack the functionality to generate personalized documents based on the user's emotions, limiting the user experience. Furthermore, when it comes to multilingual support, it is difficult to translate documents that reflect emotional nuances, which ultimately hinders effective communication.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0310] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to analyze an emotional state using an emotion engine based on the original data and data input from the user and store the emotional information in the database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results and emotional information stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document. This enables the generation of personalized documents according to the user's emotions and multilingual translation that reflects emotional nuances.

[0311] "User" refers to a user who uses this system to generate business documents.

[0312] A "standard format" is a standardized format or template for business documents.

[0313] A "server" is a computer system that manages the entire system and analyzes, stores, and generates data.

[0314] A "format management database" is a database for storing and managing standard formats and template structures.

[0315] "Original data" refers to unanalyzed data that users initially upload to the server, such as contracts and customer proposal documents.

[0316] A "natural language processing engine" is software that analyzes text data and understands the structure and meaning of sentences.

[0317] An "emotion engine" is software for analyzing emotional states from text data or user input.

[0318] "Emotional information" refers to data that expresses a user's emotional state (e.g., joy, anger, sadness).

[0319] "Generative AI" refers to an artificial intelligence model that generates text based on specified conditions.

[0320] A "multilingual translation API" is an application programming interface that provides the functionality to translate text written in one language into another language.

[0321] "Downloadable format" means a file format in which the generated document can be easily obtained by the user (e.g., PDF, Word).

[0322] "Documents" refers to all business documents generated through this system.

[0323] This invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions. This system efficiently generates business documents and provides output that responds to the user's emotions, thereby realizing a more personalized experience.

[0324] First, a user uses a client terminal to upload a standard format, such as an internal brief or a customer proposal document, to the server. The server receives the uploaded template, analyzes its structure and sections, and stores the information in a format management database. Examples of software used include natural language processing engines such as SpaCy or BERT, and an emotion engine such as IBM Watson's sentiment analysis API.

[0325] Next, the user uploads the source data (e.g., a contract or proposal document) from the client device to the server. The server then analyzes the source data using a natural language processing engine, segmenting the text, identifying sections, extracting keywords, etc. The results of this analysis are stored in a database.

[0326] Furthermore, the server uses an emotion engine to recognize emotions from the raw data and text input by the user. The emotion information is stored in a database and used in subsequent processing. For example, if a "positive" emotion is recognized from the text input by the user, this information will be useful in the next process. In this case, the server uses IBM Watson's emotion analysis API as its emotion engine.

[0327] The server then uses generative AI (e.g., GPT-4) to fill in the necessary information within a standard format based on the analyzed information and emotional information. In this process, emotional information is reflected in the tone and style of the text, and the generated document is adjusted to match the user's emotional state.

[0328] Finally, the server generates the final business document based on the supplemented information, formats it, and provides it to the user in a format that is easy to view and use (e.g., PDF or Word document).The user can then download these generated documents from their client device.

[0329] The system also supports multiple languages, allowing users to send requests to generate documents in their preferred language from their client device. The server uses a translation API (e.g., Google Translate API) to provide the translated documents in the desired language. The system also reflects the user's emotional information and translates in an appropriate tone and style.

[0330] Specific examples

[0331] Example 1: Generating internal explanatory materials from contracts

[0332] 1. Format Registration:

[0333] The user uploads a template for an internal company briefing document from a client terminal to the server.

[0334] The server parses the template and stores it in a format management database.

[0335] 2. Initial data entry:

[0336] The user uploads contract data from the supplier from the client terminal.

[0337] The server receives the contract data and analyzes it using a natural language processing engine.

[0338] The analyzed information is stored in a database.

[0339] 3. Emotion recognition:

[0340] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[0341] 4. Generative AI Completion:

[0342] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[0343] 5. Document generation and output:

[0344] The server generates internal explanatory materials based on the supplemented information.

[0345] The user downloads the generated materials from the client terminal.

[0346] Prompt Sentence Examples

[0347] "The contract data has been uploaded. Please use this data to generate an internal briefing document based on the template below. The subject's emotional state is 'positive'."

[0348] Example 2: Generating multilingual materials

[0349] 1. Format Registration:

[0350] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0351] The server parses the template and stores it in a format management database.

[0352] 2. Initial data entry:

[0353] The user uploads customer proposal materials written in Japanese from the client terminal.

[0354] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0355] The analyzed information is stored in a database.

[0356] 3. Emotion recognition:

[0357] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[0358] 4. Multilingual Translation:

[0359] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[0360] 5. Document generation and output:

[0361] The server generates an English version of the customer proposal document based on the supplemented information.

[0362] The user downloads the generated English version of the material from the client terminal.

[0363] Prompt Sentence Examples

[0364] "I have uploaded a Japanese customer proposal document. Please generate an English version based on this. The target emotional state is 'trustworthy.'"

[0365] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[0366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0367] Program processing flow

[0368] Step 1: Register the format

[0369] Input: A user uses a client terminal to select a standard format for a business document (e.g., a template for an internal briefing document) and upload it to the server.

[0370] How it works: The user drags and drops a template file (e.g., Word or Excel format) from a specified folder.

[0371] Processing: The server receives the uploaded template and parses it for structure and sections, specifically identifying the headings and sections within the template and organizing the information.

[0372] Output: The server stores the structural information of the parsed template in a format management database.

[0373] Step 2: Upload raw data

[0374] Input: The user selects original data such as contract data and proposal materials from the client terminal and uploads them to the server.

[0375] Operation: The user selects a source data file, such as a contract, and clicks the upload button.

[0376] Processing: The server receives the raw data and prepares it for the next analysis step.

[0377] Output: The raw data is stored on the server and awaits analysis.

[0378] Step 3: Natural Language Processing Analysis

[0379] Input: Uploaded raw data.

[0380] How it works: The server calls a natural language processing engine (e.g., SpaCy, BERT) to begin analyzing the text data.

[0381] Processing: The server uses a natural language processing engine to perform detailed analysis of the raw data, including text segmentation, section identification, and keyword extraction.

[0382] Output: Important information extracted as a result of the analysis is stored in a database.

[0383] Step 4: Emotion Recognition

[0384] Input: Parsed text data and user-entered text data.

[0385] How it works: The server calls an emotion engine (e.g., IBM Watson emotion analysis API) to perform emotion analysis.

[0386] Processing: The server uses the emotion engine to parse the emotional state (e.g., joy, anger, sadness) from the user's input data and raw data.

[0387] Output: The recognized emotion information is stored in a database for further processing.

[0388] Step 5: Information supplementation by generative AI

[0389] Input: Analysis results and emotion information stored in the database.

[0390] How it works: The server calls a generative AI (e.g., GPT-4) to fill in the template with the necessary information.

[0391] Processing: The server uses generative AI to complement the information in the template with tone and style that reflects emotional information, placing important information in the right place and generating expressions that fit the context.

[0392] Output: The completed content is inserted into the template and the final document is generated.

[0393] Step 6: Document generation and output

[0394] Input: The template with the completed information.

[0395] How it works: The server processes the image and formats it, and generates a PDF or Word file.

[0396] Processing: The server generates the final business document based on the completed information and formats it.

[0397] Output: The generated document is provided to the user in a downloadable format. The user downloads the document from the client terminal.

[0398] Step 7: Multilingual support

[0399] Input: A document generation request in the user's preferred language.

[0400] Operation: The user selects the desired language from the client terminal and sends a request.

[0401] Processing: The server calls a translation API (e.g., Google Translate API) to translate the generated document into the desired language, adjusting the translation to reflect sentiment information.

[0402] Output: The translated document is generated and can be downloaded by the user from the client terminal.

[0403] (Application example 2)

[0404] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0405] Conventional work document generation systems have difficulty generating work instructions and work documents that reflect the user's emotional state and the situation on-site, making it difficult to provide efficient work instructions and maintain team morale. In particular, in factory environments, there is a demand for improving work efficiency and productivity by generating personalized work instructions that reflect the emotional state of site supervisors and workers.

[0406] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0407] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document; and means for the server to recognize emotions from the original data and data input by the user and generate a document with the tone and style adjusted based on the emotional information, thereby enabling the generation of personalized business documents and work instructions that correspond to the user's emotional state.

[0408] "User" means a person or organization that uses the system to generate business documents and work instructions.

[0409] A "standard format" is a predetermined format or style, and is a template that serves as the basis for generating business documents and work instructions.

[0410] A "server" is a computer system that stores data, analyzes data, and generates documents.

[0411] The "format management database" is a database that stores and manages uploaded standard formats.

[0412] "Raw data" refers to raw information or data that forms the basis of the business documents or work instructions that are generated.

[0413] A "natural language processing engine" is a software system for analyzing text data and extracting important information.

[0414] "Generative AI" is artificial intelligence that complements the information required for a standard format based on the results of analysis.

[0415] A "multilingual translation API" is an application programming interface that automatically translates generated documents into a desired language.

[0416] An "emotion engine" is a software system that recognizes emotions from raw data and user input data and adjusts tone and style accordingly.

[0417] A "work instruction manual" is a document that instructs site supervisors and workers on specific work content and procedures in a factory environment, etc.

[0418] "Personalized" means that the content is tailored to the emotional state and needs of each individual user.

[0419] The present invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions, and will be described in particular as being applied to the generation of work instructions in a factory environment.

[0420] Hardware and software used

[0421] This system is implemented using the following hardware and software.

[0422] Hardware

[0423] Factory robots

[0424] Factory computer systems

[0425] software

[0426] Python

[0427] spacy (natural language processing library)

[0428] TextBlob (sentiment analysis library)

[0429] googletrans (translation API)

[0430] Processing Description

[0431] Operation from the client terminal

[0432] The user first selects a standard format using a client terminal and uploads it to the server. The standard format is used as a template for work instructions. The server analyzes the uploaded standard format, understands its structure, and then saves it in the format management database.

[0433] Next, the user uploads the raw data from the client terminal to the server. This raw data can include information such as a factory's production plan and target production volume. The server receives this raw data and analyzes it using a natural language processing engine. It performs processes such as text segmentation and keyword extraction, and stores important information in a database.

[0434] Use of emotion engine

[0435] The server uses an emotion engine to recognize the user's emotion based on the analyzed raw data and the user's input data. For example, if the input text is positive, a positive emotion is recognized, otherwise a negative emotion is recognized. This emotion information is stored in a database and used for subsequent processing.

[0436] Data supplementation with generative AI

[0437] The server uses generative AI to fill in the necessary information in the standard format based on the analysis results and emotional information stored in the database. The data is then filled in with a tone and style that reflects the emotional information. For example, if the user is in a positive emotional state, the generated work instructions will have a positive tone.

[0438] Document generation and translation

[0439] The server generates the final work instructions based on the completed information. This document is formatted and presented to the user in a format that is easy for the user to view and use (e.g., PDF or Word document). Furthermore, the server can use a multilingual translation API to translate the generated work instructions into the user's desired language and present them to the user.

[0440] Examples and prompts

[0441] As a concrete example, consider the process of generating work instructions aimed at increasing the production speed of a factory line. A user inputs raw data including the production line's goals, and if the sentiment is judged to be positive, an encouraging message such as "Let's work hard to achieve our goals!" is added to the document.

[0442] Prompt Sentence Examples

[0443] Below are some example prompts for the generative AI model:

[0444] Generate a work instruction based on the user's sentiment based on the text below.

[0445] Text: The production rate of product X on your production line needs to be increased by 20%. Your current production rate is not meeting your monthly target.

[0446] Sentiment score: 0.8

[0447] Instructions:

[0448] Work instructions:

[0449] We need to increase the production rate of product X on our production line by 20%. Let's work hard to achieve our goal!

[0450] Your current production rate is not meeting your monthly goal. Let's work hard to reach it!

[0451] In this way, by using the present invention, it is possible to automatically generate personalized business documents and work instructions according to the user's emotional state, thereby improving work efficiency and productivity.

[0452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0453] Step 1:

[0454] The user selects a standard format and uploads the standard format to the server.

[0455] Input: A user-selected format file (e.g., a work instruction template file).

[0456] Processing: The server receives the uploaded template and parses its structure, specifically identifying the sections and fields of the format and storing them in a format management database.

[0457] Output: The structure of the standard format stored in the format management database.

[0458] Step 2:

[0459] The user uploads the original data to the server.

[0460] Input: User-supplied raw data files (e.g., production plan, target production volume, etc.).

[0461] Processing: The server receives the uploaded raw data and analyzes the text using a natural language processing engine, which includes text segmentation, section identification, keyword extraction, etc.

[0462] Output: The parsed information is stored in a database.

[0463] Step 3:

[0464] The server recognizes emotions using an emotion engine based on the raw data and the user's input data.

[0465] Input: Raw data text and user input data.

[0466] Processing: The server calculates the sentiment score (e.g., positive, negative) of the text using a library such as TextBlob. The sentiment information is stored in a database.

[0467] Output: Emotion information is stored in a database.

[0468] Step 4:

[0469] The server uses generative AI to complete the required information in a standard format.

[0470] Input: Analysis results and sentiment information stored in the database.

[0471] Processing: The server uses a generative AI model to complement the information with a tone and style that corresponds to the emotional information. For example, if the emotional state is positive, a positive tone of text will be generated.

[0472] Output: A document with the completed information arranged in a standard format.

[0473] Step 5:

[0474] The server generates the final work instructions based on the supplemented information and provides them to the user in a downloadable format.

[0475] Input: Completed and formatted information.

[0476] Processing: The server generates the final document based on the input information. The generated document is output as a PDF or Word document, and the server provides it to the user.

[0477] Output: The document in a format that users can download (e.g., PDF or Word document).

[0478] Step 6:

[0479] The server uses a multilingual translation API to translate the generated document into the desired language and provide it to the user.

[0480] Input: The generated document and desired language information.

[0481] Processing: The server uses a translation API such as googletrans to translate the document into the desired language. The translated document is output in an appropriate tone based on the emotional information.

[0482] Output: The document translated into the desired language.

[0483] In this way, by performing data processing and calculations based on specific input data at each step and outputting the results, it is possible to generate and provide personalized work instructions that correspond to the user's emotional state.

[0484] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0485] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0486] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0487] [Second embodiment]

[0488] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0489] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0490] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0491] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0492] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0493] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0494] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0495] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0496] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0497] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0498] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0499] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0500] The present invention is an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. An embodiment of the present invention will be described below.

[0501] First, the user selects and uploads a standard format (e.g., a contract template or a customer proposal template) using a client terminal. The server receives this format, analyzes its structure, and stores it in a format management database. At this stage, the sections and fields within the template are identified and centrally managed.

[0502] Next, the user uploads the source data (e.g., proposals or contracts from suppliers) from the client device. The server receives this source data and uses a natural language processing engine to segment the text, identify sections, extract keywords, etc. The analyzed information is then stored in a database as key points.

[0503] The server uses the generated AI to supplement the necessary information based on the stored analysis data. Specifically, the information stored in the database is properly arranged according to a pre-loaded standard format. The generated AI then modifies or adds data as needed. This supplementation process increases the accuracy of the final document.

[0504] Based on the information provided, the server generates the final document, which is then formatted and formatted according to a standard format and made available for download in an easy-to-view and easy-to-use format (e.g., PDF or Word document).

[0505] It also has a multilingual feature, allowing users to request multilingual support for documents generated from their client devices. The server receives the desired language and uses a translation API to translate each section of the document. The document is then regenerated based on the translated content, and the multilingual version is stored in the database. Users can download the multilingual version of the document from their client devices.

