system

Abstract

We provide a system that will improve the sales capabilities of all sales representatives and enable them to quickly and efficiently create high-quality proposal materials. [Solution] The specific processing unit 290 of the data processing device 12 in the system performs the following processes: storing the format and content of previously used proposal materials in a database; training a generation AI based on the format and content of the proposal materials; receiving information entered by a user to create the proposal materials; extracting an appropriate format and content from the database based on the received information; generating new proposal materials using the generation AI based on the extracted format and content; providing the generated proposal materials to the user; allowing the user to review and edit the provided proposal materials; and finally saving the edited proposal materials in a database.

Description

[Technical Field]

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

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

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

[0004] In modern corporate sales, the quality of sales representatives' proposal materials is extremely important. However, not all sales representatives are able to consistently create high-quality proposal materials. It is particularly difficult for new or inexperienced sales representatives to achieve the same quality as high-performing sales representatives. Therefore, there is a need for a system that can raise the sales capabilities of all sales representatives and create high-quality proposal materials quickly and efficiently. [Means for solving the problem]

[0005] The present invention provides a means for storing the format and content of previously used proposal documents in a database and training a generation AI based on that information. The system receives information entered by a user to create a proposal document and extracts the appropriate format and content from the database based on that information. The system uses the generation AI to generate a new proposal document based on the extracted format and content, and provides the generated proposal document to the user. The user can review and edit the provided proposal document, and the final edited results are saved in the database. This enables all sales representatives to create high-quality proposal documents on par with those of high-performing salespeople, improving work efficiency and sales capabilities.

[0006] A "database" is a repository of information that structures and stores the format and content of previously used proposal materials, allowing information to be searched and extracted as needed.

[0007] "Generative AI" is an artificial intelligence model that generates new proposals based on trained data.

[0008] A "user" is a sales representative who uses the system to create proposal materials.

[0009] A "proposal document" is a document that includes product information and proposal content to be presented to corporate customers.

[0010] "Format" refers to the standard structure of the composition and layout of proposal materials.

[0011] "Content" refers to information such as customer information, product information, industry trends, and implementation examples that are specifically described in the proposal materials.

[0012] An "interface" is a means of user interaction that allows a user to interact with a system.

[0013] "Extraction" is the process of searching, selecting and retrieving requested information from a database.

[0014] "Editing" refers to the process in which the user modifies the content of the generated proposal material, adding or changing it.

[0015] "Saving" is the process of storing the final proposal document edited by the user in a database so that it can be reused at a later date.

[0016] "Training" is the process by which the generative AI learns using past data so that it can generate highly accurate proposal materials. [Brief explanation of the drawings]

[0017] [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 illustrating 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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] System Configuration

[0039] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generation AI, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[0040] Initial settings and database creation

[0041] The server first collects the formats and contents of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type and industry, and is structured so that information can be quickly extracted when needed.

[0042] Training generative AI

[0043] The server trains the generative AI using the proposal data stored in the database. The trained generative AI is then able to generate new proposals with high accuracy.

[0044] User interaction and data entry

[0045] Users access the system through a terminal and input information to create new proposal materials. Specifically, users use an interface to enter basic information about corporate clients (e.g., company name, industry, size) and information about the products they are proposing (e.g., product name, features, price).

[0046] Data extraction and proposal generation

[0047] When the server receives the information entered by the user, it searches and extracts the appropriate format and relevant content from the database. Based on the extracted data, it uses generative AI to generate a new proposal document. This generated proposal document is structured based on the selected format and includes the specific information requested by the user.

[0048] Review and edit proposal materials

[0049] The terminal provides the generated proposal materials to the user. The user uses an interface to check the displayed proposal materials and edit the content as necessary. The user can adjust the content of the materials appropriately and finalize them.

[0050] Saving proposal materials

[0051] The final edited proposal is sent from the device to a server and saved in a database, where the server indexes and stores the new proposal for future reuse by other users.

[0052] Specific examples

[0053] User operation example

[0054] When a salesperson creates a proposal document for a new corporate client, the salesperson logs into the system and enters basic information about the client and details of the products they are proposing.

[0055] For example, suppose the client is a manufacturing company with 500 employees and the proposed product is new ERP software.

[0056] System working example

[0057] The server receives the input information and selects the appropriate format from past proposal documents for the manufacturing industry.

[0058] Based on the selected format, the server uses trained generative AI to generate new proposal materials.

[0059] For example, the proposal document includes trends in the manufacturing industry, the benefits of ERP software, and past implementation examples.

[0060] Review and edit

[0061] The generated proposal is provided to the user via a terminal, who can review the proposal and make modifications to suit their specific needs.

[0062] For example, adding customized solutions to proposals based on specific customer requirements.

[0063] Save and reuse

[0064] The final proposal is sent to a server and stored in a database, which indexes and stores the new proposal for future use by other salespeople.

[0065] This system enables all sales representatives to efficiently create high-quality proposal materials, improving overall sales capabilities.

[0066] The processing flow will be explained below.

[0067] Step 1: Building the database

[0068] The server collects the format and content of previously used proposal documents, structures them, and stores them in a database that is categorized by industry and category, allowing for quick search and retrieval of information.

[0069] Step 2: Training the generative AI

[0070] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0071] Step 3: User login and input

[0072] The user logs into the system through a terminal and enters basic information about the corporate customer (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) into the interface, which is necessary to create a proposal document.

[0073] Step 4: Receiving and analyzing information

[0074] The server receives the information sent by the user, analyzes it, and prepares to search for related data in the database based on the analysis results.

[0075] Step 5: Extracting format and content

[0076] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[0077] Step 6: Generate a proposal

[0078] The server uses the extracted format and content to run a generative AI to generate new proposals, which are customized based on the information provided by the user.

[0079] Step 7: Submit your proposal

[0080] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[0081] Step 8: Review and edit your proposal

[0082] The user can review the provided proposal materials on their device and use the interface to make any necessary corrections or additions, for example, to tailor the content to meet the specific needs of the client.

[0083] Step 9: Finalize and submit

[0084] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[0085] Step 10: Save your proposal

[0086] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[0087] The above steps create a system that enables sales representatives to efficiently create high-quality proposal materials.

[0088] Example 1

[0089] 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."