[0506] Specific examples

[0507] Example 1: Generating internal explanatory materials from contracts

[0508] 1. Format Registration:

[0509] Users upload templates for internal explanatory materials from their client terminals to the server.

[0510] The server parses the template and stores it in a format management database.

[0511] 2. Initial data entry:

[0512] The user uploads contract data from the supplier from the client terminal.

[0513] The server receives the contract data and analyzes it using a natural language processing engine.

[0514] The analyzed information is stored in a database.

[0515] 3. Generative AI Completion:

[0516] Based on the analyzed information, the server supplements the necessary information in the template for internal explanatory materials and places the data.

[0517] 4. Document generation and output:

[0518] The server generates internal explanatory materials based on the supplemented information.

[0519] The user downloads the generated materials from the client terminal.

[0520] Example 2: Generating multilingual materials

[0521] 1. Format Registration:

[0522] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0523] The server parses the template and stores it in a format management database.

[0524] 2. Initial data entry:

[0525] Users upload customer proposal documents written in Japanese from their client terminal.

[0526] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0527] The analyzed information is stored in a database.

[0528] 3. Multilingual Translation:

[0529] The server uses a translation API to translate Japanese information into English.

[0530] 4. Generative AI Completion:

[0531] Based on the translated information, the server complements the necessary information in the English template and places the data.

[0532] 5. Document generation and output:

[0533] The server generates an English version of the customer proposal document based on the supplemented information.

[0534] The user downloads the generated English version of the materials from the client terminal.

[0535] In this way, the present invention provides a system that allows users to easily automatically generate a variety of business documents, greatly improving business efficiency. In addition, the system has multilingual capabilities, making it flexible enough to handle international cases.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[0539] Step 2:

[0540] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[0541] Step 3:

[0542] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[0543] Step 4:

[0544] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[0545] Step 5:

[0546] The server stores the analysis results, and the analyzed information is organized and stored as important points in a database.

[0547] Step 6:

[0548] The server uses a generation AI to complete the information. Based on the analysis results stored in the database and pre-registered standard formats, the server uses a generation AI to complete the necessary information. The generation AI places information that fits into each section of the format and modifies or adds data as necessary.

[0549] Step 7:

[0550] The server generates the document. Based on the information provided, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[0551] Step 8:

[0552] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[0553] Step 9:

[0554] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[0555] Step 10:

[0556] The server translates the document. The server uses a translation API to translate the document into the specified language. The content of each section is automatically translated and the document is regenerated based on the translated content.

[0557] Step 11:

[0558] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[0559] Through the above steps, this system can automatically generate business documents efficiently and quickly, and also supports multiple languages.

[0560] Example 1

[0561] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0562] Conventionally, creating business documents requires a great deal of effort and time, so there is a demand for a system that supports efficient document creation. Furthermore, when multilingual support is required, individual translations are required, which requires additional effort and time. Therefore, the challenge is to provide a system that can efficiently automatically generate business documents and support multiple languages.

[0563] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0564] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in the database; means for the server to supplement information necessary for the standard format with a generative AI model based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a translation API and provide the translated document. This enables efficient creation of business documents and multilingual support.

[0565] "User" means a person or organization that generates and manages documents using the business document automatic generation system.

[0566] A "standard format" is a pre-set, fixed format or template such as a contract, proposal, or meeting document.

[0567] A "server" is a computer system that works in conjunction with client terminals via a network and provides core functions such as data processing, database management, and document generation.

[0568] The "format management database" is a database for storing and managing uploaded standard formats and related structural information.

[0569] "Original data" refers to unprocessed data before it is generated based on a standard format, such as a contract or proposal from a supplier.

[0570] A "natural language processing engine" is software or algorithms that analyze text data and perform segmentation, section identification, keyword extraction, etc.

[0571] A "database" is a system for centrally storing and managing data such as analyzed information, generated documents, and translation results.

[0572] A "generative AI model" is an artificial intelligence algorithm that generates and complements necessary information based on stored analysis data to create the final document.

[0573] "Translation API" means an application programming interface for automatically translating text written in one language into another language.

[0574] "Documents" are official documents such as contracts, proposals, and meeting materials generated by the server, and are provided in PDF or Word document format.

[0575] "Downloadable format" means a file format (e.g., PDF, Word) that can be easily acquired and viewed by a user using a client terminal.

[0576] "Translated Document" means a document that has been translated and reproduced into a desired language using the Translation API.

[0577] "External Plug-ins" are external software components used in conjunction with the Server to add charts and graphs or provide contractual advice.

[0578] The present invention relates to an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. Specific embodiments for carrying out the present invention will be described below.

[0579] User-generated format uploads

[0580] Users select standard formats such as contracts and proposals from their client devices and upload them to the server. The server receives the format and analyzes its structure using a natural language processing engine (e.g., SpaCy, NLTK). The analyzed information is stored in a format management database. At this stage, each section and field within the template is identified and centrally managed.

[0581] Initial data upload and analysis

[0582] The user then uploads the source data (e.g., a contract from a supplier) from the client device to the server. The server receives this data and uses a natural language processing engine to segment the text, identify sections, and extract keywords. The analyzed information is then stored in a database.

[0583] Data Complementation with Generative AI

[0584] The server uses generative AI (e.g., OpenAI GPT) to fill in the necessary information based on the analysis data stored in the database. Specifically, it arranges the information stored in the database appropriately according to a standard format, and the generative AI generates new information to fill in any missing parts.

[0585] Document generation and output

[0586] The server generates the final document based on the input information. This is done using a template engine (e.g., Jinja2) or a document generation library (e.g., ReportLab for PDF, python-docx for Word) to format the document. The generated document is provided in PDF or Word document format, and can be easily downloaded by the user from their client device.

[0587] Multilingual translation support

[0588] This system also has a multilingual translation function, allowing users to request that generated documents be translated into multiple languages. The server receives the desired language and translates the document using a translation API (e.g., Google Translate API). The translated document is regenerated and saved in the database again. Users can download the multilingual version of the document from their client device.

[0589] Specific examples

[0590] Example 1: Generating internal explanatory materials from contracts

[0591] 1. Format Registration:

[0592] Users upload templates for internal explanatory materials from their client terminals to the server.

[0593] The server parses this template and stores it in a format management database.

[0594] 2. Initial data entry:

[0595] The user uploads the contract data from the supplier to the server from the client terminal.

[0596] The server receives the contract data, analyzes it using a natural language processing engine, and stores it in a database.

[0597] 3. Generative AI Completion:

[0598] Based on the analyzed information, the server complements the necessary information in the template for internal explanatory materials and places the data.

[0599] 4. Document generation and output:

[0600] The server generates internal explanatory materials based on the supplemented information.

[0601] The user downloads the generated materials from the client terminal.

[0602] Example 2: Generating multilingual materials

[0603] 1. Format Registration:

[0604] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0605] The server parses this template and stores it in a format management database.

[0606] 2. Initial data entry:

[0607] Users upload customer proposal documents written in Japanese to the server from their client terminals.

[0608] The server receives the proposal materials, analyzes them using a natural language processing engine, and stores them in a database.

[0609] 3. Multilingual Translation:

[0610] The server uses a translation API to translate Japanese information into English.

[0611] 4. Generative AI Completion:

[0612] Based on the translated information, the server complements the necessary information in the English template and places the data.

[0613] 5. Document generation and output:

[0614] The server generates an English version of the customer proposal document based on the supplemented information.

[0615] The user downloads the generated English version of the materials from the client terminal.

[0616] Prompt Sentence Examples

[0617] Follow the generated template to complete the information translated from Japanese to English and generate the final customer proposal. The uploaded Japanese documents are stored in the database. Please follow the format of the template you use and arrange the information appropriately.

[0618] In this way, the present invention dramatically improves the efficiency of users' work and greatly reduces the burden of document preparation and multilingual support.

[0619] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0620] Step 1: Upload a template

[0621] Input: The user uses a client terminal to select a standard format and upload it to the server.

[0622] Specific operation: The user uploads a contract or proposal template from the client terminal. The server receives this template and performs structural analysis.

[0623] Data processing: The server uses a natural language processing engine (e.g. SpaCy) to parse the template text and identify sections and fields.

[0624] Output: The parsed format information is saved in the format management database.

[0625] Step 2: Upload raw data

[0626] Input: The user uploads raw data from the client terminal to the server.

[0627] Specific operation: The user uploads raw data (original data) such as contracts and proposals from the client terminal. The server receives this data and begins analyzing it.

[0628] Data processing: The server uses a natural language processing engine to segment the text, identify sections, and extract keywords.

[0629] Output: The parsed information is stored in a database.

[0630] Step 3: Data enrichment with generative AI

[0631] Input: The server obtains the information that needs to be completed based on the analysis results stored in the database.

[0632] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT) to complete the information required for the standard format based on the stored analysis data.

[0633] Data processing: The server properly places the information retrieved from the database into the template, and the generating AI generates any missing parts.

[0634] Output: The completed information is temporarily saved and used to generate the final document.

[0635] Step 4: Document generation

[0636] Input: The server receives instructions to generate the final document based on the completed information.

[0637] Specific operation: The server generates documents using a template engine (e.g., Jinja2) and a document generation library (e.g., ReportLab for PDF, python-docx for Word).

[0638] Data processing: Based on the supplemented information, the data is formatted according to a standard format and the final document is created.

[0639] Output: The final generated document is saved in PDF or Word format and can be downloaded by the user.

[0640] Step 5: Multilingual Translation (Optional)

[0641] Input: A user requests multilingual support, and the server complies.

[0642] Specific operation: The user requests multilingual support for the generated document from the client device. The server receives the desired language and translates it using a translation API (e.g., Google Translate API).

[0643] Data processing: The server translates each section of the document into the desired language and recreates the document in the new language.

[0644] Output: The translated documents are stored in a database and are available for users to download.

[0645] (Application example 1)

[0646] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0647] Improving the efficiency of business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) at logistics centers is a major challenge. Manual document creation is time-consuming and can lead to accuracy issues and human error. Furthermore, multilingual support is essential for international operations, which also involves tedious work. Against this backdrop, there is a growing need for a system that can quickly and accurately generate report documents based on standard formats and that can also support multiple languages.

[0648] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0649] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and save it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and save it in a database; means for the server to supplement information necessary for the standard format using a generation artificial intelligence based on the analysis results saved in the database; means for the server to generate documents based on the supplemented information and provide the documents in a format that the user can download; means for the server to translate the generated documents into a desired language using a multilingual translation API and provide the translated documents; and means for generating reports, inventory reports, and delivery plan reports for logistics business processes. This enables report documents to be generated quickly and accurately at logistics centers, and makes it easy to support multiple languages.

[0650] A "standard format" is a standard document template created based on a predetermined structure or format.

[0651] A "server" is a computer system that processes and provides data in response to requests from client terminals on a network.

[0652] A "natural language processing engine" is software that contains a set of algorithms and models that allow computers to understand, analyze, and generate human language.

[0653] The "format management database" is a database system that systematically stores and manages standard formats and analyzed data.

[0654] "Raw data" refers to raw data or information generated at the work site.

[0655] "Generative AI" is an AI that has the ability to generate and complement new information based on input data.

[0656] A "multilingual translation API" is a program interface for performing automatic translation between different languages.

[0657] A "logistics business process" is a series of business procedures at a logistics center, such as managing incoming and outgoing goods, inventory management, and delivery planning.

[0658] A "report" is a document that organizes and describes detailed information about each process in logistics operations.

[0659] An "inventory report" is a document used to report the quantity and status of products and materials currently held at a logistics center.

[0660] A "delivery plan report" is a document that describes plans, schedules, delivery procedures, etc. for product delivery.

[0661] This invention is a system that automatically generates documents for business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) in a logistics center. This system includes components such as a server, client terminals (e.g., smartphones, head-mounted displays), and a database.

[0662] System configuration

[0663] 1. Client Terminal

[0664] A device that allows a user to select a standard format and upload it to a server. Examples of such devices include smartphones and head-mounted displays.

[0665] 2. Server

[0666] The server analyzes the uploaded standard format and stores it in a format management database. It also analyzes the raw data uploaded by users using a natural language processing engine (e.g., SpaCy, NLTK), extracts important information, and stores it in the database.

[0667] The server uses a generation AI (e.g., GPT-3) to fill in the information required for a standard format based on the stored analysis results and generate the final document. This generated document is provided to the user in PDF or Word document format.

[0668] The server uses a multilingual translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language and provide the translated document to the user.

[0669] 3. Database

[0670] The two main roles are played by the format management database and the analysis database: the former is used for storing the standard formats, and the latter is used to store the raw analyzed data.

[0671] Workflow

[0672] 1. Format registration

[0673] Users upload templates for inventory reports and stock reports from their client terminals to the server, which analyzes them and stores them in a format management database.

[0674] 2. Entering initial data

[0675] Users upload raw data (e.g., product inventory lists) generated at the logistics center from their client terminals. The server analyzes the data using a natural language processing engine and stores important information in an analysis database.

[0676] 3. Complementation by generative AI

[0677] Based on the analyzed information, the server complements the information required for the standard format and arranges the data appropriately.

[0678] 4. Document generation and output

[0679] The server generates reports, inventory reports, etc. based on the supplemented information. Users can download the generated reports in PDF or Word format from their client terminals.

[0680] 5. Multilingual support

[0681] The server uses a translation API to translate the generated document into the desired language and provides the translated document to the user.

[0682] Examples and prompts

[0683] Example: Generating inventory reports at a distribution center

[0684] The user uploads a standard format inventory report template to the server, and sends the latest inventory list to the server as raw data. The server analyzes this using natural language processing, extracts the necessary information, and then uses generative AI to complete the report and generate the final document.

[0685] Example prompt sentence:

[0686] Input: warehouse_data.csv

[0687] Output: Generate a detailed stock report based on the given data.

[0688] As described above, the present invention significantly improves the operational efficiency of a logistics center and realizes the accurate and rapid generation of reports.

[0689] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0690] Step 1:

[0691] The user uses a client terminal to select a standard format for a stock entry / exit report or inventory report and upload it to the server. A format file (e.g., Excel or Word) is used as input. The server analyzes the received format file, identifies its structure and fields, and saves them in a format management database. This standardizes the format, making subsequent data processing easier.

[0692] Step 2:

[0693] The user uploads raw data (e.g., product inventory lists and shipping instructions) generated at the logistics center from a client terminal. CSV files, Excel files, etc. are used as input. The server receives this raw data and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). Text segmentation, section identification, keyword extraction, etc. are performed, and important information is stored in an analysis database. This organizes the necessary data and puts it in an easily usable format.

[0694] Step 3:

[0695] The server uses a generative AI (e.g., GPT-3) based on the analysis data to fill in the information required for the standard format. The information stored in the analysis database is used as input. Based on this data, the generative AI automatically fills in any missing parts and places the appropriate data in the standard format. This process brings the report closer to completion.

[0696] Step 4:

[0697] The server generates the final document based on the supplemented information. The output is in a format that the user can select, such as PDF or Word document. The server generates this document and provides it in a format that the user can download from their client device. This allows users to quickly obtain high-quality reports.

[0698] Step 5:

[0699] To support multiple languages, the server uses a translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language. The input requires the text content of the generated document and the desired translation language. Using the translation API, accurate translation is performed for each required section, and the translated document is saved on the server. Finally, the multilingual version of the document is made available for download from the client device.

[0700] Step 6:

[0701] For the final supplemented information and generated documents, if required by the user, the server can provide visual analysis information using third-party plug-ins (e.g., Microsoft Graph) that add charts and graphs. The supplemented information and underlying data are used as input, allowing the user to obtain additional information that is useful for gaining a deeper understanding of their business.