[0090] The traditional proposal document creation process had problems with high quality variation and low efficiency because each sales representative created their own documents. Furthermore, there was often no database to utilize past success stories, making it difficult to share know-how. Furthermore, creating new documents took time and effort, making it difficult to respond quickly when a quick response was required.

[0091] 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.

[0092] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generative AI model based on the format and content of the proposal materials, means for receiving information entered by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generative AI model based on the extracted format and content, means for providing the generated proposal materials to the user, means for the user to review and edit the provided proposal materials, means for saving the final edited proposal materials in the database, and means for indexing the proposal materials to make them reusable. This enables consistent and rapid creation of high-quality proposal materials, thereby realizing the sharing of know-how and improved business efficiency.

[0093] "Previously used proposal materials" are materials that contain proposal content and formats that have already been used in practice.

[0094] "Format" refers to the layout, format, design, and general components of the proposal.

[0095] "Content" refers to the specific information, data, examples, and explanatory text contained in the proposal materials.

[0096] A "database" is a system that can efficiently store, manage, search, and update structured data.

[0097] A "generative AI model" refers to an artificial intelligence algorithm that learns from input data and automatically generates new proposal materials.

[0098] "User" refers to a person who uses the system to create, review, and edit proposal materials.

[0099] "Information" refers to data such as basic customer information and proposed product information that the user inputs to create proposal materials.

[0100] "Means of receiving" refers to the technology or method by which the system receives information entered by the user.

[0101] "Format and content extraction means" refers to the techniques and methods used to select appropriate format and content from the database.

[0102] "New proposal materials" refers to proposal documents automatically generated by a generative AI model based on user input information and past data.

[0103] "Means for providing" refers to the technology or method for displaying, transmitting, or making accessible the generated proposal materials to the user.

[0104] "Means for reviewing and editing" refers to techniques and methods that allow users to review, correct, and supplement the generated proposal materials.

[0105] "Final edited proposal material" refers to the proposal material that has been checked and corrected as necessary by the user.

[0106] "Means of indexing proposal documents to make them reusable" refers to techniques and methods for adding easily searchable tags and data to proposal documents for future use.

[0107] System Configuration

[0108] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generative AI model, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[0109] Initial settings and database creation

[0110] The server first collects the format and content of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type (e.g., pptx, pdf, docx) and industry (manufacturing, IT, healthcare, etc.), and is structured so that information can be quickly extracted when needed. To do this, the server uses Python's Pandas library to format the data.

[0111] Training generative AI

[0112] The server uses the stored proposal data to train the generative AI model. This training uses machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch. The specific training procedure involves preprocessing the data, dividing it into a training dataset and a test dataset, and then inputting the data into the generative AI model for training.

[0113] User interaction and data entry

[0114] Users log in to the system via their terminal and enter information to create proposal materials. This input is done using a dedicated form on a web browser. The form is built using HTML5 and JavaScript (registered trademark) and includes fields for entering information such as the company name, industry, number of employees, proposed product name, features, and price. When the user performs input operations, the data is sent to the server in JSON format.

[0115] Data extraction and proposal generation

[0116] When the server receives the information entered by the user, it searches the database for the appropriate format and content based on that information. This search is performed using an SQL query. For example, to search for manufacturing data, the query "SELECT FROM Proposal Documents WHERE Industry = 'Manufacturing'" is used. Then, based on the search results, a generative AI model is used to generate new proposal documents. The generative AI model generates personalized proposal content based on the user's input, including instructions provided by the prompt.

[0117] Specific examples

[0118] Prompt: "Write a proposal for ERP software for a 500-person manufacturing company."

[0119] Review and edit proposal materials

[0120] The device provides the generated proposal documents to the user, who then reviews them using an interface on the device. This interface was designed using JavaScript and React, allowing the user to make real-time edits to the proposal documents. For example, they can add information about specific features of the proposed software or edit existing information.

[0121] Saving proposal materials

[0122] The final edited proposal document is sent from the device to the server and saved in a database. This saving process also stores metadata, including the file name and the date and time of saving. The server uses the Python Django framework to save the proposal document and its metadata in a database. MySQL (registered trademark) or PostgreSQL is used for the database. After saving, the document is indexed so that other sales representatives can reuse it in the future.

[0123] This enables the system to help sales representatives create efficient, high-quality proposal materials, improving overall sales performance.

[0124] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0125] Step 1:

[0126] The server collects the format and content of past proposal documents and stores them in a database. During this process, the server uses the Python Pandas library to format the collected proposal documents into the appropriate format.

[0127] Input: Previously used proposal materials

[0128] Data processing: Use Pandas to format the data and categorize it by format.

[0129] Output: Formatted proposal data stored in a database

[0130] Step 2:

[0131] The server uses the proposal data stored in the database to train the generative AI model, using machine learning frameworks such as TensorFlow and PyTorch, which involves steps of preprocessing, data partitioning, and model training.

[0132] Input: Proposal data in the database

[0133] Data Computing: Preprocessing and model training using TensorFlow and PyTorch

[0134] Output: A trained generative AI model

[0135] Step 3:

[0136] Users log in to the system via their terminal and enter information to create proposal documents. The input form is built using HTML5 and JavaScript, and users enter information such as company name, industry, number of employees, proposed product name, features, and price.

[0137] Input: Company name, industry, number of employees, product information to be proposed, etc.

[0138] Data processing: Convert input information into JSON format and send it to the server

[0139] Output: User input data received from server in JSON format

[0140] Step 4:

[0141] The server uses the received user input to extract the appropriate format and content from the database, using SQL queries to quickly retrieve the relevant data.

[0142] Input: User input information in JSON format

[0143] Data Search: Use SQL queries to find the right format and content

[0144] Output: Extracted format and content

[0145] Step 5:

[0146] The server generates new proposal documents using a generative AI model based on the extracted format and content. This generation process involves inputting prompts containing user input information into the generative AI model.

[0147] Input: Extracted format and content, user-entered information

[0148] Data computation: Generative AI models are fed with user information and prompts to generate new proposals.

[0149] Output: The new proposal that was generated

[0150] Step 6:

[0151] The device provides the generated proposal documents to the user, who can then review and edit them as needed using the device's interface, which is built with JavaScript and React.

[0152] Input: Generated new proposal

[0153] Behavior: Displays material to the user and provides an editing interface

[0154] Output: User-reviewed and edited proposal

[0155] Step 7:

[0156] The user checks and edits the proposal material to finalize it, and the terminal transmits the edited proposal material to the server.

[0157] Input: Generated proposal, user modifications

[0158] Data processing: Creating the final proposal document reflecting the user's modifications

[0159] Output: Final edited proposal

[0160] Step 8:

[0161] The server then stores the final edited proposal in a database, indexes it, and makes it reusable, along with metadata such as the file name and the date and time it was saved.

[0162] Input: Final edited proposal

[0163] Data storage: Stored in database and indexed

[0164] Output: Final proposal and index stored in database

[0165] (Application example 1)

[0166] 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."

[0167] Conventional proposal generation systems do not necessarily enable sales representatives to efficiently create proposal materials for corporate customers. Real-time data collection and analysis is particularly important for in-factory production planning and parts procurement proposals, but this requires a lot of manual work, which takes time and effort. This can lead to insufficient optimization of production lines and cost reductions. Furthermore, because the quality of proposal materials depends on the experience and skills of sales representatives, it is difficult to maintain consistent quality.

[0168] 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.

[0169] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generation AI based on the format and content of the proposal materials, means for receiving information input by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generation AI based on the extracted format and content, means for machines operating in a factory to collect production data in real time and generate proposal materials related to parts shortages and production plan optimization, means for providing the generated proposal materials to a user, means for the user to review and edit the provided proposal materials, and means for saving the final edited proposal materials in a database. This makes it possible to utilize real-time data for in-factory production plans and parts procurement proposals, and to automatically generate high-quality proposal materials quickly and efficiently.

[0170] A "proposal document" is a document that summarizes the details of the products or services that are proposed to corporate clients.

[0171] A "database" is a collection of electronic data that is structured to store information systematically and make it easy to search and retrieve.

[0172] "Generative AI" is a system or program that uses artificial intelligence technology to automatically generate new information or documents.

[0173] "User" means an individual or company employee who uses the system to create and edit proposal materials.

[0174] "Format" refers to the layout and structure of the proposal materials, specifically including the placement of text and design elements.

[0175] "Content" refers to the specific information in the documents and data contained in the proposal materials, including product features, prices, implementation examples, etc.

[0176] An "interface" is a screen or tool that allows a user to interact with a system and facilitates the input and editing of information.

[0177] "Real-time data" refers to data collected in real time by machines and sensors operating within a factory to determine the current situation.

[0178] "Production planning" refers to the product manufacturing schedule and resource allocation plan in a factory.

[0179] "Parts shortage" refers to a situation where a necessary part is not available on the production line.

[0180] This invention relates to a system that works in conjunction with machines operating in a factory and uses real-time data to automatically generate proposal materials related to parts shortages and optimization of production plans. The system includes the following elements:

[0181] 1. Database construction:

[0182] The server collects the format and content of past proposal documents and stores them in a database. This database is categorized based on the format and content of the proposal documents and is structured to allow for quick extraction of relevant information.

[0183] 2. Training the generative AI:

[0184] The server uses the proposal data stored in the database to train a generative AI model, which has the ability to automatically generate new proposals with high accuracy.

[0185] 3. Data Collection:

[0186] Machines operating in factories collect production data in real time, including machine operation status, parts consumption, and inventory status.

[0187] 4. User Input:

[0188] Users access the system through a terminal and input basic information about the corporate customer and information about the product they wish to propose. This can be done easily using the interface.

[0189] 5. Data extraction and proposal generation:

[0190] The server integrates user-entered information with real-time production data, extracts the appropriate format and content from the database, and then uses generative AI to generate new proposal materials based on the extracted information.

[0191] 6. Proposal materials provision and editing:

[0192] The generated proposal material is provided to the user, who can use an interface to check the material through a terminal and edit the content as necessary.

[0193] 7. Save the Final Version:

[0194] The final proposal document edited by the user is sent back to the server and saved in the database, allowing other users to reuse the new proposal document.

[0195] Hardware and Software Used

[0196] Hardware:

[0197] Machines operating in factories (production machines with sensors)

[0198] Servers (requiring high performance computing)

[0199] User devices (smartphones, tablets, computers)

[0200] software:

[0201] Deep learning frameworks (e.g., Keras)

[0202] Database Management Systems

[0203] User interface tools (web or mobile app)

[0204] Specific examples

[0205] In a factory, the following prompts can be used:

[0206] Prompt Sentence Examples

[0207] Based on the information below, please create next week's production plan and parts procurement proposal materials.

[0208] Customer name: Manufacturing A

[0209] Industry: Auto parts manufacturing

[0210] Number of employees: 1,200

[0211] Production planning data: [List data here]

[0212] Product name: New engine parts

[0213] Features: Lightweight, high strength

[0214] Price: 5,000 yen / piece

[0215] This system allows factory managers to utilize real-time data to quickly and efficiently create production plans and automatically generate parts procurement proposals, thereby improving production efficiency and reducing costs.

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] The server collects the format and content of proposal documents used in the past and stores them in a database. Specifically, the server collects existing proposal documents as electronic data and stores them in a database. In the database, this data is structured so that it is categorized based on industry and format. The input is the past proposal document data, and the output is a structured database.

[0219] Step 2:

[0220] The server trains the generative AI model using proposal data stored in the database. The server extracts the format and content of proposal documents from the database and supplies them to the generative AI model to train the model. The input is the proposal data extracted from the database, and the output is the trained generative AI model.

[0221] Step 3:

[0222] Machines operating in a factory collect production data in real time. This data is obtained from the machine's sensors and is related to the operating status, parts consumption, and inventory status. This data is sent to a server. The input is the real-time data from the machine's sensors, and the output is the production data sent to the server.

[0223] Step 4:

[0224] The user uses a terminal to input basic information about the corporate customer and information about the product they are proposing. The user inputs this information through a dedicated interface, and the terminal sends the information to the server. The input is the corporate customer information and product information entered by the user, and the output is the information sent to the server.

[0225] Step 5:

[0226] The server integrates the information entered by the user with real-time production data and extracts the appropriate format and content from the database. The server processes the data as needed based on this information and reconstructs the appropriate data. The input is the information entered by the user and real-time production data, and the output is the extracted format and content.

[0227] Step 6:

[0228] The server generates new proposal materials using the generative AI model. The server inputs the extracted format and content into the generative AI model and automatically generates new proposal materials. The input is the extracted format and content, and the output is the generated new proposal materials.