[0702] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0703] The present invention combines an emotion engine that recognizes user emotions in an automatic business document generation system. This system efficiently generates business documents and provides output that responds to the user's emotions, providing a more personalized experience.

[0704] First, the user selects a template using a client terminal and uploads it to the server. The server analyzes the uploaded template, understands its structure, and stores it in the format management database. This allows the system to manage the sections and fields within the template.

[0705] Next, the user uploads the source data (e.g., a contract or proposal) from the client terminal. The server analyzes this source data using a natural language processing engine. It performs text segmentation, section identification, keyword extraction, etc., and stores the analyzed information in a database. Up to this point, the process is the same as in conventional technology.

[0706] As a feature of the present invention, the server further employs an emotion engine. The emotion engine recognizes the user's emotion based on the raw data and input data from the user. For example, it analyzes the user's emotional state (e.g., joy, anger, sadness) from the tone and style of the text entered by the user. The recognized emotion is stored in a database and used for subsequent processing.

[0707] The generation AI uses this emotional information to complement the information needed in the standard format. Specifically, it complements the information with a tone and writing style that matches the user's emotions. For example, if the user indicates a "positive" tone, the generated document will also be adjusted to be written in a positive tone.

[0708] The server generates the final document based on the input information, formatting it, and presents it to the user in a format that is easy to view and use (e.g., PDF or Word document).

[0709] It also has multilingual support, allowing users to request documents in their preferred language from their client device. The server uses a translation API to translate the document into the desired language. The translation content is also adjusted based on the user's emotional information.

[0710] Specific examples

[0711] Example 1: Generating internal explanatory materials from contracts

[0712] 1. Format Registration:

[0713] Users upload templates for internal explanatory materials from their client terminals to the server.

[0714] The server parses the template and stores it in a format management database.

[0715] 2. Initial data entry:

[0716] The user uploads contract data from the supplier from the client terminal.

[0717] The server receives the contract data and analyzes it using a natural language processing engine.

[0718] The analyzed information is stored in a database.

[0719] 3. Emotion recognition:

[0720] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[0721] 4. Generative AI Completion:

[0722] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[0723] 5. Document generation and output:

[0724] The server generates internal explanatory materials based on the supplemented information.

[0725] The user downloads the generated materials from the client terminal.

[0726] Example 2: Generating multilingual materials

[0727] 1. Format Registration:

[0728] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0729] The server parses the template and stores it in a format management database.

[0730] 2. Initial data entry:

[0731] Users upload customer proposal documents written in Japanese from their client terminal.

[0732] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0733] The analyzed information is stored in a database.

[0734] 3. Emotion recognition:

[0735] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[0736] 4. Multilingual Translation:

[0737] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[0738] 5. Document generation and output:

[0739] The server generates an English version of the customer proposal document based on the supplemented information.

[0740] The user downloads the generated English version of the materials from the client terminal.

[0741] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[0742] The processing flow will be explained below.

[0743] Step 1:

[0744] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[0745] Step 2:

[0746] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[0747] Step 3:

[0748] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[0749] Step 4:

[0750] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[0751] Step 5:

[0752] The server uses an emotion engine to recognize emotions. The server analyzes the user's emotions using the emotion engine based on the raw data and the user's input text. The analysis results are assigned as emotion tags such as "joy," "anger," and "sadness."

[0753] Step 6:

[0754] The server stores the analysis results, and the analyzed information and emotion tags are organized and stored as important points in a database.

[0755] Step 7:

[0756] The server uses a generation AI to complete the information. The server completes the information required for the standard format based on the analysis results and emotion tags stored in the database. The generation AI places data that reflects the emotion information in each section of the format.

[0757] Step 8:

[0758] The server generates the document. Based on the input information and sentiment tags, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[0759] Step 9:

[0760] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[0761] Step 10:

[0762] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[0763] Step 11:

[0764] The server translates the document. The server uses a translation API to translate the document into the specified language. It automatically translates the content of each section and adjusts the translation to reflect the recognized sentiment information.

[0765] Step 12:

[0766] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[0767] Example 2

[0768] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0769] Conventional business document generation systems can automatically generate documents based on standard formats, but lack the functionality to generate personalized documents based on the user's emotions, limiting the user experience. Furthermore, when it comes to multilingual support, it is difficult to translate documents that reflect emotional nuances, which ultimately hinders effective communication.

[0770] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0771] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to analyze an emotional state using an emotion engine based on the original data and data input from the user and store the emotional information in the database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results and emotional information stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document. This enables the generation of personalized documents according to the user's emotions and multilingual translation that reflects emotional nuances.

[0772] "User" refers to a user who uses this system to generate business documents.

[0773] A "standard format" is a standardized format or template for business documents.

[0774] A "server" is a computer system that manages the entire system and analyzes, stores, and generates data.

[0775] A "format management database" is a database for storing and managing standard formats and template structures.

[0776] "Original data" refers to unanalyzed data that users initially upload to the server, such as contracts and customer proposal documents.

[0777] A "natural language processing engine" is software that analyzes text data and understands the structure and meaning of sentences.

[0778] An "emotion engine" is software for analyzing emotional states from text data or user input.

[0779] "Emotional information" refers to data that expresses a user's emotional state (e.g., joy, anger, sadness).

[0780] "Generative AI" refers to an artificial intelligence model that generates text based on specified conditions.

[0781] A "multilingual translation API" is an application programming interface that provides the functionality to translate text written in one language into another language.

[0782] "Downloadable format" means a file format in which the generated document can be easily obtained by the user (e.g., PDF, Word).

[0783] "Documents" refers to all business documents generated through this system.

[0784] This invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions. This system efficiently generates business documents and provides output that responds to the user's emotions, thereby realizing a more personalized experience.

[0785] First, a user uses a client terminal to upload a standard format, such as an internal brief or a customer proposal document, to the server. The server receives the uploaded template, analyzes its structure and sections, and stores the information in a format management database. Examples of software used include natural language processing engines such as SpaCy or BERT, and an emotion engine such as IBM Watson's sentiment analysis API.

[0786] Next, the user uploads the source data (e.g., a contract or proposal document) from the client device to the server. The server then analyzes the source data using a natural language processing engine, segmenting the text, identifying sections, extracting keywords, etc. The results of this analysis are stored in a database.

[0787] Furthermore, the server uses an emotion engine to recognize emotions from the raw data and text input by the user. The emotion information is stored in a database and used in subsequent processing. For example, if a "positive" emotion is recognized from the text input by the user, this information will be useful in the next process. In this case, the server uses IBM Watson's emotion analysis API as its emotion engine.

[0788] The server then uses generative AI (e.g., GPT-4) to fill in the necessary information within a standard format based on the analyzed information and emotional information. In this process, emotional information is reflected in the tone and style of the text, and the generated document is adjusted to match the user's emotional state.

[0789] Finally, the server generates the final business document based on the supplemented information, formats it, and provides it to the user in a format that is easy to view and use (e.g., PDF or Word document).The user can then download these generated documents from their client device.

[0790] The system also supports multiple languages, allowing users to send requests to generate documents in their preferred language from their client device. The server uses a translation API (e.g., Google Translate API) to provide the translated documents in the desired language. The system also reflects the user's emotional information and translates in an appropriate tone and style.

[0791] Specific examples

[0792] Example 1: Generating internal explanatory materials from contracts

[0793] 1. Format Registration:

[0794] The user uploads a template for an internal company briefing document from a client terminal to the server.

[0795] The server parses the template and stores it in a format management database.

[0796] 2. Initial data entry:

[0797] The user uploads contract data from the supplier from the client terminal.

[0798] The server receives the contract data and analyzes it using a natural language processing engine.

[0799] The analyzed information is stored in a database.

[0800] 3. Emotion recognition:

[0801] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[0802] 4. Generative AI Completion:

[0803] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[0804] 5. Document generation and output:

[0805] The server generates internal explanatory materials based on the supplemented information.

[0806] The user downloads the generated materials from the client terminal.

[0807] Prompt Sentence Examples

[0808] "The contract data has been uploaded. Please use this data to generate an internal briefing document based on the template below. The subject's emotional state is 'positive'."

[0809] Example 2: Generating multilingual materials

[0810] 1. Format Registration:

[0811] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0812] The server parses the template and stores it in a format management database.

[0813] 2. Initial data entry:

[0814] The user uploads customer proposal materials written in Japanese from the client terminal.

[0815] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0816] The analyzed information is stored in a database.

[0817] 3. Emotion recognition:

[0818] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[0819] 4. Multilingual Translation:

[0820] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[0821] 5. Document generation and output:

[0822] The server generates an English version of the customer proposal document based on the supplemented information.

[0823] The user downloads the generated English version of the material from the client terminal.

[0824] Prompt Sentence Examples

[0825] "I have uploaded a Japanese customer proposal document. Please generate an English version based on this. The target emotional state is 'trustworthy.'"

[0826] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[0827] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0828] Program processing flow

[0829] Step 1: Register the format

[0830] Input: A user uses a client terminal to select a standard format for a business document (e.g., a template for an internal briefing document) and upload it to the server.

[0831] How it works: The user drags and drops a template file (e.g., Word or Excel format) from a specified folder.

[0832] Processing: The server receives the uploaded template and parses it for structure and sections, specifically identifying the headings and sections within the template and organizing the information.

[0833] Output: The server stores the structural information of the parsed template in a format management database.

[0834] Step 2: Upload raw data

[0835] Input: The user selects original data such as contract data and proposal materials from the client terminal and uploads them to the server.

[0836] Operation: The user selects a source data file, such as a contract, and clicks the upload button.

[0837] Processing: The server receives the raw data and prepares it for the next analysis step.

[0838] Output: The raw data is stored on the server and awaits analysis.

[0839] Step 3: Natural Language Processing Analysis

[0840] Input: Uploaded raw data.

[0841] How it works: The server calls a natural language processing engine (e.g., SpaCy, BERT) to begin analyzing the text data.

[0842] Processing: The server uses a natural language processing engine to perform detailed analysis of the raw data, including text segmentation, section identification, and keyword extraction.

[0843] Output: Important information extracted as a result of the analysis is stored in a database.

[0844] Step 4: Emotion Recognition

[0845] Input: Parsed text data and user-entered text data.

[0846] How it works: The server calls an emotion engine (e.g., IBM Watson emotion analysis API) to perform emotion analysis.

[0847] Processing: The server uses the emotion engine to parse the emotional state (e.g., joy, anger, sadness) from the user's input data and raw data.

[0848] Output: The recognized emotion information is stored in a database for further processing.

[0849] Step 5: Information supplementation by generative AI

[0850] Input: Analysis results and emotion information stored in the database.

[0851] How it works: The server calls a generative AI (e.g., GPT-4) to fill in the template with the necessary information.

[0852] Processing: The server uses generative AI to complement the information in the template with tone and style that reflects emotional information, placing important information in the right place and generating expressions that fit the context.

[0853] Output: The completed content is inserted into the template and the final document is generated.

[0854] Step 6: Document generation and output

[0855] Input: The template with the completed information.

[0856] How it works: The server processes the image and formats it, and generates a PDF or Word file.

[0857] Processing: The server generates the final business document based on the completed information and formats it.

[0858] Output: The generated document is provided to the user in a downloadable format. The user downloads the document from the client terminal.

[0859] Step 7: Multilingual support

[0860] Input: A document generation request in the user's preferred language.

[0861] Operation: The user selects the desired language from the client terminal and sends a request.

[0862] Processing: The server calls a translation API (e.g., Google Translate API) to translate the generated document into the desired language, adjusting the translation to reflect sentiment information.

[0863] Output: The translated document is generated and can be downloaded by the user from the client terminal.

[0864] (Application example 2)

[0865] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0866] Conventional work document generation systems have difficulty generating work instructions and work documents that reflect the user's emotional state and the situation on-site, making it difficult to provide efficient work instructions and maintain team morale. In particular, in factory environments, there is a demand for improving work efficiency and productivity by generating personalized work instructions that reflect the emotional state of site supervisors and workers.

[0867] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0868] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document; and means for the server to recognize emotions from the original data and data input by the user and generate a document with the tone and style adjusted based on the emotional information, thereby enabling the generation of personalized business documents and work instructions that correspond to the user's emotional state.

[0869] "User" means a person or organization that uses the system to generate business documents and work instructions.

[0870] A "standard format" is a predetermined format or style, and is a template that serves as the basis for generating business documents and work instructions.

[0871] A "server" is a computer system that stores data, analyzes data, and generates documents.

[0872] The "format management database" is a database that stores and manages uploaded standard formats.

[0873] "Raw data" refers to raw information or data that forms the basis of the business documents or work instructions that are generated.

[0874] A "natural language processing engine" is a software system for analyzing text data and extracting important information.

[0875] "Generative AI" is artificial intelligence that complements the information required for a standard format based on the results of analysis.

[0876] A "multilingual translation API" is an application programming interface that automatically translates generated documents into a desired language.

[0877] An "emotion engine" is a software system that recognizes emotions from raw data and user input data and adjusts tone and style accordingly.

[0878] A "work instruction manual" is a document that instructs site supervisors and workers on specific work content and procedures in a factory environment, etc.

[0879] "Personalized" means that the content is tailored to the emotional state and needs of each individual user.

[0880] The present invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions, and will be described in particular as being applied to the generation of work instructions in a factory environment.

[0881] Hardware and software used

[0882] This system is implemented using the following hardware and software.

[0883] Hardware

[0884] Factory robots

[0885] Factory computer systems

[0886] software

[0887] Python

[0888] spacy (natural language processing library)

[0889] TextBlob (sentiment analysis library)

[0890] googletrans (translation API)

[0891] Processing Description

[0892] Operation from the client terminal

[0893] The user first selects a standard format using a client terminal and uploads it to the server. The standard format is used as a template for work instructions. The server analyzes the uploaded standard format, understands its structure, and then saves it in the format management database.

[0894] Next, the user uploads the raw data from the client terminal to the server. This raw data can include information such as a factory's production plan and target production volume. The server receives this raw data and analyzes it using a natural language processing engine. It performs processes such as text segmentation and keyword extraction, and stores important information in a database.

[0895] Use of emotion engine

[0896] The server uses an emotion engine to recognize the user's emotion based on the analyzed raw data and the user's input data. For example, if the input text is positive, a positive emotion is recognized, otherwise a negative emotion is recognized. This emotion information is stored in a database and used for subsequent processing.

[0897] Data supplementation with generative AI

[0898] The server uses generative AI to fill in the necessary information in the standard format based on the analysis results and emotional information stored in the database. The data is then filled in with a tone and style that reflects the emotional information. For example, if the user is in a positive emotional state, the generated work instructions will have a positive tone.

[0899] Document generation and translation

[0900] The server generates the final work instructions based on the completed information. This document is formatted and presented to the user in a format that is easy for the user to view and use (e.g., PDF or Word document). Furthermore, the server can use a multilingual translation API to translate the generated work instructions into the user's desired language and present them to the user.

[0901] Examples and prompts

[0902] As a concrete example, consider the process of generating work instructions aimed at increasing the production speed of a factory line. A user inputs raw data including the production line's goals, and if the sentiment is judged to be positive, an encouraging message such as "Let's work hard to achieve our goals!" is added to the document.

[0903] Prompt Sentence Examples

[0904] Below are some example prompts for the generative AI model:

[0905] Generate a work instruction based on the user's sentiment based on the text below.

[0906] Text: The production rate of product X on your production line needs to be increased by 20%. Your current production rate is not meeting your monthly target.