[0229] Step 7:

[0230] The generated proposal materials are provided to the user. The server sends the generated proposal materials to the terminal, where the user can review and edit them. The input is the generated proposal materials, and the output is the user's review and editing.

[0231] Step 8:

[0232] The user submits the final edited proposal to the server, which stores it in a database. The server indexes the new proposal so that it can be reused by other users in the future. The input is the final edited proposal by the user, and the output is the proposal stored in the database.

[0233] 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.

[0234] System Configuration

[0235] The system of the present invention includes a server, a terminal, a user interface, a database, and an emotion engine. The server is responsible for storing data, training the generative AI, extracting information, generating proposal materials, and processing emotion data. The terminal provides an interface for users to interact with the system and input and edit information. Users are responsible for creating and editing proposal materials for corporate clients. The emotion engine recognizes user emotions and reflects that information in the generation of proposal materials.

[0236] Initial settings and database creation

[0237] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[0238] Training generative AI

[0239] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0240] User interaction and data entry

[0241] Users access the system through their terminals and input information to create proposal materials. Specifically, users enter basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price) into the interface. At this time, the emotion engine recognizes the user's emotions and collects emotion data.

[0242] Receiving and analyzing information

[0243] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[0244] Format and content extraction

[0245] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[0246] Proposal generation

[0247] The server uses the extracted format and content to run the generative AI to generate new proposal materials. At this time, the emotion engine adjusts the content and tone of the materials based on the user's emotional data collected. For example, if the user is expressing positive emotions, the proposal materials will reflect a positive tone.

[0248] Providing proposal materials

[0249] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[0250] Review and edit proposal materials

[0251] The user can review the provided proposal materials on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requests. The emotion engine also continuously monitors changes in the user's emotions and reflects them in the editing process.

[0252] Finalize and send

[0253] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[0254] Saving proposal materials

[0255] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[0256] Specific examples

[0257] User operation example

[0258] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[0259] System working example

[0260] The server analyzes the input information and emotion data, and selects the appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document.

[0261] The generated proposal is then provided to the user via their device, who can review it and fine-tune it to suit the client's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the proposal as needed.

[0262] The final edited proposal document is sent to the server and stored in the database, where other sales representatives can use it as a reference when creating their own proposal documents.

[0263] The present invention makes it possible to efficiently create high-quality proposal materials that take into account the emotional state of the user, thereby improving overall sales capabilities.

[0264] The processing flow will be explained below.

[0265] Step 1: Building the database

[0266] The server collects the format and content of past proposal documents, structures them, and stores them in a database. This database is categorized by the industry and category of the proposal, allowing for quick search and retrieval of information.

[0267] Step 2: Training the generative AI

[0268] The server trains the AI ​​using the proposal data stored in the database. The trained AI can then generate optimal proposals with high accuracy based on new information entered by the user.

[0269] Step 3: User Login and Data Entry

[0270] The user logs in to the system using a terminal, and then enters basic information about the corporate client (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) through an interface for creating proposal materials.

[0271] Step 4: Emotion Recognition with the Emotion Engine

[0272] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotional state, and this emotional data is reflected in the creation of proposal materials.

[0273] Step 5: Receiving and analyzing information

[0274] The server receives and analyzes the basic information, product information, and emotion data sent by the user. Based on the analysis results, it prepares to search for related data in the database.

[0275] Step 6: Extracting format and content

[0276] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it extracts the proposal format and related content for the manufacturing industry.

[0277] Step 7: Generate a proposal

[0278] The server uses the extracted format and content to run a generative AI to generate a new proposal. At this stage, emotional data from the emotion engine is also incorporated, and the proposal incorporates a tone and style that reflects the user's emotional state.

[0279] Step 8: Submit your proposal

[0280] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user has the opportunity to review the proposal and fine-tune its content.

[0281] Step 9: Review and edit your proposal

[0282] The user reviews the proposal displayed on their device in detail. They then use the interface to edit the content of the proposal, making any necessary corrections or adding additional information. While editing, the emotion engine continues to monitor the user's emotional state and optimizes the tone and style of the proposal.

[0283] Step 10: Finalize and submit

[0284] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the completed proposal document is sent to the server.

[0285] Step 11: Save your proposal

[0286] The server saves the final proposal documents it receives in a database, where they are indexed and stored for future reference by other sales representatives.

[0287] The above steps realize a process for creating proposal materials that utilizes an emotion engine, making it possible to generate high-quality materials that take into account the user's emotional state.

[0288] Example 2

[0289] 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."

[0290] Conventional systems for creating proposal materials were unable to effectively utilize past data and had difficulty automatically generating proposal materials that reflected user emotions. In particular, reading user emotions and creating materials that reflected them had to be done manually, which was inefficient. Furthermore, the content of proposal materials was uniform and lacked customization for individual customers, resulting in a low success rate for proposals. A new system that solves these problems is needed.

[0291] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing the format and content of proposal materials used in the past in a database, a means for training the generation AI based on the format and content of the proposal materials, and a means for recognizing the user's emotions and reflecting the data in the proposal materials. This makes it possible to quickly and efficiently generate customized proposal materials that reflect the user's emotions while effectively utilizing past data.

[0292] The "database" is a collection of information that stores the format and content of proposal materials used in the past and is categorized by industry and category.

[0293] "Generative AI" is an artificial intelligence that is trained based on proposal document data in a database and automatically generates new proposal documents using input information and emotional data from users.

[0294] A "user" is an entity that inputs information into the system to create proposal materials, and checks and edits the generated proposal materials.

[0295] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions and tone of voice, and reflects that data in the content and tone of proposal materials.

[0296] A "terminal" is a device through which a user accesses the system and enters and edits information.

[0297] A "proposal document" is a document that summarizes the content of a proposal to a corporate client, and is automatically generated by generation AI.

[0298] "Format" refers to the structure and layout of a proposal document, and is suitable for a particular industry or purpose.

[0299] "Information extraction" is the process of searching and retrieving the required format and content from within a database.

[0300] "Emotion data" is data that represents the emotional state obtained by the emotion engine from the user's facial expression and voice.

[0301] MODE FOR CARRYING OUT THE INVENTION

[0302] The present invention is a system that includes a server, a terminal, a user interface, a database, and an emotion engine. Here, the role of each component and its specific operation will be explained.

[0303] 1. Server configuration and operation

[0304] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for fast and efficient information retrieval.

[0305] The generative AI is trained using data stored in the database, using open-source machine learning frameworks (e.g., TensorFlow, PyTorch).

[0306] The server receives the information and emotion data sent by the user, analyzes them, and based on the analysis results, searches and extracts relevant data from the database.

[0307] The server inputs the extracted format and content into the generation AI to generate new proposal materials, adjusting the content and tone of the proposal materials based on the user's emotional data recognized by the emotion engine.

[0308] 2. Terminal configuration and operation

[0309] The terminal provides an interface for users to interact with the system and input information. This interface is implemented using HTML and JavaScript, and allows users to enter basic information about corporate customers and details of the products they are proposing.

[0310] The terminal provides the generated proposal material to the user, who can then check the material and edit it as necessary.

[0311] The terminal has the function of sending the proposal document that the user has completed editing to the server, where it is analyzed again for final confirmation and saved in the database.

[0312] 3. User Operation

[0313] Users access the system through a terminal and input information to create proposal materials. Specifically, they input basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price).

[0314] The emotion engine recognizes emotions from the user's facial expressions and tone of voice and collects this emotion data.

[0315] 4. Emotion Engine

[0316] The emotion engine recognizes the user's emotions and reflects that data in the proposal materials. Specifically, if the user shows positive emotions, the proposal materials will reflect a positive tone.

[0317] Specific examples

[0318] Example of user action:

[0319] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[0320] Example of a working system:

[0321] The server analyzes the input information and emotion data and selects an appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document. The generated proposal document is provided to the user via their device, who reviews it and fine-tunes it to suit the customer's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the document as needed. The final edited proposal document is sent to the server and stored in a database. Other sales representatives can use this document as a reference when creating their own proposal documents.

[0322] Prompt Sentence Examples

[0323] Company Information: Smart Tech Co., Ltd.

[0324] Industry: Manufacturing

[0325] Size: Medium-sized company

[0326] Proposed product: ERP software

[0327] Product features: Integrated management, automation, real-time analysis

[0328] Price: 1 million yen for a yearly contract

[0329] This makes it possible to efficiently create high-quality proposal materials that take into account the user's emotional state, thereby improving overall sales capabilities.

[0330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0331] Step 1:

[0332] The server collects past proposal materials and stores them in a database.

[0333] Input: Previously used proposal materials (PDF, Word, etc.)

[0334] Processing: Analyze the format and content of the documents, then classify and store them in a database. Specifically, extract text data from the documents and organize them by industry and category.

[0335] Output: A database containing classified proposals

[0336] Step 2:

[0337] The server trains the generative AI using proposal data in the database.

[0338] Input: Text data of proposal documents stored in a database

[0339] Processing: Use machine learning frameworks (e.g., TensorFlow, PyTorch) to train generative AI on the format and content of the proposal.

[0340] Output: A trained generative AI model

[0341] Step 3:

[0342] A user accesses the system through a terminal and inputs information to create a proposal document.

[0343] Input: Basic information about the corporate customer (company name, industry, size) and information about the proposed product (product name, features, price)

[0344] Processing: Collect input data using an information input interface (HTML, JavaScript).

[0345] Output: User input data

[0346] Step 4:

[0347] The emotion engine recognizes the user's emotions and collects that data.

[0348] Input: User's facial expression, tone of voice

[0349] Processing: Emotion recognition algorithms are used to analyze facial expressions and vocal tones.

[0350] Output: Emotion data

[0351] Step 5:

[0352] The server receives the information and emotion data sent by the user and analyzes them.

[0353] Input: User input data, emotion data

[0354] Processing: Analysis algorithms are used to check the consistency of the input data with the sentiment data and extract relevant data.

[0355] Output: Parsed input data and emotion data

[0356] Step 6:

[0357] Based on the analysis results, the server extracts the appropriate format and relevant content from the database.

[0358] Input: Parsed input data and emotion data

[0359] Processing: Using database search algorithms, we extract the most appropriate format and relevant content, for example, selecting the suggested format and content for the manufacturing industry.

[0360] Output: Extracted format and content

[0361] Step 7:

[0362] The server uses the extracted format and content to run a generative AI to generate new proposal materials.

[0363] Input: Extracted format, content, and sentiment data

[0364] Processing: Run the generative AI model to generate a pitch deck, adjusting the tone and content of the deck based on the sentiment data.

[0365] Output: Generated proposal

[0366] Step 8:

[0367] The server temporarily stores the generated proposal materials and provides them to the user through the terminal.

[0368] Input: Generated proposal

[0369] Processing: The proposal materials are temporarily stored and prepared for transmission to the user via the terminal.

[0370] Output: Proposal document ready for user review

[0371] Step 9:

[0372] The user checks the provided proposal materials on the terminal and makes any necessary corrections or additions using the interface.

[0373] Input: Generated proposal

[0374] Processing: The user reviews the proposal and makes corrections or additions via the user interface. The emotion engine also monitors changes in emotion during editing.

[0375] Output: Edited proposal

[0376] Step 10:

[0377] The user completes the edits and finalizes the proposal.

[0378] Input: Edited proposal

[0379] Processing: By pressing the Confirm button, the proposal materials are sent to the server.

[0380] Output: Final, confirmed proposal

[0381] Step 11:

[0382] The server stores the received final proposal document in a database.

[0383] Input: Final, confirmed proposal

[0384] Processing: Store in a database and index for future reference when creating proposals.

[0385] Output: Saved proposal

[0386] (Application example 2)

[0387] 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."

[0388] Conventional proposal material creation systems do not take into account the user's emotional state, resulting in problems with the materials provided not being in line with the user's emotions or situation. Furthermore, when personalizing the purchasing experience in a virtual store, there was a lack of a mechanism to respond to the user's real-time emotional changes. This made it difficult to effectively improve the user's purchasing motivation and satisfaction.

[0389] 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.

[0390] In this invention, the server includes means for storing the format and content of previously used proposals in a database, means for training a generation AI based on the format and content of the proposals, means for receiving information entered by a user for creating a proposal, means for extracting appropriate formats and content from the database based on the received information, means for generating a new proposal using the generation AI based on the extracted format and content, means for providing the generated proposal to the user, means for the user to review and edit the provided proposal, means for saving the final edited proposal in the database, means for analyzing the user's emotions in real time using an emotion recognition engine, and means for adjusting the content and tone of the proposal based on the user's emotional state, thereby making it possible to provide proposal materials and purchasing experiences that reflect the user's emotions.