[0907] Sentiment score: 0.8

[0908] Instructions:

[0909] Work instructions:

[0910] We need to increase the production rate of product X on our production line by 20%. Let's work hard to achieve our goal!

[0911] Your current production rate is not meeting your monthly goal. Let's work hard to reach it!

[0912] In this way, by using the present invention, it is possible to automatically generate personalized business documents and work instructions according to the user's emotional state, thereby improving work efficiency and productivity.

[0913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0914] Step 1:

[0915] The user selects a standard format and uploads the standard format to the server.

[0916] Input: A user-selected format file (e.g., a work instruction template file).

[0917] Processing: The server receives the uploaded template and parses its structure, specifically identifying the sections and fields of the format and storing them in a format management database.

[0918] Output: The structure of the standard format stored in the format management database.

[0919] Step 2:

[0920] The user uploads the original data to the server.

[0921] Input: User-supplied raw data files (e.g., production plan, target production volume, etc.).

[0922] Processing: The server receives the uploaded raw data and analyzes the text using a natural language processing engine, which includes text segmentation, section identification, keyword extraction, etc.

[0923] Output: The parsed information is stored in a database.

[0924] Step 3:

[0925] The server recognizes emotions using an emotion engine based on the raw data and the user's input data.

[0926] Input: Raw data text and user input data.

[0927] Processing: The server calculates the sentiment score (e.g., positive, negative) of the text using a library such as TextBlob. The sentiment information is stored in a database.

[0928] Output: Emotion information is stored in a database.

[0929] Step 4:

[0930] The server uses generative AI to complete the required information in a standard format.

[0931] Input: Analysis results and sentiment information stored in the database.

[0932] Processing: The server uses a generative AI model to complement the information with a tone and style that corresponds to the emotional information. For example, if the emotional state is positive, a positive tone of text will be generated.

[0933] Output: A document with the completed information arranged in a standard format.

[0934] Step 5:

[0935] The server generates the final work instructions based on the supplemented information and provides them to the user in a downloadable format.

[0936] Input: Completed and formatted information.

[0937] Processing: The server generates the final document based on the input information. The generated document is output as a PDF or Word document, and the server provides it to the user.

[0938] Output: The document in a format that users can download (e.g., PDF or Word document).

[0939] Step 6:

[0940] The server uses a multilingual translation API to translate the generated document into the desired language and provide it to the user.

[0941] Input: The generated document and desired language information.

[0942] Processing: The server uses a translation API such as googletrans to translate the document into the desired language. The translated document is output in an appropriate tone based on the emotional information.

[0943] Output: The document translated into the desired language.

[0944] In this way, by performing data processing and calculations based on specific input data at each step and outputting the results, it is possible to generate and provide personalized work instructions that correspond to the user's emotional state.

[0945] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0946] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0947] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0948] [Third embodiment]

[0949] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0950] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0951] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0952] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0953] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0954] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0955] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0956] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0957] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0958] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0959] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0960] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0961] The present invention is an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. An embodiment of the present invention will be described below.

[0962] First, the user selects and uploads a standard format (e.g., a contract template or a customer proposal template) using a client terminal. The server receives this format, analyzes its structure, and stores it in a format management database. At this stage, the sections and fields within the template are identified and centrally managed.

[0963] Next, the user uploads the source data (e.g., proposals or contracts from suppliers) from the client device. The server receives this source data and uses a natural language processing engine to segment the text, identify sections, extract keywords, etc. The analyzed information is then stored in a database as key points.

[0964] The server uses the generated AI to supplement the necessary information based on the stored analysis data. Specifically, the information stored in the database is properly arranged according to a pre-loaded standard format. The generated AI then modifies or adds data as needed. This supplementation process increases the accuracy of the final document.

[0965] Based on the information provided, the server generates the final document, which is then formatted and formatted according to a standard format and made available for download in an easy-to-view and easy-to-use format (e.g., PDF or Word document).

[0966] It also has a multilingual feature, allowing users to request multilingual support for documents generated from their client devices. The server receives the desired language and uses a translation API to translate each section of the document. The document is then regenerated based on the translated content, and the multilingual version is stored in the database. Users can download the multilingual version of the document from their client devices.

[0967] Specific examples

[0968] Example 1: Generating internal explanatory materials from contracts

[0969] 1. Format Registration:

[0970] Users upload templates for internal explanatory materials from their client terminals to the server.

[0971] The server parses the template and stores it in a format management database.

[0972] 2. Initial data entry:

[0973] The user uploads contract data from the supplier from the client terminal.

[0974] The server receives the contract data and analyzes it using a natural language processing engine.

[0975] The analyzed information is stored in a database.

[0976] 3. Generative AI Completion:

[0977] Based on the analyzed information, the server supplements the necessary information in the template for internal explanatory materials and places the data.

[0978] 4. Document generation and output:

[0979] The server generates internal explanatory materials based on the supplemented information.

[0980] The user downloads the generated materials from the client terminal.

[0981] Example 2: Generating multilingual materials

[0982] 1. Format Registration:

[0983] The user uploads the English version of the customer proposal template from the client terminal to the server.

[0984] The server parses the template and stores it in a format management database.

[0985] 2. Initial data entry:

[0986] Users upload customer proposal documents written in Japanese from their client terminal.

[0987] The server receives the proposal materials and analyzes them using a natural language processing engine.

[0988] The analyzed information is stored in a database.

[0989] 3. Multilingual Translation:

[0990] The server uses a translation API to translate Japanese information into English.

[0991] 4. Generative AI Completion:

[0992] Based on the translated information, the server complements the necessary information in the English template and places the data.

[0993] 5. Document generation and output:

[0994] The server generates an English version of the customer proposal document based on the supplemented information.

[0995] The user downloads the generated English version of the materials from the client terminal.

[0996] In this way, the present invention provides a system that allows users to easily automatically generate a variety of business documents, greatly improving business efficiency. In addition, the system has multilingual capabilities, making it flexible enough to handle international cases.

[0997] The processing flow will be explained below.

[0998] Step 1:

[0999] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[1000] Step 2:

[1001] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[1002] Step 3:

[1003] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[1004] Step 4:

[1005] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[1006] Step 5:

[1007] The server stores the analysis results, and the analyzed information is organized and stored as important points in a database.

[1008] Step 6:

[1009] The server uses a generation AI to complete the information. Based on the analysis results stored in the database and pre-registered standard formats, the server uses a generation AI to complete the necessary information. The generation AI places information that fits into each section of the format and modifies or adds data as necessary.

[1010] Step 7:

[1011] The server generates the document. Based on the information provided, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[1012] Step 8:

[1013] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[1014] Step 9:

[1015] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[1016] Step 10:

[1017] The server translates the document. The server uses a translation API to translate the document into the specified language. The content of each section is automatically translated and the document is regenerated based on the translated content.

[1018] Step 11:

[1019] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[1020] Through the above steps, this system can automatically generate business documents efficiently and quickly, and also supports multiple languages.

[1021] Example 1

[1022] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1023] Conventionally, creating business documents requires a great deal of effort and time, so there is a demand for a system that supports efficient document creation. Furthermore, when multilingual support is required, individual translations are required, which requires additional effort and time. Therefore, the challenge is to provide a system that can efficiently automatically generate business documents and support multiple languages.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1025] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in the database; means for the server to supplement information necessary for the standard format with a generative AI model based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a translation API and provide the translated document. This enables efficient creation of business documents and multilingual support.

[1026] "User" means a person or organization that generates and manages documents using the business document automatic generation system.

[1027] A "standard format" is a pre-set, fixed format or template such as a contract, proposal, or meeting document.

[1028] A "server" is a computer system that works in conjunction with client terminals via a network and provides core functions such as data processing, database management, and document generation.

[1029] The "format management database" is a database for storing and managing uploaded standard formats and related structural information.

[1030] "Original data" refers to unprocessed data before it is generated based on a standard format, such as a contract or proposal from a supplier.

[1031] A "natural language processing engine" is software or algorithms that analyze text data and perform segmentation, section identification, keyword extraction, etc.

[1032] A "database" is a system for centrally storing and managing data such as analyzed information, generated documents, and translation results.

[1033] A "generative AI model" is an artificial intelligence algorithm that generates and complements necessary information based on stored analysis data to create the final document.

[1034] "Translation API" means an application programming interface for automatically translating text written in one language into another language.

[1035] "Documents" are official documents such as contracts, proposals, and meeting materials generated by the server, and are provided in PDF or Word document format.

[1036] "Downloadable format" means a file format (e.g., PDF, Word) that can be easily acquired and viewed by a user using a client terminal.

[1037] "Translated Document" means a document that has been translated and reproduced into a desired language using the Translation API.

[1038] "External Plug-ins" are external software components used in conjunction with the Server to add charts and graphs or provide contractual advice.

[1039] The present invention relates to an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. Specific embodiments for carrying out the present invention will be described below.

[1040] User-generated format uploads

[1041] Users select standard formats such as contracts and proposals from their client devices and upload them to the server. The server receives the format and analyzes its structure using a natural language processing engine (e.g., SpaCy, NLTK). The analyzed information is stored in a format management database. At this stage, each section and field within the template is identified and centrally managed.

[1042] Initial data upload and analysis

[1043] The user then uploads the source data (e.g., a contract from a supplier) from the client device to the server. The server receives this data and uses a natural language processing engine to segment the text, identify sections, and extract keywords. The analyzed information is then stored in a database.

[1044] Data Complementation with Generative AI

[1045] The server uses generative AI (e.g., OpenAI GPT) to fill in the necessary information based on the analysis data stored in the database. Specifically, it arranges the information stored in the database appropriately according to a standard format, and the generative AI generates new information to fill in any missing parts.

[1046] Document generation and output

[1047] The server generates the final document based on the input information. This is done using a template engine (e.g., Jinja2) or a document generation library (e.g., ReportLab for PDF, python-docx for Word) to format the document. The generated document is provided in PDF or Word document format, and can be easily downloaded by the user from their client device.

[1048] Multilingual translation support

[1049] This system also has a multilingual translation function, allowing users to request that generated documents be translated into multiple languages. The server receives the desired language and translates the document using a translation API (e.g., Google Translate API). The translated document is regenerated and saved in the database again. Users can download the multilingual version of the document from their client device.

[1050] Specific examples

[1051] Example 1: Generating internal explanatory materials from contracts

[1052] 1. Format Registration:

[1053] Users upload templates for internal explanatory materials from their client terminals to the server.

[1054] The server parses this template and stores it in a format management database.

[1055] 2. Initial data entry:

[1056] The user uploads the contract data from the supplier to the server from the client terminal.

[1057] The server receives the contract data, analyzes it using a natural language processing engine, and stores it in a database.

[1058] 3. Generative AI Completion:

[1059] Based on the analyzed information, the server complements the necessary information in the template for internal explanatory materials and places the data.

[1060] 4. Document generation and output:

[1061] The server generates internal explanatory materials based on the supplemented information.

[1062] The user downloads the generated materials from the client terminal.

[1063] Example 2: Generating multilingual materials

[1064] 1. Format Registration:

[1065] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1066] The server parses this template and stores it in a format management database.

[1067] 2. Initial data entry:

[1068] Users upload customer proposal documents written in Japanese to the server from their client terminals.

[1069] The server receives the proposal materials, analyzes them using a natural language processing engine, and stores them in a database.

[1070] 3. Multilingual Translation:

[1071] The server uses a translation API to translate Japanese information into English.

[1072] 4. Generative AI Completion:

[1073] Based on the translated information, the server complements the necessary information in the English template and places the data.

[1074] 5. Document generation and output:

[1075] The server generates an English version of the customer proposal document based on the supplemented information.

[1076] The user downloads the generated English version of the materials from the client terminal.

[1077] Prompt Sentence Examples

[1078] Follow the generated template to complete the information translated from Japanese to English and generate the final customer proposal. The uploaded Japanese documents are stored in the database. Please follow the format of the template you use and arrange the information appropriately.

[1079] In this way, the present invention dramatically improves the efficiency of users' work and greatly reduces the burden of document preparation and multilingual support.

[1080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1081] Step 1: Upload a template

[1082] Input: The user uses a client terminal to select a standard format and upload it to the server.

[1083] Specific operation: The user uploads a contract or proposal template from the client terminal. The server receives this template and performs structural analysis.

[1084] Data processing: The server uses a natural language processing engine (e.g. SpaCy) to parse the template text and identify sections and fields.

[1085] Output: The parsed format information is saved in the format management database.

[1086] Step 2: Upload raw data

[1087] Input: The user uploads raw data from the client terminal to the server.

[1088] Specific operation: The user uploads raw data (original data) such as contracts and proposals from the client terminal. The server receives this data and begins analyzing it.

[1089] Data processing: The server uses a natural language processing engine to segment the text, identify sections, and extract keywords.

[1090] Output: The parsed information is stored in a database.

[1091] Step 3: Data enrichment with generative AI

[1092] Input: The server obtains the information that needs to be completed based on the analysis results stored in the database.

[1093] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT) to complete the information required for the standard format based on the stored analysis data.

[1094] Data processing: The server properly places the information retrieved from the database into the template, and the generating AI generates any missing parts.

[1095] Output: The completed information is temporarily saved and used to generate the final document.

[1096] Step 4: Document generation

[1097] Input: The server receives instructions to generate the final document based on the completed information.

[1098] Specific operation: The server generates documents using a template engine (e.g., Jinja2) and a document generation library (e.g., ReportLab for PDF, python-docx for Word).

[1099] Data processing: Based on the supplemented information, the data is formatted according to a standard format and the final document is created.

[1100] Output: The final generated document is saved in PDF or Word format and can be downloaded by the user.

[1101] Step 5: Multilingual Translation (Optional)

[1102] Input: A user requests multilingual support, and the server complies.

[1103] Specific operation: The user requests multilingual support for the generated document from the client device. The server receives the desired language and translates it using a translation API (e.g., Google Translate API).

[1104] Data processing: The server translates each section of the document into the desired language and recreates the document in the new language.

[1105] Output: The translated documents are stored in a database and are available for users to download.

[1106] (Application example 1)

[1107] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1108] Improving the efficiency of business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) at logistics centers is a major challenge. Manual document creation is time-consuming and can lead to accuracy issues and human error. Furthermore, multilingual support is essential for international operations, which also involves tedious work. Against this backdrop, there is a growing need for a system that can quickly and accurately generate report documents based on standard formats and that can also support multiple languages.

[1109] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1110] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and save it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and save it in a database; means for the server to supplement information necessary for the standard format using a generation artificial intelligence based on the analysis results saved in the database; means for the server to generate documents based on the supplemented information and provide the documents in a format that the user can download; means for the server to translate the generated documents into a desired language using a multilingual translation API and provide the translated documents; and means for generating reports, inventory reports, and delivery plan reports for logistics business processes. This enables report documents to be generated quickly and accurately at logistics centers, and makes it easy to support multiple languages.

[1111] A "standard format" is a standard document template created based on a predetermined structure or format.

[1112] A "server" is a computer system that processes and provides data in response to requests from client terminals on a network.

[1113] A "natural language processing engine" is software that contains a set of algorithms and models that allow computers to understand, analyze, and generate human language.

[1114] The "format management database" is a database system that systematically stores and manages standard formats and analyzed data.

[1115] "Raw data" refers to raw data or information generated at the work site.

[1116] "Generative AI" is an AI that has the ability to generate and complement new information based on input data.

[1117] A "multilingual translation API" is a program interface for performing automatic translation between different languages.

[1118] A "logistics business process" is a series of business procedures at a logistics center, such as managing incoming and outgoing goods, inventory management, and delivery planning.