[0391] "Proposal format" refers to the layout and structure of documents such as proposals and reports, and is a template or format that improves the readability of the content and the ease with which information is conveyed.

[0392] "Proposal content" refers to text or data containing detailed information about a specific proposal or project, and is an element that explains the key points and advantages of a specific proposal.

[0393] A "database" is a structured collection of data, a system that allows for efficient information storage, management, and retrieval.

[0394] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to automatically generate new data and documents, for example, to create proposals and reports.

[0395] "User" refers to the entity that uses this system to create, edit, and check proposals, and in most cases is a corporate sales representative or presentation person.

[0396] An "emotion recognition engine" is a system that automatically analyzes and recognizes emotions from a user's facial expressions and voice, and is a technology that optimizes the system's operation based on that information.

[0397] "Proposal tone adjustment" is the process of adapting the presentation and wording of a proposal's content to suit the user's emotional state.

[0398] A "personalized shopping experience" is a method for increasing user satisfaction by providing a shopping experience that is customized based on the preferences, needs, and emotions of each individual user.

[0399] The present invention provides a system for generating a new proposal based on the format and content of an existing proposal, and for adjusting the content and tone of the proposal depending on the user's emotional state. A specific embodiment of this system is described below.

[0400] System Configuration

[0401] The system includes a server, a terminal, a user interface, a database, and an emotion recognition engine. The server is responsible for storing data, training the generative AI, extracting information, and generating proposals. The emotion recognition engine recognizes users' emotions and reflects that information in the generation and adjustment of proposals.

[0402] Initial settings and database creation

[0403] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[0404] Training generative AI

[0405] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0406] User interaction and data entry

[0407] Users access the system through their terminals and input information to create proposals. Specifically, users enter basic information about the corporate client (company name, industry, size) and information about the product they are proposing (product name, features, price) into the interface. At this time, an emotion recognition engine recognizes the user's emotions and collects data.

[0408] Receiving and analyzing information

[0409] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[0410] Format and content extraction

[0411] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user proposes ERP software to a manufacturing customer, the server extracts the proposal format and related content for the manufacturing industry.

[0412] Proposal generation

[0413] The server uses the extracted format and content to run a generative AI to generate a new proposal. The emotion recognition engine then adjusts the content and tone of the proposal based on the user's emotional data collected. For example, if the user expresses positive emotions, the proposal will reflect a positive tone.

[0414] Proposal submission

[0415] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[0416] Review and edit the proposal

[0417] The user can review the provided proposal on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requirements. The emotion recognition engine also continuously monitors the user's emotional changes and reflects them in the editing process.

[0418] Finalize and send

[0419] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[0420] Save the proposal

[0421] The server stores the final proposal it receives in a database, where it indexes the proposal so that other sales representatives can refer to it when creating future proposals.

[0422] Hardware and software used

[0423] Facial Recognition Camera: Commonly Used Webcam

[0424] Smart glasses or head-mounted displays (HMDs): For example, Oculus Quest 2

[0425] Emotion Recognition: Pipeline Methods in the Transformers Library

[0426] VR Interface: Virtual 3D VR Library

[0427] Specific examples

[0428] A user visits a virtual store and puts on smart glasses. The system analyzes the user's facial expressions and voice, and if the user appears happy, it will proactively suggest products (e.g., new or popular items). On the other hand, if the user appears tired, it will suggest relaxation goods. This personalizes the user's shopping experience and increases satisfaction.

[0429] Example prompts to input to the generative AI model

[0430] "If the user is feeling relaxed, suggest products that will help them relax."

[0431] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0432] Processing Steps

[0433] Step 1:

[0434] Initial settings and database creation

[0435] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick information retrieval.

[0436] Input: Past proposal data

[0437] Output: A structured database

[0438] Step 2:

[0439] Training generative AI

[0440] The server uses the proposal data in the database to train the generative AI model, giving it the ability to adapt to new situations and generate high-quality proposals.

[0441] Input: Proposal data in the database

[0442] Output: A trained generative AI model

[0443] Step 3:

[0444] User interaction and data entry

[0445] Users access the system using a terminal and enter basic information (company name, industry, size) and details of the proposed product (product name, features, price) to create a proposal. At this time, the emotion recognition engine analyzes the user's emotions in real time and collects data.

[0446] Input: User's basic information, item information, facial expressions and voice data

[0447] Output: User input information and emotion data

[0448] Step 4:

[0449] Receiving and analyzing information

[0450] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data from the database based on the analysis results.

[0451] Input: User input information, emotion data

[0452] Output: Analysis results, search criteria

[0453] Step 5:

[0454] Format and content extraction

[0455] Based on the analysis results, the server extracts the appropriate format and content from the database, for example, selecting a proposal format for the manufacturing industry and related content.

[0456] Input: Analysis results, database

[0457] Output: appropriate format and content

[0458] Step 6:

[0459] Proposal generation

[0460] The server uses the extracted format and content to run a generative AI to generate a new proposal, adjusting the tone and content of the proposal based on the user's emotional data collected by the emotion recognition engine.

[0461] Input: Extracted format, content, and sentiment data

[0462] Output: New proposal

[0463] Step 7:

[0464] Proposal submission

[0465] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[0466] Enter: New Proposal

[0467] Output: Temporarily save the proposal and provide it to the user

[0468] Step 8:

[0469] Review and edit the proposal

[0470] The user can use the device to check the proposal and make any necessary corrections or additions. The emotion recognition engine monitors the user's emotional changes and reflects them in the editing process.

[0471] Input: Proposal, edits, sentiment data

[0472] Output: Revised and added proposal

[0473] Step 9:

[0474] Finalize and send

[0475] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[0476] Input: Final edited proposal

[0477] Output: Send the final proposal to the server

[0478] Step 10:

[0479] Save the proposal

[0480] The server stores the final proposals it receives in a database and indexes them for future reference.

[0481] Input: Final proposal

[0482] Output: Stored in database, indexed

[0483] 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.

[0484] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0485] 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.

[0486] [Second embodiment]

[0487] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0488] 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.

[0489] 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).

[0490] 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.

[0491] 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.

[0492] 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).

[0493] 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.

[0494] 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.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] 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."