[1119] A "report" is a document that organizes and describes detailed information about each process in logistics operations.

[1120] An "inventory report" is a document used to report the quantity and status of products and materials currently held at a logistics center.

[1121] A "delivery plan report" is a document that describes plans, schedules, delivery procedures, etc. for product delivery.

[1122] This invention is a system that automatically generates documents for business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) in a logistics center. This system includes components such as a server, client terminals (e.g., smartphones, head-mounted displays), and a database.

[1123] System configuration

[1124] 1. Client Terminal

[1125] A device that allows a user to select a standard format and upload it to a server. Examples of such devices include smartphones and head-mounted displays.

[1126] 2. Server

[1127] The server analyzes the uploaded standard format and stores it in a format management database. It also analyzes the raw data uploaded by users using a natural language processing engine (e.g., SpaCy, NLTK), extracts important information, and stores it in the database.

[1128] The server uses a generation AI (e.g., GPT-3) to fill in the information required for a standard format based on the stored analysis results and generate the final document. This generated document is provided to the user in PDF or Word document format.

[1129] The server uses a multilingual translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language and provide the translated document to the user.

[1130] 3. Database

[1131] The two main roles are played by the format management database and the analysis database: the former is used for storing the standard formats, and the latter is used to store the raw analyzed data.

[1132] Workflow

[1133] 1. Format registration

[1134] Users upload templates for inventory reports and stock reports from their client terminals to the server, which analyzes them and stores them in a format management database.

[1135] 2. Entering initial data

[1136] Users upload raw data (e.g., product inventory lists) generated at the logistics center from their client terminals. The server analyzes the data using a natural language processing engine and stores important information in an analysis database.

[1137] 3. Complementation by generative AI

[1138] Based on the analyzed information, the server complements the information required for the standard format and arranges the data appropriately.

[1139] 4. Document generation and output

[1140] The server generates reports, inventory reports, etc. based on the supplemented information. Users can download the generated reports in PDF or Word format from their client terminals.

[1141] 5. Multilingual support

[1142] The server uses a translation API to translate the generated document into the desired language and provides the translated document to the user.

[1143] Examples and prompts

[1144] Example: Generating inventory reports at a distribution center

[1145] The user uploads a standard format inventory report template to the server, and sends the latest inventory list to the server as raw data. The server analyzes this using natural language processing, extracts the necessary information, and then uses generative AI to complete the report and generate the final document.

[1146] Example prompt sentence:

[1147] Input: warehouse_data.csv

[1148] Output: Generate a detailed stock report based on the given data.

[1149] As described above, the present invention significantly improves the operational efficiency of a logistics center and realizes the accurate and rapid generation of reports.

[1150] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1151] Step 1:

[1152] The user uses a client terminal to select a standard format for a stock entry / exit report or inventory report and upload it to the server. A format file (e.g., Excel or Word) is used as input. The server analyzes the received format file, identifies its structure and fields, and saves them in a format management database. This standardizes the format, making subsequent data processing easier.

[1153] Step 2:

[1154] The user uploads raw data (e.g., product inventory lists and shipping instructions) generated at the logistics center from a client terminal. CSV files, Excel files, etc. are used as input. The server receives this raw data and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). Text segmentation, section identification, keyword extraction, etc. are performed, and important information is stored in an analysis database. This organizes the necessary data and puts it in an easily usable format.

[1155] Step 3:

[1156] The server uses a generative AI (e.g., GPT-3) based on the analysis data to fill in the information required for the standard format. The information stored in the analysis database is used as input. Based on this data, the generative AI automatically fills in any missing parts and places the appropriate data in the standard format. This process brings the report closer to completion.

[1157] Step 4:

[1158] The server generates the final document based on the supplemented information. The output is in a format that the user can select, such as PDF or Word document. The server generates this document and provides it in a format that the user can download from their client device. This allows users to quickly obtain high-quality reports.

[1159] Step 5:

[1160] To support multiple languages, the server uses a translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language. The input requires the text content of the generated document and the desired translation language. Using the translation API, accurate translation is performed for each required section, and the translated document is saved on the server. Finally, the multilingual version of the document is made available for download from the client device.

[1161] Step 6:

[1162] For the final supplemented information and generated documents, if required by the user, the server can provide visual analysis information using third-party plug-ins (e.g., Microsoft Graph) that add charts and graphs. The supplemented information and underlying data are used as input, allowing the user to obtain additional information that is useful for gaining a deeper understanding of their business.

[1163] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1164] The present invention combines an emotion engine that recognizes user emotions in an automatic business document generation system. This system efficiently generates business documents and provides output that responds to the user's emotions, providing a more personalized experience.

[1165] First, the user selects a template using a client terminal and uploads it to the server. The server analyzes the uploaded template, understands its structure, and stores it in the format management database. This allows the system to manage the sections and fields within the template.

[1166] Next, the user uploads the source data (e.g., a contract or proposal) from the client terminal. The server analyzes this source data using a natural language processing engine. It performs text segmentation, section identification, keyword extraction, etc., and stores the analyzed information in a database. Up to this point, the process is the same as in conventional technology.

[1167] As a feature of the present invention, the server further employs an emotion engine. The emotion engine recognizes the user's emotion based on the raw data and input data from the user. For example, it analyzes the user's emotional state (e.g., joy, anger, sadness) from the tone and style of the text entered by the user. The recognized emotion is stored in a database and used for subsequent processing.

[1168] The generation AI uses this emotional information to complement the information needed in the standard format. Specifically, it complements the information with a tone and writing style that matches the user's emotions. For example, if the user indicates a "positive" tone, the generated document will also be adjusted to be written in a positive tone.

[1169] The server generates the final document based on the input information, formatting it, and presents it to the user in a format that is easy to view and use (e.g., PDF or Word document).

[1170] It also has multilingual support, allowing users to request documents in their preferred language from their client device. The server uses a translation API to translate the document into the desired language. The translation content is also adjusted based on the user's emotional information.

[1171] Specific examples

[1172] Example 1: Generating internal explanatory materials from contracts

[1173] 1. Format Registration:

[1174] Users upload templates for internal explanatory materials from their client terminals to the server.

[1175] The server parses the template and stores it in a format management database.

[1176] 2. Initial data entry:

[1177] The user uploads contract data from the supplier from the client terminal.

[1178] The server receives the contract data and analyzes it using a natural language processing engine.

[1179] The analyzed information is stored in a database.

[1180] 3. Emotion recognition:

[1181] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[1182] 4. Generative AI Completion:

[1183] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[1184] 5. Document generation and output:

[1185] The server generates internal explanatory materials based on the supplemented information.

[1186] The user downloads the generated materials from the client terminal.

[1187] Example 2: Generating multilingual materials

[1188] 1. Format Registration:

[1189] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1190] The server parses the template and stores it in a format management database.

[1191] 2. Initial data entry:

[1192] Users upload customer proposal documents written in Japanese from their client terminal.

[1193] The server receives the proposal materials and analyzes them using a natural language processing engine.

[1194] The analyzed information is stored in a database.

[1195] 3. Emotion recognition:

[1196] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[1197] 4. Multilingual Translation:

[1198] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[1199] 5. Document generation and output:

[1200] The server generates an English version of the customer proposal document based on the supplemented information.

[1201] The user downloads the generated English version of the materials from the client terminal.

[1202] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[1206] Step 2:

[1207] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[1208] Step 3:

[1209] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[1210] Step 4:

[1211] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[1212] Step 5:

[1213] The server uses an emotion engine to recognize emotions. The server analyzes the user's emotions using the emotion engine based on the raw data and the user's input text. The analysis results are assigned as emotion tags such as "joy," "anger," and "sadness."

[1214] Step 6:

[1215] The server stores the analysis results, and the analyzed information and emotion tags are organized and stored as important points in a database.

[1216] Step 7:

[1217] The server uses a generation AI to complete the information. The server completes the information required for the standard format based on the analysis results and emotion tags stored in the database. The generation AI places data that reflects the emotion information in each section of the format.

[1218] Step 8:

[1219] The server generates the document. Based on the input information and sentiment tags, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[1220] Step 9:

[1221] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[1222] Step 10:

[1223] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[1224] Step 11:

[1225] The server translates the document. The server uses a translation API to translate the document into the specified language. It automatically translates the content of each section and adjusts the translation to reflect the recognized sentiment information.

[1226] Step 12:

[1227] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[1228] Example 2

[1229] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1230] Conventional business document generation systems can automatically generate documents based on standard formats, but lack the functionality to generate personalized documents based on the user's emotions, limiting the user experience. Furthermore, when it comes to multilingual support, it is difficult to translate documents that reflect emotional nuances, which ultimately hinders effective communication.

[1231] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1232] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to analyze an emotional state using an emotion engine based on the original data and data input from the user and store the emotional information in the database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results and emotional information stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document. This enables the generation of personalized documents according to the user's emotions and multilingual translation that reflects emotional nuances.

[1233] "User" refers to a user who uses this system to generate business documents.

[1234] A "standard format" is a standardized format or template for business documents.

[1235] A "server" is a computer system that manages the entire system and analyzes, stores, and generates data.

[1236] A "format management database" is a database for storing and managing standard formats and template structures.

[1237] "Original data" refers to unanalyzed data that users initially upload to the server, such as contracts and customer proposal documents.

[1238] A "natural language processing engine" is software that analyzes text data and understands the structure and meaning of sentences.

[1239] An "emotion engine" is software for analyzing emotional states from text data or user input.

[1240] "Emotional information" refers to data that expresses a user's emotional state (e.g., joy, anger, sadness).

[1241] "Generative AI" refers to an artificial intelligence model that generates text based on specified conditions.

[1242] A "multilingual translation API" is an application programming interface that provides the functionality to translate text written in one language into another language.

[1243] "Downloadable format" means a file format in which the generated document can be easily obtained by the user (e.g., PDF, Word).

[1244] "Documents" refers to all business documents generated through this system.

[1245] This invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions. This system efficiently generates business documents and provides output that responds to the user's emotions, thereby realizing a more personalized experience.

[1246] First, a user uses a client terminal to upload a standard format, such as an internal brief or a customer proposal document, to the server. The server receives the uploaded template, analyzes its structure and sections, and stores the information in a format management database. Examples of software used include natural language processing engines such as SpaCy or BERT, and an emotion engine such as IBM Watson's sentiment analysis API.

[1247] Next, the user uploads the source data (e.g., a contract or proposal document) from the client device to the server. The server then analyzes the source data using a natural language processing engine, segmenting the text, identifying sections, extracting keywords, etc. The results of this analysis are stored in a database.

[1248] Furthermore, the server uses an emotion engine to recognize emotions from the raw data and text input by the user. The emotion information is stored in a database and used in subsequent processing. For example, if a "positive" emotion is recognized from the text input by the user, this information will be useful in the next process. In this case, the server uses IBM Watson's emotion analysis API as its emotion engine.

[1249] The server then uses generative AI (e.g., GPT-4) to fill in the necessary information within a standard format based on the analyzed information and emotional information. In this process, emotional information is reflected in the tone and style of the text, and the generated document is adjusted to match the user's emotional state.

[1250] Finally, the server generates the final business document based on the supplemented information, formats it, and provides it to the user in a format that is easy to view and use (e.g., PDF or Word document).The user can then download these generated documents from their client device.

[1251] The system also supports multiple languages, allowing users to send requests to generate documents in their preferred language from their client device. The server uses a translation API (e.g., Google Translate API) to provide the translated documents in the desired language. The system also reflects the user's emotional information and translates in an appropriate tone and style.

[1252] Specific examples

[1253] Example 1: Generating internal explanatory materials from contracts

[1254] 1. Format Registration:

[1255] The user uploads a template for an internal company briefing document from a client terminal to the server.

[1256] The server parses the template and stores it in a format management database.

[1257] 2. Initial data entry:

[1258] The user uploads contract data from the supplier from the client terminal.

[1259] The server receives the contract data and analyzes it using a natural language processing engine.

[1260] The analyzed information is stored in a database.

[1261] 3. Emotion recognition:

[1262] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[1263] 4. Generative AI Completion:

[1264] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[1265] 5. Document generation and output:

[1266] The server generates internal explanatory materials based on the supplemented information.

[1267] The user downloads the generated materials from the client terminal.

[1268] Prompt Sentence Examples

[1269] "The contract data has been uploaded. Please use this data to generate an internal briefing document based on the template below. The subject's emotional state is 'positive'."

[1270] Example 2: Generating multilingual materials

[1271] 1. Format Registration:

[1272] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1273] The server parses the template and stores it in a format management database.

[1274] 2. Initial data entry:

[1275] The user uploads customer proposal materials written in Japanese from the client terminal.

[1276] The server receives the proposal materials and analyzes them using a natural language processing engine.

[1277] The analyzed information is stored in a database.

[1278] 3. Emotion recognition:

[1279] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[1280] 4. Multilingual Translation:

[1281] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[1282] 5. Document generation and output:

[1283] The server generates an English version of the customer proposal document based on the supplemented information.

[1284] The user downloads the generated English version of the material from the client terminal.

[1285] Prompt Sentence Examples

[1286] "I have uploaded a Japanese customer proposal document. Please generate an English version based on this. The target emotional state is 'trustworthy.'"

[1287] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[1288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1289] Program processing flow

[1290] Step 1: Register the format

[1291] Input: A user uses a client terminal to select a standard format for a business document (e.g., a template for an internal briefing document) and upload it to the server.

[1292] How it works: The user drags and drops a template file (e.g., Word or Excel format) from a specified folder.

[1293] Processing: The server receives the uploaded template and parses it for structure and sections, specifically identifying the headings and sections within the template and organizing the information.

[1294] Output: The server stores the structural information of the parsed template in a format management database.

[1295] Step 2: Upload raw data

[1296] Input: The user selects original data such as contract data and proposal materials from the client terminal and uploads them to the server.

[1297] Operation: The user selects a source data file, such as a contract, and clicks the upload button.

[1298] Processing: The server receives the raw data and prepares it for the next analysis step.

[1299] Output: The raw data is stored on the server and awaits analysis.

[1300] Step 3: Natural Language Processing Analysis

[1301] Input: Uploaded raw data.

[1302] How it works: The server calls a natural language processing engine (e.g., SpaCy, BERT) to begin analyzing the text data.

[1303] Processing: The server uses a natural language processing engine to perform detailed analysis of the raw data, including text segmentation, section identification, and keyword extraction.

[1304] Output: Important information extracted as a result of the analysis is stored in a database.

[1305] Step 4: Emotion Recognition

[1306] Input: Parsed text data and user-entered text data.

[1307] How it works: The server calls an emotion engine (e.g., IBM Watson emotion analysis API) to perform emotion analysis.

[1308] Processing: The server uses the emotion engine to parse the emotional state (e.g., joy, anger, sadness) from the user's input data and raw data.

[1309] Output: The recognized emotion information is stored in a database for further processing.

[1310] Step 5: Information supplementation by generative AI

[1311] Input: Analysis results and emotion information stored in the database.

[1312] How it works: The server calls a generative AI (e.g., GPT-4) to fill in the template with the necessary information.

[1313] Processing: The server uses generative AI to complement the information in the template with tone and style that reflects emotional information, placing important information in the right place and generating expressions that fit the context.

[1314] Output: The completed content is inserted into the template and the final document is generated.

[1315] Step 6: Document generation and output

[1316] Input: The template with the completed information.

[1317] How it works: The server processes the image and formats it, and generates a PDF or Word file.

[1318] Processing: The server generates the final business document based on the completed information and formats it.

[1319] Output: The generated document is provided to the user in a downloadable format. The user downloads the document from the client terminal.

[1320] Step 7: Multilingual support

[1321] Input: A document generation request in the user's preferred language.

[1322] Operation: The user selects the desired language from the client terminal and sends a request.

[1323] Processing: The server calls a translation API (e.g., Google Translate API) to translate the generated document into the desired language, adjusting the translation to reflect sentiment information.

[1324] Output: The translated document is generated and can be downloaded by the user from the client terminal.

[1325] (Application example 2)

[1326] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1327] Conventional work document generation systems have difficulty generating work instructions and work documents that reflect the user's emotional state and the situation on-site, making it difficult to provide efficient work instructions and maintain team morale. In particular, in factory environments, there is a demand for improving work efficiency and productivity by generating personalized work instructions that reflect the emotional state of site supervisors and workers.

[1328] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1329] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document; and means for the server to recognize emotions from the original data and data input by the user and generate a document with the tone and style adjusted based on the emotional information, thereby enabling the generation of personalized business documents and work instructions that correspond to the user's emotional state.

[1330] "User" means a person or organization that uses the system to generate business documents and work instructions.

[1331] A "standard format" is a predetermined format or style, and is a template that serves as the basis for generating business documents and work instructions.

[1332] A "server" is a computer system that stores data, analyzes data, and generates documents.

[1333] The "format management database" is a database that stores and manages uploaded standard formats.

[1334] "Raw data" refers to raw information or data that forms the basis of the business documents or work instructions that are generated.

[1335] A "natural language processing engine" is a software system for analyzing text data and extracting important information.

[1336] "Generative AI" is artificial intelligence that complements the information required for a standard format based on the results of analysis.

[1337] A "multilingual translation API" is an application programming interface that automatically translates generated documents into a desired language.

[1338] An "emotion engine" is a software system that recognizes emotions from raw data and user input data and adjusts tone and style accordingly.

[1339] A "work instruction manual" is a document that instructs site supervisors and workers on specific work content and procedures in a factory environment, etc.

[1340] "Personalized" means that the content is tailored to the emotional state and needs of each individual user.

[1341] The present invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions, and will be described in particular as being applied to the generation of work instructions in a factory environment.

[1342] Hardware and software used

[1343] This system is implemented using the following hardware and software.

[1344] Hardware

[1345] Factory robots

[1346] Factory computer systems

[1347] software

[1348] Python

[1349] spacy (natural language processing library)

[1350] TextBlob (sentiment analysis library)

[1351] googletrans (translation API)

[1352] Processing Description

[1353] Operation from the client terminal

[1354] The user first selects a standard format using a client terminal and uploads it to the server. The standard format is used as a template for work instructions. The server analyzes the uploaded standard format, understands its structure, and then saves it in the format management database.

[1355] Next, the user uploads the raw data from the client terminal to the server. This raw data can include information such as a factory's production plan and target production volume. The server receives this raw data and analyzes it using a natural language processing engine. It performs processes such as text segmentation and keyword extraction, and stores important information in a database.

[1356] Use of emotion engine

[1357] The server uses an emotion engine to recognize the user's emotion based on the analyzed raw data and the user's input data. For example, if the input text is positive, a positive emotion is recognized, otherwise a negative emotion is recognized. This emotion information is stored in a database and used for subsequent processing.

[1358] Data supplementation with generative AI

[1359] The server uses generative AI to fill in the necessary information in the standard format based on the analysis results and emotional information stored in the database. The data is then filled in with a tone and style that reflects the emotional information. For example, if the user is in a positive emotional state, the generated work instructions will have a positive tone.

[1360] Document generation and translation

[1361] The server generates the final work instructions based on the completed information. This document is formatted and presented to the user in a format that is easy for the user to view and use (e.g., PDF or Word document). Furthermore, the server can use a multilingual translation API to translate the generated work instructions into the user's desired language and present them to the user.

[1362] Examples and prompts

[1363] As a concrete example, consider the process of generating work instructions aimed at increasing the production speed of a factory line. A user inputs raw data including the production line's goals, and if the sentiment is judged to be positive, an encouraging message such as "Let's work hard to achieve our goals!" is added to the document.

[1364] Prompt Sentence Examples

[1365] Below are some example prompts for the generative AI model:

[1366] Generate a work instruction based on the user's sentiment based on the text below.

[1367] Text: The production rate of product X on your production line needs to be increased by 20%. Your current production rate is not meeting your monthly target.

[1368] Sentiment score: 0.8

[1369] Instructions:

[1370] Work instructions:

[1371] We need to increase the production rate of product X on our production line by 20%. Let's work hard to achieve our goal!

[1372] Your current production rate is not meeting your monthly goal. Let's work hard to reach it!

[1373] In this way, by using the present invention, it is possible to automatically generate personalized business documents and work instructions according to the user's emotional state, thereby improving work efficiency and productivity.

[1374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1375] Step 1:

[1376] The user selects a standard format and uploads the standard format to the server.

[1377] Input: A user-selected format file (e.g., a work instruction template file).

[1378] Processing: The server receives the uploaded template and parses its structure, specifically identifying the sections and fields of the format and storing them in a format management database.

[1379] Output: The structure of the standard format stored in the format management database.

[1380] Step 2:

[1381] The user uploads the original data to the server.

[1382] Input: User-supplied raw data files (e.g., production plan, target production volume, etc.).

[1383] Processing: The server receives the uploaded raw data and analyzes the text using a natural language processing engine, which includes text segmentation, section identification, keyword extraction, etc.

[1384] Output: The parsed information is stored in a database.

[1385] Step 3:

[1386] The server recognizes emotions using an emotion engine based on the raw data and the user's input data.

[1387] Input: Raw data text and user input data.

[1388] Processing: The server calculates the sentiment score (e.g., positive, negative) of the text using a library such as TextBlob. The sentiment information is stored in a database.

[1389] Output: Emotion information is stored in a database.

[1390] Step 4:

[1391] The server uses generative AI to complete the required information in a standard format.

[1392] Input: Analysis results and sentiment information stored in the database.

[1393] Processing: The server uses a generative AI model to complement the information with a tone and style that corresponds to the emotional information. For example, if the emotional state is positive, a positive tone of text will be generated.

[1394] Output: A document with the completed information arranged in a standard format.

[1395] Step 5:

[1396] The server generates the final work instructions based on the supplemented information and provides them to the user in a downloadable format.

[1397] Input: Completed and formatted information.

[1398] Processing: The server generates the final document based on the input information. The generated document is output as a PDF or Word document, and the server provides it to the user.

[1399] Output: The document in a format that users can download (e.g., PDF or Word document).

[1400] Step 6:

[1401] The server uses a multilingual translation API to translate the generated document into the desired language and provide it to the user.

[1402] Input: The generated document and desired language information.

[1403] Processing: The server uses a translation API such as googletrans to translate the document into the desired language. The translated document is output in an appropriate tone based on the emotional information.

[1404] Output: The document translated into the desired language.

[1405] In this way, by performing data processing and calculations based on specific input data at each step and outputting the results, it is possible to generate and provide personalized work instructions that correspond to the user's emotional state.

[1406] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1407] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1408] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1409] [Fourth embodiment]

[1410] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1411] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1412] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1413] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1414] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1416] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1417] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1418] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1419] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1421] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1422] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1423] The present invention is an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. An embodiment of the present invention will be described below.

[1424] First, the user selects and uploads a standard format (e.g., a contract template or a customer proposal template) using a client terminal. The server receives this format, analyzes its structure, and stores it in a format management database. At this stage, the sections and fields within the template are identified and centrally managed.

[1425] Next, the user uploads the source data (e.g., proposals or contracts from suppliers) from the client device. The server receives this source data and uses a natural language processing engine to segment the text, identify sections, extract keywords, etc. The analyzed information is then stored in a database as key points.

[1426] The server uses the generated AI to supplement the necessary information based on the stored analysis data. Specifically, the information stored in the database is properly arranged according to a pre-loaded standard format. The generated AI then modifies or adds data as needed. This supplementation process increases the accuracy of the final document.

[1427] Based on the information provided, the server generates the final document, which is then formatted and formatted according to a standard format and made available for download in an easy-to-view and easy-to-use format (e.g., PDF or Word document).

[1428] It also has a multilingual feature, allowing users to request multilingual support for documents generated from their client devices. The server receives the desired language and uses a translation API to translate each section of the document. The document is then regenerated based on the translated content, and the multilingual version is stored in the database. Users can download the multilingual version of the document from their client devices.

[1429] Specific examples

[1430] Example 1: Generating internal explanatory materials from contracts

[1431] 1. Format Registration:

[1432] Users upload templates for internal explanatory materials from their client terminals to the server.

[1433] The server parses the template and stores it in a format management database.

[1434] 2. Initial data entry:

[1435] The user uploads contract data from the supplier from the client terminal.

[1436] The server receives the contract data and analyzes it using a natural language processing engine.

[1437] The analyzed information is stored in a database.

[1438] 3. Generative AI Completion:

[1439] Based on the analyzed information, the server supplements the necessary information in the template for internal explanatory materials and places the data.

[1440] 4. Document generation and output:

[1441] The server generates internal explanatory materials based on the supplemented information.

[1442] The user downloads the generated materials from the client terminal.

[1443] Example 2: Generating multilingual materials

[1444] 1. Format Registration:

[1445] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1446] The server parses the template and stores it in a format management database.

[1447] 2. Initial data entry:

[1448] Users upload customer proposal documents written in Japanese from their client terminal.

[1449] The server receives the proposal materials and analyzes them using a natural language processing engine.

[1450] The analyzed information is stored in a database.

[1451] 3. Multilingual Translation:

[1452] The server uses a translation API to translate Japanese information into English.

[1453] 4. Generative AI Completion:

[1454] Based on the translated information, the server complements the necessary information in the English template and places the data.

[1455] 5. Document generation and output:

[1456] The server generates an English version of the customer proposal document based on the supplemented information.

[1457] The user downloads the generated English version of the materials from the client terminal.

[1458] In this way, the present invention provides a system that allows users to easily automatically generate a variety of business documents, greatly improving business efficiency. In addition, the system has multilingual capabilities, making it flexible enough to handle international cases.

[1459] The processing flow will be explained below.

[1460] Step 1:

[1461] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[1462] Step 2:

[1463] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[1464] Step 3:

[1465] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[1466] Step 4:

[1467] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[1468] Step 5:

[1469] The server stores the analysis results, and the analyzed information is organized and stored as important points in a database.

[1470] Step 6:

[1471] The server uses a generation AI to complete the information. Based on the analysis results stored in the database and pre-registered standard formats, the server uses a generation AI to complete the necessary information. The generation AI places information that fits into each section of the format and modifies or adds data as necessary.

[1472] Step 7:

[1473] The server generates the document. Based on the information provided, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[1474] Step 8:

[1475] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[1476] Step 9:

[1477] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[1478] Step 10:

[1479] The server translates the document. The server uses a translation API to translate the document into the specified language. The content of each section is automatically translated and the document is regenerated based on the translated content.

[1480] Step 11:

[1481] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[1482] Through the above steps, this system can automatically generate business documents efficiently and quickly, and also supports multiple languages.

[1483] Example 1

[1484] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1485] Conventionally, creating business documents requires a great deal of effort and time, so there is a demand for a system that supports efficient document creation. Furthermore, when multilingual support is required, individual translations are required, which requires additional effort and time. Therefore, the challenge is to provide a system that can efficiently automatically generate business documents and support multiple languages.

[1486] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1487] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in the database; means for the server to supplement information necessary for the standard format with a generative AI model based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a translation API and provide the translated document. This enables efficient creation of business documents and multilingual support.

[1488] "User" means a person or organization that generates and manages documents using the business document automatic generation system.

[1489] A "standard format" is a pre-set, fixed format or template such as a contract, proposal, or meeting document.

[1490] A "server" is a computer system that works in conjunction with client terminals via a network and provides core functions such as data processing, database management, and document generation.

[1491] The "format management database" is a database for storing and managing uploaded standard formats and related structural information.

[1492] "Original data" refers to unprocessed data before it is generated based on a standard format, such as a contract or proposal from a supplier.

[1493] A "natural language processing engine" is software or algorithms that analyze text data and perform segmentation, section identification, keyword extraction, etc.

[1494] A "database" is a system for centrally storing and managing data such as analyzed information, generated documents, and translation results.

[1495] A "generative AI model" is an artificial intelligence algorithm that generates and complements necessary information based on stored analysis data to create the final document.

[1496] "Translation API" means an application programming interface for automatically translating text written in one language into another language.

[1497] "Documents" are official documents such as contracts, proposals, and meeting materials generated by the server, and are provided in PDF or Word document format.

[1498] "Downloadable format" means a file format (e.g., PDF, Word) that can be easily acquired and viewed by a user using a client terminal.

[1499] "Translated Document" means a document that has been translated and reproduced into a desired language using the Translation API.

[1500] "External Plug-ins" are external software components used in conjunction with the Server to add charts and graphs or provide contractual advice.

[1501] The present invention relates to an automatic business document generation system in which a server receives a request from a user via a client terminal and automatically generates a document based on a fixed format. Specific embodiments for carrying out the present invention will be described below.

[1502] User-generated format uploads

[1503] Users select standard formats such as contracts and proposals from their client devices and upload them to the server. The server receives the format and analyzes its structure using a natural language processing engine (e.g., SpaCy, NLTK). The analyzed information is stored in a format management database. At this stage, each section and field within the template is identified and centrally managed.

[1504] Initial data upload and analysis

[1505] The user then uploads the source data (e.g., a contract from a supplier) from the client device to the server. The server receives this data and uses a natural language processing engine to segment the text, identify sections, and extract keywords. The analyzed information is then stored in a database.

[1506] Data Complementation with Generative AI

[1507] The server uses generative AI (e.g., OpenAI GPT) to fill in the necessary information based on the analysis data stored in the database. Specifically, it arranges the information stored in the database appropriately according to a standard format, and the generative AI generates new information to fill in any missing parts.

[1508] Document generation and output

[1509] The server generates the final document based on the input information. This is done using a template engine (e.g., Jinja2) or a document generation library (e.g., ReportLab for PDF, python-docx for Word) to format the document. The generated document is provided in PDF or Word document format, and can be easily downloaded by the user from their client device.

[1510] Multilingual translation support

[1511] This system also has a multilingual translation function, allowing users to request that generated documents be translated into multiple languages. The server receives the desired language and translates the document using a translation API (e.g., Google Translate API). The translated document is regenerated and saved in the database again. Users can download the multilingual version of the document from their client device.

[1512] Specific examples

[1513] Example 1: Generating internal explanatory materials from contracts

[1514] 1. Format Registration:

[1515] Users upload templates for internal explanatory materials from their client terminals to the server.

[1516] The server parses this template and stores it in a format management database.

[1517] 2. Initial data entry:

[1518] The user uploads the contract data from the supplier to the server from the client terminal.

[1519] The server receives the contract data, analyzes it using a natural language processing engine, and stores it in a database.

[1520] 3. Generative AI Completion:

[1521] Based on the analyzed information, the server complements the necessary information in the template for internal explanatory materials and places the data.

[1522] 4. Document generation and output:

[1523] The server generates internal explanatory materials based on the supplemented information.

[1524] The user downloads the generated materials from the client terminal.

[1525] Example 2: Generating multilingual materials

[1526] 1. Format Registration:

[1527] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1528] The server parses this template and stores it in a format management database.

[1529] 2. Initial data entry:

[1530] Users upload customer proposal documents written in Japanese to the server from their client terminals.