[0499] System Configuration

[0500] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generation AI, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[0501] Initial settings and database creation

[0502] The server first collects the formats and contents of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type and industry, and is structured so that information can be quickly extracted when needed.

[0503] Training generative AI

[0504] The server trains the generative AI using the proposal data stored in the database. The trained generative AI is then able to generate new proposals with high accuracy.

[0505] User interaction and data entry

[0506] Users access the system through a terminal and input information to create new proposal materials. Specifically, users use an interface to enter basic information about corporate clients (e.g., company name, industry, size) and information about the products they are proposing (e.g., product name, features, price).

[0507] Data extraction and proposal generation

[0508] When the server receives the information entered by the user, it searches and extracts the appropriate format and relevant content from the database. Based on the extracted data, it uses generative AI to generate a new proposal document. This generated proposal document is structured based on the selected format and includes the specific information requested by the user.

[0509] Review and edit proposal materials

[0510] The terminal provides the generated proposal materials to the user. The user uses an interface to check the displayed proposal materials and edit the content as necessary. The user can adjust the content of the materials appropriately and finalize them.

[0511] Saving proposal materials

[0512] The final edited proposal is sent from the device to a server and saved in a database, where the server indexes and stores the new proposal for future reuse by other users.

[0513] Specific examples

[0514] User operation example

[0515] When a salesperson creates a proposal document for a new corporate client, the salesperson logs into the system and enters basic information about the client and details of the products they are proposing.

[0516] For example, suppose the client is a manufacturing company with 500 employees and the proposed product is new ERP software.

[0517] System working example

[0518] The server receives the input information and selects the appropriate format from past proposal documents for the manufacturing industry.

[0519] Based on the selected format, the server uses trained generative AI to generate new proposal materials.

[0520] For example, the proposal document includes trends in the manufacturing industry, the benefits of ERP software, and past implementation examples.

[0521] Review and edit

[0522] The generated proposal is provided to the user via a terminal, who can review the proposal and make modifications to suit their specific needs.

[0523] For example, adding customized solutions to proposals based on specific customer requirements.

[0524] Save and reuse

[0525] The final proposal is sent to a server and stored in a database, which indexes and stores the new proposal for future use by other salespeople.

[0526] This system enables all sales representatives to efficiently create high-quality proposal materials, improving overall sales capabilities.

[0527] The processing flow will be explained below.

[0528] Step 1: Building the database

[0529] The server collects the format and content of previously used proposal documents, structures them, and stores them in a database that is categorized by industry and category, allowing for quick search and retrieval of information.

[0530] Step 2: Training the generative AI

[0531] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0532] Step 3: User login and input

[0533] The user logs into the system through a terminal and enters basic information about the corporate customer (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) into the interface, which is necessary to create a proposal document.

[0534] Step 4: Receiving and analyzing information

[0535] The server receives the information sent by the user, analyzes it, and prepares to search for related data in the database based on the analysis results.

[0536] Step 5: Extracting format and content

[0537] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[0538] Step 6: Generate a proposal

[0539] The server uses the extracted format and content to run a generative AI to generate new proposals, which are customized based on the information provided by the user.

[0540] Step 7: Submit your proposal

[0541] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[0542] Step 8: Review and edit your proposal

[0543] The user can review the provided proposal materials on their device and use the interface to make any necessary corrections or additions, for example, to tailor the content to meet the specific needs of the client.

[0544] Step 9: Finalize and submit

[0545] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[0546] Step 10: Save your proposal

[0547] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[0548] The above steps create a system that enables sales representatives to efficiently create high-quality proposal materials.

[0549] Example 1

[0550] 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."

[0551] The traditional proposal document creation process had problems with high quality variation and low efficiency because each sales representative created their own documents. Furthermore, there was often no database to utilize past success stories, making it difficult to share know-how. Furthermore, creating new documents took time and effort, making it difficult to respond quickly when a quick response was required.

[0552] 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.

[0553] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generative AI model based on the format and content of the proposal materials, means for receiving information entered by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generative AI model based on the extracted format and content, means for providing the generated proposal materials to the user, means for the user to review and edit the provided proposal materials, means for saving the final edited proposal materials in the database, and means for indexing the proposal materials to make them reusable. This enables consistent and rapid creation of high-quality proposal materials, thereby realizing the sharing of know-how and improved business efficiency.

[0554] "Previously used proposal materials" are materials that contain proposal content and formats that have already been used in practice.

[0555] "Format" refers to the layout, format, design, and general components of the proposal.

[0556] "Content" refers to the specific information, data, examples, and explanatory text contained in the proposal materials.

[0557] A "database" is a system that can efficiently store, manage, search, and update structured data.

[0558] A "generative AI model" refers to an artificial intelligence algorithm that learns from input data and automatically generates new proposal materials.

[0559] "User" refers to a person who uses the system to create, review, and edit proposal materials.

[0560] "Information" refers to data such as basic customer information and proposed product information that the user inputs to create proposal materials.

[0561] "Means of receiving" refers to the technology or method by which the system receives information entered by the user.

[0562] "Format and content extraction means" refers to the techniques and methods used to select appropriate format and content from the database.

[0563] "New proposal materials" refers to proposal documents automatically generated by a generative AI model based on user input information and past data.

[0564] "Means for providing" refers to the technology or method for displaying, transmitting, or making accessible the generated proposal materials to the user.

[0565] "Means for reviewing and editing" refers to techniques and methods that allow users to review, correct, and supplement the generated proposal materials.

[0566] "Final edited proposal material" refers to the proposal material that has been checked and corrected as necessary by the user.

[0567] "Means of indexing proposal documents to make them reusable" refers to techniques and methods for adding easily searchable tags and data to proposal documents for future use.

[0568] System Configuration

[0569] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generative AI model, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[0570] Initial settings and database creation

[0571] The server first collects the format and content of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type (e.g., pptx, pdf, docx) and industry (manufacturing, IT, healthcare, etc.), and is structured so that information can be quickly extracted when needed. To do this, the server uses Python's Pandas library to format the data.

[0572] Training generative AI

[0573] The server uses the stored proposal data to train the generative AI model. This training uses machine learning frameworks such as TensorFlow and PyTorch. The specific training procedure involves preprocessing the data, splitting it into a training dataset and a test dataset, and then inputting the data into the generative AI model for training.