[1531] The server receives the proposal materials, analyzes them using a natural language processing engine, and stores them in a database.

[1532] 3. Multilingual Translation:

[1533] The server uses a translation API to translate Japanese information into English.

[1534] 4. Generative AI Completion:

[1535] Based on the translated information, the server complements the necessary information in the English template and places the data.

[1536] 5. Document generation and output:

[1537] The server generates an English version of the customer proposal document based on the supplemented information.

[1538] The user downloads the generated English version of the materials from the client terminal.

[1539] Prompt Sentence Examples

[1540] Follow the generated template to complete the information translated from Japanese to English and generate the final customer proposal. The uploaded Japanese documents are stored in the database. Please follow the format of the template you use and arrange the information appropriately.

[1541] In this way, the present invention dramatically improves the efficiency of users' work and greatly reduces the burden of document preparation and multilingual support.

[1542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1543] Step 1: Upload a template

[1544] Input: The user uses a client terminal to select a standard format and upload it to the server.

[1545] Specific operation: The user uploads a contract or proposal template from the client terminal. The server receives this template and performs structural analysis.

[1546] Data processing: The server uses a natural language processing engine (e.g. SpaCy) to parse the template text and identify sections and fields.

[1547] Output: The parsed format information is saved in the format management database.

[1548] Step 2: Upload raw data

[1549] Input: The user uploads raw data from the client terminal to the server.

[1550] Specific operation: The user uploads raw data (original data) such as contracts and proposals from the client terminal. The server receives this data and begins analyzing it.

[1551] Data processing: The server uses a natural language processing engine to segment the text, identify sections, and extract keywords.

[1552] Output: The parsed information is stored in a database.

[1553] Step 3: Data enrichment with generative AI

[1554] Input: The server obtains the information that needs to be completed based on the analysis results stored in the database.

[1555] Specific operation: The server uses a generative AI model (e.g., OpenAI GPT) to complete the information required for the standard format based on the stored analysis data.

[1556] Data processing: The server properly places the information retrieved from the database into the template, and the generating AI generates any missing parts.

[1557] Output: The completed information is temporarily saved and used to generate the final document.

[1558] Step 4: Document generation

[1559] Input: The server receives instructions to generate the final document based on the completed information.

[1560] Specific operation: The server generates documents using a template engine (e.g., Jinja2) and a document generation library (e.g., ReportLab for PDF, python-docx for Word).

[1561] Data processing: Based on the supplemented information, the data is formatted according to a standard format and the final document is created.

[1562] Output: The final generated document is saved in PDF or Word format and can be downloaded by the user.

[1563] Step 5: Multilingual Translation (Optional)

[1564] Input: A user requests multilingual support, and the server complies.

[1565] Specific operation: The user requests multilingual support for the generated document from the client device. The server receives the desired language and translates it using a translation API (e.g., Google Translate API).

[1566] Data processing: The server translates each section of the document into the desired language and recreates the document in the new language.

[1567] Output: The translated documents are stored in a database and are available for users to download.

[1568] (Application example 1)

[1569] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1570] Improving the efficiency of business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) at logistics centers is a major challenge. Manual document creation is time-consuming and can lead to accuracy issues and human error. Furthermore, multilingual support is essential for international operations, which also involves tedious work. Against this backdrop, there is a growing need for a system that can quickly and accurately generate report documents based on standard formats and that can also support multiple languages.

[1571] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1572] In this invention, the server includes: means for a user to select a standard format and upload the standard format to the server; means for the server to analyze the uploaded standard format and save it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and save it in a database; means for the server to supplement information necessary for the standard format using a generation artificial intelligence based on the analysis results saved in the database; means for the server to generate documents based on the supplemented information and provide the documents in a format that the user can download; means for the server to translate the generated documents into a desired language using a multilingual translation API and provide the translated documents; and means for generating reports, inventory reports, and delivery plan reports for logistics business processes. This enables report documents to be generated quickly and accurately at logistics centers, and makes it easy to support multiple languages.

[1573] A "standard format" is a standard document template created based on a predetermined structure or format.

[1574] A "server" is a computer system that processes and provides data in response to requests from client terminals on a network.

[1575] A "natural language processing engine" is software that contains a set of algorithms and models that allow computers to understand, analyze, and generate human language.

[1576] The "format management database" is a database system that systematically stores and manages standard formats and analyzed data.

[1577] "Raw data" refers to raw data or information generated at the work site.

[1578] "Generative AI" is an AI that has the ability to generate and complement new information based on input data.

[1579] A "multilingual translation API" is a program interface for performing automatic translation between different languages.

[1580] A "logistics business process" is a series of business procedures at a logistics center, such as managing incoming and outgoing goods, inventory management, and delivery planning.

[1581] A "report" is a document that organizes and describes detailed information about each process in logistics operations.

[1582] An "inventory report" is a document used to report the quantity and status of products and materials currently held at a logistics center.

[1583] A "delivery plan report" is a document that describes plans, schedules, delivery procedures, etc. for product delivery.

[1584] This invention is a system that automatically generates documents for business processes (e.g., inventory management, inventory reports, delivery plan reports, etc.) in a logistics center. This system includes components such as a server, client terminals (e.g., smartphones, head-mounted displays), and a database.

[1585] System configuration

[1586] 1. Client Terminal

[1587] A device that allows a user to select a standard format and upload it to a server. Examples of such devices include smartphones and head-mounted displays.

[1588] 2. Server

[1589] The server analyzes the uploaded standard format and stores it in a format management database. It also analyzes the raw data uploaded by users using a natural language processing engine (e.g., SpaCy, NLTK), extracts important information, and stores it in the database.

[1590] The server uses a generation AI (e.g., GPT-3) to fill in the information required for a standard format based on the stored analysis results and generate the final document. This generated document is provided to the user in PDF or Word document format.

[1591] The server uses a multilingual translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language and provide the translated document to the user.

[1592] 3. Database

[1593] The two main roles are played by the format management database and the analysis database: the former is used for storing the standard formats, and the latter is used to store the raw analyzed data.

[1594] Workflow

[1595] 1. Format registration

[1596] Users upload templates for inventory reports and stock reports from their client terminals to the server, which analyzes them and stores them in a format management database.

[1597] 2. Entering initial data

[1598] Users upload raw data (e.g., product inventory lists) generated at the logistics center from their client terminals. The server analyzes the data using a natural language processing engine and stores important information in an analysis database.

[1599] 3. Complementation by generative AI

[1600] Based on the analyzed information, the server complements the information required for the standard format and arranges the data appropriately.

[1601] 4. Document generation and output

[1602] The server generates reports, inventory reports, etc. based on the supplemented information. Users can download the generated reports in PDF or Word format from their client terminals.

[1603] 5. Multilingual support

[1604] The server uses a translation API to translate the generated document into the desired language and provides the translated document to the user.

[1605] Examples and prompts

[1606] Example: Generating inventory reports at a distribution center

[1607] The user uploads a standard format inventory report template to the server, and sends the latest inventory list to the server as raw data. The server analyzes this using natural language processing, extracts the necessary information, and then uses generative AI to complete the report and generate the final document.

[1608] Example prompt sentence:

[1609] Input: warehouse_data.csv

[1610] Output: Generate a detailed stock report based on the given data.

[1611] As described above, the present invention significantly improves the operational efficiency of a logistics center and realizes the accurate and rapid generation of reports.

[1612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1613] Step 1:

[1614] The user uses a client terminal to select a standard format for a stock entry / exit report or inventory report and upload it to the server. A format file (e.g., Excel or Word) is used as input. The server analyzes the received format file, identifies its structure and fields, and saves them in a format management database. This standardizes the format, making subsequent data processing easier.

[1615] Step 2:

[1616] The user uploads raw data (e.g., product inventory lists and shipping instructions) generated at the logistics center from a client terminal. CSV files, Excel files, etc. are used as input. The server receives this raw data and analyzes it using a natural language processing engine (e.g., SpaCy, NLTK). Text segmentation, section identification, keyword extraction, etc. are performed, and important information is stored in an analysis database. This organizes the necessary data and puts it in an easily usable format.

[1617] Step 3:

[1618] The server uses a generative AI (e.g., GPT-3) based on the analysis data to fill in the information required for the standard format. The information stored in the analysis database is used as input. Based on this data, the generative AI automatically fills in any missing parts and places the appropriate data in the standard format. This process brings the report closer to completion.

[1619] Step 4:

[1620] The server generates the final document based on the supplemented information. The output is in a format that the user can select, such as PDF or Word document. The server generates this document and provides it in a format that the user can download from their client device. This allows users to quickly obtain high-quality reports.

[1621] Step 5:

[1622] To support multiple languages, the server uses a translation API (e.g., Google Cloud Translation API) to translate the generated document into the desired language. The input requires the text content of the generated document and the desired translation language. Using the translation API, accurate translation is performed for each required section, and the translated document is saved on the server. Finally, the multilingual version of the document is made available for download from the client device.

[1623] Step 6:

[1624] For the final supplemented information and generated documents, if required by the user, the server can provide visual analysis information using third-party plug-ins (e.g., Microsoft Graph) that add charts and graphs. The supplemented information and underlying data are used as input, allowing the user to obtain additional information that is useful for gaining a deeper understanding of their business.

[1625] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1626] The present invention combines an emotion engine that recognizes user emotions in an automatic business document generation system. This system efficiently generates business documents and provides output that responds to the user's emotions, providing a more personalized experience.

[1627] First, the user selects a template using a client terminal and uploads it to the server. The server analyzes the uploaded template, understands its structure, and stores it in the format management database. This allows the system to manage the sections and fields within the template.

[1628] Next, the user uploads the source data (e.g., a contract or proposal) from the client terminal. The server analyzes this source data using a natural language processing engine. It performs text segmentation, section identification, keyword extraction, etc., and stores the analyzed information in a database. Up to this point, the process is the same as in conventional technology.

[1629] As a feature of the present invention, the server further employs an emotion engine. The emotion engine recognizes the user's emotion based on the raw data and input data from the user. For example, it analyzes the user's emotional state (e.g., joy, anger, sadness) from the tone and style of the text entered by the user. The recognized emotion is stored in a database and used for subsequent processing.

[1630] The generation AI uses this emotional information to complement the information needed in the standard format. Specifically, it complements the information with a tone and writing style that matches the user's emotions. For example, if the user indicates a "positive" tone, the generated document will also be adjusted to be written in a positive tone.

[1631] The server generates the final document based on the input information, formatting it, and presents it to the user in a format that is easy to view and use (e.g., PDF or Word document).

[1632] It also has multilingual support, allowing users to request documents in their preferred language from their client device. The server uses a translation API to translate the document into the desired language. The translation content is also adjusted based on the user's emotional information.

[1633] Specific examples

[1634] Example 1: Generating internal explanatory materials from contracts

[1635] 1. Format Registration:

[1636] Users upload templates for internal explanatory materials from their client terminals to the server.

[1637] The server parses the template and stores it in a format management database.

[1638] 2. Initial data entry:

[1639] The user uploads contract data from the supplier from the client terminal.

[1640] The server receives the contract data and analyzes it using a natural language processing engine.

[1641] The analyzed information is stored in a database.

[1642] 3. Emotion recognition:

[1643] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[1644] 4. Generative AI Completion:

[1645] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[1646] 5. Document generation and output:

[1647] The server generates internal explanatory materials based on the supplemented information.

[1648] The user downloads the generated materials from the client terminal.

[1649] Example 2: Generating multilingual materials

[1650] 1. Format Registration:

[1651] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1652] The server parses the template and stores it in a format management database.

[1653] 2. Initial data entry:

[1654] Users upload customer proposal documents written in Japanese from their client terminal.

[1655] The server receives the proposal materials and analyzes them using a natural language processing engine.

[1656] The analyzed information is stored in a database.

[1657] 3. Emotion recognition:

[1658] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[1659] 4. Multilingual Translation:

[1660] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[1661] 5. Document generation and output:

[1662] The server generates an English version of the customer proposal document based on the supplemented information.

[1663] The user downloads the generated English version of the materials from the client terminal.

[1664] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[1665] The processing flow will be explained below.

[1666] Step 1:

[1667] The user uploads a template. Using a client terminal, the user selects a pre-prepared template (e.g., a contract template or a customer proposal template) and uploads it to the server.

[1668] Step 2:

[1669] The server parses the template. The server receives the uploaded template and parses its structure. Specifically, it identifies the sections and input fields in the template and stores this information in a format management database.

[1670] Step 3:

[1671] The user uploads the original data. The user uses the client terminal to upload original data such as a contract or proposal to the server.

[1672] Step 4:

[1673] The server analyzes the raw data. The server uses a natural language processing engine to analyze the uploaded raw data, specifically segmenting the text and identifying important sections and keywords.

[1674] Step 5:

[1675] The server uses an emotion engine to recognize emotions. The server analyzes the user's emotions using the emotion engine based on the raw data and the user's input text. The analysis results are assigned as emotion tags such as "joy," "anger," and "sadness."

[1676] Step 6:

[1677] The server stores the analysis results, and the analyzed information and emotion tags are organized and stored as important points in a database.

[1678] Step 7:

[1679] The server uses a generation AI to complete the information. The server completes the information required for the standard format based on the analysis results and emotion tags stored in the database. The generation AI places data that reflects the emotion information in each section of the format.

[1680] Step 8:

[1681] The server generates the document. Based on the input information and sentiment tags, the server generates the final document according to a standard format. The document is then formatted and organized into an easy-to-read form.

[1682] Step 9:

[1683] The user downloads the document. The generated document is stored in the database, and the user can obtain the document from the client device in a downloadable format such as a PDF or Word document.

[1684] Step 10:

[1685] The user requests multilingual support. The user sends a request to the server from the client terminal to make the document multilingual. The user can specify the desired language.

[1686] Step 11:

[1687] The server translates the document. The server uses a translation API to translate the document into the specified language. It automatically translates the content of each section and adjusts the translation to reflect the recognized sentiment information.

[1688] Step 12:

[1689] The user downloads the multilingual version of the document. The translated multilingual version of the document is stored in the database and can be downloaded by the user from the client terminal.

[1690] Example 2

[1691] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1692] Conventional business document generation systems can automatically generate documents based on standard formats, but lack the functionality to generate personalized documents based on the user's emotions, limiting the user experience. Furthermore, when it comes to multilingual support, it is difficult to translate documents that reflect emotional nuances, which ultimately hinders effective communication.

[1693] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1694] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to analyze an emotional state using an emotion engine based on the original data and data input from the user and store the emotional information in the database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results and emotional information stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; and means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document. This enables the generation of personalized documents according to the user's emotions and multilingual translation that reflects emotional nuances.

[1695] "User" refers to a user who uses this system to generate business documents.

[1696] A "standard format" is a standardized format or template for business documents.

[1697] A "server" is a computer system that manages the entire system and analyzes, stores, and generates data.

[1698] A "format management database" is a database for storing and managing standard formats and template structures.

[1699] "Original data" refers to unanalyzed data that users initially upload to the server, such as contracts and customer proposal documents.

[1700] A "natural language processing engine" is software that analyzes text data and understands the structure and meaning of sentences.

[1701] An "emotion engine" is software for analyzing emotional states from text data or user input.

[1702] "Emotional information" refers to data that expresses a user's emotional state (e.g., joy, anger, sadness).

[1703] "Generative AI" refers to an artificial intelligence model that generates text based on specified conditions.

[1704] A "multilingual translation API" is an application programming interface that provides the functionality to translate text written in one language into another language.

[1705] "Downloadable format" means a file format in which the generated document can be easily obtained by the user (e.g., PDF, Word).

[1706] "Documents" refers to all business documents generated through this system.

[1707] This invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions. This system efficiently generates business documents and provides output that responds to the user's emotions, thereby realizing a more personalized experience.

[1708] First, a user uses a client terminal to upload a standard format, such as an internal brief or a customer proposal document, to the server. The server receives the uploaded template, analyzes its structure and sections, and stores the information in a format management database. Examples of software used include natural language processing engines such as SpaCy or BERT, and an emotion engine such as IBM Watson's sentiment analysis API.

[1709] Next, the user uploads the source data (e.g., a contract or proposal document) from the client device to the server. The server then analyzes the source data using a natural language processing engine, segmenting the text, identifying sections, extracting keywords, etc. The results of this analysis are stored in a database.

[1710] Furthermore, the server uses an emotion engine to recognize emotions from the raw data and text input by the user. The emotion information is stored in a database and used in subsequent processing. For example, if a "positive" emotion is recognized from the text input by the user, this information will be useful in the next process. In this case, the server uses IBM Watson's emotion analysis API as its emotion engine.

[1711] The server then uses generative AI (e.g., GPT-4) to fill in the necessary information within a standard format based on the analyzed information and emotional information. In this process, emotional information is reflected in the tone and style of the text, and the generated document is adjusted to match the user's emotional state.

[1712] Finally, the server generates the final business document based on the supplemented information, formats it, and provides it to the user in a format that is easy to view and use (e.g., PDF or Word document).The user can then download these generated documents from their client device.

[1713] The system also supports multiple languages, allowing users to send requests to generate documents in their preferred language from their client device. The server uses a translation API (e.g., Google Translate API) to provide the translated documents in the desired language. The system also reflects the user's emotional information and translates in an appropriate tone and style.

[1714] Specific examples

[1715] Example 1: Generating internal explanatory materials from contracts

[1716] 1. Format Registration:

[1717] The user uploads a template for an internal company briefing document from a client terminal to the server.

[1718] The server parses the template and stores it in a format management database.

[1719] 2. Initial data entry:

[1720] The user uploads contract data from the supplier from the client terminal.

[1721] The server receives the contract data and analyzes it using a natural language processing engine.

[1722] The analyzed information is stored in a database.

[1723] 3. Emotion recognition:

[1724] The server uses an emotion engine to recognize the user's emotion from the contract data and stores the emotion information in a database.

[1725] 4. Generative AI Completion:

[1726] Based on the analyzed information and emotional information, the server complements the necessary information in templates for internal company briefing materials and arranges the data in an appropriate tone and style.

[1727] 5. Document generation and output:

[1728] The server generates internal explanatory materials based on the supplemented information.

[1729] The user downloads the generated materials from the client terminal.

[1730] Prompt Sentence Examples

[1731] "The contract data has been uploaded. Please use this data to generate an internal briefing document based on the template below. The subject's emotional state is 'positive'."

[1732] Example 2: Generating multilingual materials

[1733] 1. Format Registration:

[1734] The user uploads the English version of the customer proposal template from the client terminal to the server.

[1735] The server parses the template and stores it in a format management database.

[1736] 2. Initial data entry:

[1737] The user uploads customer proposal materials written in Japanese from the client terminal.

[1738] The server receives the proposal materials and analyzes them using a natural language processing engine.

[1739] The analyzed information is stored in a database.

[1740] 3. Emotion recognition:

[1741] The server uses an emotion engine to recognize the user's emotion from the proposal materials and stores the emotion information in a database.

[1742] 4. Multilingual Translation:

[1743] The server uses a translation API to translate Japanese information into English, taking into account emotional information and ensuring the translation is done in an appropriate tone and style.

[1744] 5. Document generation and output:

[1745] The server generates an English version of the customer proposal document based on the supplemented information.

[1746] The user downloads the generated English version of the material from the client terminal.

[1747] Prompt Sentence Examples

[1748] "I have uploaded a Japanese customer proposal document. Please generate an English version based on this. The target emotional state is 'trustworthy.'"

[1749] In this way, by combining an emotion engine, the present invention automatically generates personalized business documents according to the user's emotions, thereby supporting more effective communication.

[1750] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1751] Program processing flow

[1752] Step 1: Register the format

[1753] Input: A user uses a client terminal to select a standard format for a business document (e.g., a template for an internal briefing document) and upload it to the server.

[1754] How it works: The user drags and drops a template file (e.g., Word or Excel format) from a specified folder.

[1755] Processing: The server receives the uploaded template and parses it for structure and sections, specifically identifying the headings and sections within the template and organizing the information.

[1756] Output: The server stores the structural information of the parsed template in a format management database.

[1757] Step 2: Upload raw data

[1758] Input: The user selects original data such as contract data and proposal materials from the client terminal and uploads them to the server.

[1759] Operation: The user selects a source data file, such as a contract, and clicks the upload button.

[1760] Processing: The server receives the raw data and prepares it for the next analysis step.

[1761] Output: The raw data is stored on the server and awaits analysis.

[1762] Step 3: Natural Language Processing Analysis

[1763] Input: Uploaded raw data.

[1764] How it works: The server calls a natural language processing engine (e.g., SpaCy, BERT) to begin analyzing the text data.

[1765] Processing: The server uses a natural language processing engine to perform detailed analysis of the raw data, including text segmentation, section identification, and keyword extraction.

[1766] Output: Important information extracted as a result of the analysis is stored in a database.

[1767] Step 4: Emotion Recognition

[1768] Input: Parsed text data and user-entered text data.

[1769] How it works: The server calls an emotion engine (e.g., IBM Watson emotion analysis API) to perform emotion analysis.

[1770] Processing: The server uses the emotion engine to parse the emotional state (e.g., joy, anger, sadness) from the user's input data and raw data.

[1771] Output: The recognized emotion information is stored in a database for further processing.

[1772] Step 5: Information supplementation by generative AI

[1773] Input: Analysis results and emotion information stored in the database.

[1774] How it works: The server calls a generative AI (e.g., GPT-4) to fill in the template with the necessary information.

[1775] Processing: The server uses generative AI to complement the information in the template with tone and style that reflects emotional information, placing important information in the right place and generating expressions that fit the context.

[1776] Output: The completed content is inserted into the template and the final document is generated.

[1777] Step 6: Document generation and output

[1778] Input: The template with the completed information.

[1779] How it works: The server processes the image and formats it, and generates a PDF or Word file.

[1780] Processing: The server generates the final business document based on the completed information and formats it.

[1781] Output: The generated document is provided to the user in a downloadable format. The user downloads the document from the client terminal.

[1782] Step 7: Multilingual support

[1783] Input: A document generation request in the user's preferred language.

[1784] Operation: The user selects the desired language from the client terminal and sends a request.

[1785] Processing: The server calls a translation API (e.g., Google Translate API) to translate the generated document into the desired language, adjusting the translation to reflect sentiment information.

[1786] Output: The translated document is generated and can be downloaded by the user from the client terminal.

[1787] (Application example 2)

[1788] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1789] Conventional work document generation systems have difficulty generating work instructions and work documents that reflect the user's emotional state and the situation on-site, making it difficult to provide efficient work instructions and maintain team morale. In particular, in factory environments, there is a demand for improving work efficiency and productivity by generating personalized work instructions that reflect the emotional state of site supervisors and workers.

[1790] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1791] In this invention, the server includes: means for a user to select a template and upload the template to the server; means for the server to analyze the uploaded template and store it in a format management database; means for a user to upload original data to the server; means for the server to analyze the original data using a natural language processing engine and extract important information and store it in a database; means for the server to supplement information necessary for the template using a generation AI based on the analysis results stored in the database; means for the server to generate a document based on the supplemented information and provide the document in a format that the user can download; means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document; and means for the server to recognize emotions from the original data and data input by the user and generate a document with the tone and style adjusted based on the emotional information, thereby enabling the generation of personalized business documents and work instructions that correspond to the user's emotional state.

[1792] "User" means a person or organization that uses the system to generate business documents and work instructions.

[1793] A "standard format" is a predetermined format or style, and is a template that serves as the basis for generating business documents and work instructions.

[1794] A "server" is a computer system that stores data, analyzes data, and generates documents.

[1795] The "format management database" is a database that stores and manages uploaded standard formats.

[1796] "Raw data" refers to raw information or data that forms the basis of the business documents or work instructions that are generated.

[1797] A "natural language processing engine" is a software system for analyzing text data and extracting important information.

[1798] "Generative AI" is artificial intelligence that complements the information required for a standard format based on the results of analysis.

[1799] A "multilingual translation API" is an application programming interface that automatically translates generated documents into a desired language.

[1800] An "emotion engine" is a software system that recognizes emotions from raw data and user input data and adjusts tone and style accordingly.

[1801] A "work instruction manual" is a document that instructs site supervisors and workers on specific work content and procedures in a factory environment, etc.

[1802] "Personalized" means that the content is tailored to the emotional state and needs of each individual user.

[1803] The present invention is an automatic business document generation system that combines an emotion engine that recognizes user emotions, and will be described in particular as being applied to the generation of work instructions in a factory environment.

[1804] Hardware and software used

[1805] This system is implemented using the following hardware and software.

[1806] Hardware

[1807] Factory robots

[1808] Factory computer systems

[1809] software

[1810] Python

[1811] spacy (natural language processing library)

[1812] TextBlob (sentiment analysis library)

[1813] googletrans (translation API)

[1814] Processing Description

[1815] Operation from the client terminal

[1816] The user first selects a standard format using a client terminal and uploads it to the server. The standard format is used as a template for work instructions. The server analyzes the uploaded standard format, understands its structure, and then saves it in the format management database.

[1817] Next, the user uploads the raw data from the client terminal to the server. This raw data can include information such as a factory's production plan and target production volume. The server receives this raw data and analyzes it using a natural language processing engine. It performs processes such as text segmentation and keyword extraction, and stores important information in a database.

[1818] Use of emotion engine

[1819] The server uses an emotion engine to recognize the user's emotion based on the analyzed raw data and the user's input data. For example, if the input text is positive, a positive emotion is recognized, otherwise a negative emotion is recognized. This emotion information is stored in a database and used for subsequent processing.

[1820] Data supplementation with generative AI

[1821] The server uses generative AI to fill in the necessary information in the standard format based on the analysis results and emotional information stored in the database. The data is then filled in with a tone and style that reflects the emotional information. For example, if the user is in a positive emotional state, the generated work instructions will have a positive tone.

[1822] Document generation and translation

[1823] The server generates the final work instructions based on the completed information. This document is formatted and presented to the user in a format that is easy for the user to view and use (e.g., PDF or Word document). Furthermore, the server can use a multilingual translation API to translate the generated work instructions into the user's desired language and present them to the user.

[1824] Examples and prompts

[1825] As a concrete example, consider the process of generating work instructions aimed at increasing the production speed of a factory line. A user inputs raw data including the production line's goals, and if the sentiment is judged to be positive, an encouraging message such as "Let's work hard to achieve our goals!" is added to the document.

[1826] Prompt Sentence Examples

[1827] Below are some example prompts for the generative AI model:

[1828] Generate a work instruction based on the user's sentiment based on the text below.

[1829] Text: The production rate of product X on your production line needs to be increased by 20%. Your current production rate is not meeting your monthly target.

[1830] Sentiment score: 0.8

[1831] Instructions:

[1832] Work instructions:

[1833] We need to increase the production rate of product X on our production line by 20%. Let's work hard to achieve our goal!

[1834] Your current production rate is not meeting your monthly goal. Let's work hard to reach it!

[1835] In this way, by using the present invention, it is possible to automatically generate personalized business documents and work instructions according to the user's emotional state, thereby improving work efficiency and productivity.

[1836] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1837] Step 1:

[1838] The user selects a standard format and uploads the standard format to the server.

[1839] Input: A user-selected format file (e.g., a work instruction template file).

[1840] Processing: The server receives the uploaded template and parses its structure, specifically identifying the sections and fields of the format and storing them in a format management database.

[1841] Output: The structure of the standard format stored in the format management database.

[1842] Step 2:

[1843] The user uploads the original data to the server.

[1844] Input: User-supplied raw data files (e.g., production plan, target production volume, etc.).

[1845] Processing: The server receives the uploaded raw data and analyzes the text using a natural language processing engine, which includes text segmentation, section identification, keyword extraction, etc.

[1846] Output: The parsed information is stored in a database.

[1847] Step 3:

[1848] The server recognizes emotions using an emotion engine based on the raw data and the user's input data.

[1849] Input: Raw data text and user input data.

[1850] Processing: The server calculates the sentiment score (e.g., positive, negative) of the text using a library such as TextBlob. The sentiment information is stored in a database.

[1851] Output: Emotion information is stored in a database.

[1852] Step 4:

[1853] The server uses generative AI to complete the required information in a standard format.

[1854] Input: Analysis results and sentiment information stored in the database.

[1855] Processing: The server uses a generative AI model to complement the information with a tone and style that corresponds to the emotional information. For example, if the emotional state is positive, a positive tone of text will be generated.

[1856] Output: A document with the completed information arranged in a standard format.

[1857] Step 5:

[1858] The server generates the final work instructions based on the supplemented information and provides them to the user in a downloadable format.

[1859] Input: Completed and formatted information.

[1860] Processing: The server generates the final document based on the input information. The generated document is output as a PDF or Word document, and the server provides it to the user.

[1861] Output: The document in a format that users can download (e.g., PDF or Word document).

[1862] Step 6:

[1863] The server uses a multilingual translation API to translate the generated document into the desired language and provide it to the user.

[1864] Input: The generated document and desired language information.

[1865] Processing: The server uses a translation API such as googletrans to translate the document into the desired language. The translated document is output in an appropriate tone based on the emotional information.

[1866] Output: The document translated into the desired language.

[1867] In this way, by performing data processing and calculations based on specific input data at each step and outputting the results, it is possible to generate and provide personalized work instructions that correspond to the user's emotional state.

[1868] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1869] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1870] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1871] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1872] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1873] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1874] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1875] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1876] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1877] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1878] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1879] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1880] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1881] 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.

[1882] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1883] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1884] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1885] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1886] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1887] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1888] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1889] The following is further disclosed regarding the above embodiment.

[1890] (Claim 1)

[1891] A means for a user to select a standard format and upload the standard format to a server;

[1892] A means for the server to analyze the uploaded standard format and store it in a format management database;

[1893] a means for users to upload raw data to a server;

[1894] The server analyzes the raw data using a natural language processing engine, extracts important information, and stores it in a database;

[1895] The server uses AI to generate data based on the analysis results stored in the database, and this is how the information required for the standard format is supplemented.

[1896] a means for the server to generate a document based on the completed information and provide the document in a downloadable format to the user;

[1897] A means for the ser...

Claims

1. A means for a user to select a standard format and upload the standard format to a server; A means for the server to analyze the uploaded standard format and store it in a format management database; a means for users to upload raw data to a server; The server analyzes the raw data using a natural language processing engine, extracts important information, and stores it in a database; The server uses AI to generate data based on the analysis results stored in the database, and this is how the information required for the standard format is supplemented. a means for the server to generate a document based on the completed information and provide the document in a downloadable format to the user; A means for the server to translate the generated document into a desired language using a multilingual translation API and provide the translated document; A system including:

2. 2. The system according to claim 1, wherein the server includes means for generating a plurality of types of documents such as contracts, customer proposal materials, and management meeting materials based on the supplemented information.

3. 2. The system of claim 1, further comprising means for utilizing third-party plug-ins to add diagrams and graphs to the generated documents and to provide advice on contractual opinions and issues.

Images