[0574] User interaction and data entry

[0575] Users log in to the system via their terminal and enter information to create proposal documents. This input is done using a dedicated form on a web browser. The form is built using HTML5 and JavaScript and includes fields for entering the company name, industry, number of employees, proposed product name, features, price, etc. When the user performs input operations, the data is sent to the server in JSON format.

[0576] Data extraction and proposal generation

[0577] When the server receives the information entered by the user, it searches the database for the appropriate format and content based on that information. This search is performed using an SQL query. For example, to search for manufacturing data, the query "SELECT FROM Proposal Documents WHERE Industry = 'Manufacturing'" is used. Then, based on the search results, a generative AI model is used to generate new proposal documents. The generative AI model generates personalized proposal content based on the user's input, including instructions provided by the prompt.

[0578] Specific examples

[0579] Prompt: "Write a proposal for ERP software for a 500-person manufacturing company."

[0580] Review and edit proposal materials

[0581] The device provides the generated proposal documents to the user, who then reviews them using an interface on the device. This interface was designed using JavaScript and React, allowing the user to make real-time edits to the proposal documents. For example, they can add information about specific features of the proposed software or edit existing information.

[0582] Saving proposal materials

[0583] The final edited proposal document is sent from the device to the server and saved in a database. This saving process also stores metadata, including the file name and the date and time of saving. The server uses the Python Django framework to save the proposal document and its metadata in a database, using MySQL or PostgreSQL. After saving, the document is indexed so that other sales representatives can reuse it in the future.

[0584] This enables the system to help sales representatives create efficient, high-quality proposal materials, improving overall sales performance.

[0585] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0586] Step 1:

[0587] The server collects the format and content of past proposal documents and stores them in a database. During this process, the server uses the Python Pandas library to format the collected proposal documents into the appropriate format.

[0588] Input: Previously used proposal materials

[0589] Data processing: Use Pandas to format the data and categorize it by format.

[0590] Output: Formatted proposal data stored in a database

[0591] Step 2:

[0592] The server uses the proposal data stored in the database to train the generative AI model, using machine learning frameworks such as TensorFlow and PyTorch, which involves steps of preprocessing, data partitioning, and model training.

[0593] Input: Proposal data in the database

[0594] Data Computing: Preprocessing and model training using TensorFlow and PyTorch

[0595] Output: A trained generative AI model

[0596] Step 3:

[0597] Users log in to the system via their terminal and enter information to create proposal documents. The input form is built using HTML5 and JavaScript, and users enter information such as company name, industry, number of employees, proposed product name, features, and price.

[0598] Input: Company name, industry, number of employees, product information to be proposed, etc.

[0599] Data processing: Convert input information into JSON format and send it to the server

[0600] Output: User input data received from server in JSON format

[0601] Step 4:

[0602] The server uses the received user input to extract the appropriate format and content from the database, using SQL queries to quickly retrieve the relevant data.

[0603] Input: User input information in JSON format

[0604] Data Search: Use SQL queries to find the right format and content

[0605] Output: Extracted format and content

[0606] Step 5:

[0607] The server generates new proposal documents using a generative AI model based on the extracted format and content. This generation process involves inputting prompts containing user input information into the generative AI model.

[0608] Input: Extracted format and content, user-entered information

[0609] Data computation: Generative AI models are fed with user information and prompts to generate new proposals.

[0610] Output: The new proposal that was generated

[0611] Step 6:

[0612] The device provides the generated proposal documents to the user, who can then review and edit them as needed using the device's interface, which is built with JavaScript and React.

[0613] Input: Generated new proposal

[0614] Behavior: Displays material to the user and provides an editing interface

[0615] Output: User-reviewed and edited proposal

[0616] Step 7:

[0617] The user checks and edits the proposal material to finalize it, and the terminal transmits the edited proposal material to the server.

[0618] Input: Generated proposal, user modifications

[0619] Data processing: Creating the final proposal document reflecting the user's modifications

[0620] Output: Final edited proposal

[0621] Step 8:

[0622] The server then stores the final edited proposal in a database, indexes it, and makes it reusable, along with metadata such as the file name and the date and time it was saved.

[0623] Input: Final edited proposal

[0624] Data storage: Stored in database and indexed

[0625] Output: Final proposal and index stored in database

[0626] (Application example 1)

[0627] 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."

[0628] Conventional proposal generation systems do not necessarily enable sales representatives to efficiently create proposal materials for corporate customers. Real-time data collection and analysis is particularly important for in-factory production planning and parts procurement proposals, but this requires a lot of manual work, which takes time and effort. This can lead to insufficient optimization of production lines and cost reductions. Furthermore, because the quality of proposal materials depends on the experience and skills of sales representatives, it is difficult to maintain consistent quality.

[0629] 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.

[0630] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generation AI based on the format and content of the proposal materials, means for receiving information input by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generation AI based on the extracted format and content, means for machines operating in a factory to collect production data in real time and generate proposal materials related to parts shortages and production plan optimization, means for providing the generated proposal materials to a user, means for the user to review and edit the provided proposal materials, and means for saving the final edited proposal materials in a database. This makes it possible to utilize real-time data for in-factory production plans and parts procurement proposals, and to automatically generate high-quality proposal materials quickly and efficiently.

[0631] A "proposal document" is a document that summarizes the details of the products or services that are proposed to corporate clients.

[0632] A "database" is a collection of electronic data that is structured to store information systematically and make it easy to search and retrieve.

[0633] "Generative AI" is a system or program that uses artificial intelligence technology to automatically generate new information or documents.

[0634] "User" means an individual or company employee who uses the system to create and edit proposal materials.

[0635] "Format" refers to the layout and structure of the proposal materials, specifically including the placement of text and design elements.

[0636] "Content" refers to the specific information in the documents and data contained in the proposal materials, including product features, prices, implementation examples, etc.

[0637] An "interface" is a screen or tool that allows a user to interact with a system and facilitates the input and editing of information.

[0638] "Real-time data" refers to data collected in real time by machines and sensors operating within a factory to determine the current situation.

[0639] "Production planning" refers to the product manufacturing schedule and resource allocation plan in a factory.

[0640] "Parts shortage" refers to a situation where a necessary part is not available on the production line.

[0641] This invention relates to a system that works in conjunction with machines operating in a factory and uses real-time data to automatically generate proposal materials related to parts shortages and optimization of production plans. The system includes the following elements:

[0642] 1. Database construction:

[0643] The server collects the format and content of past proposal documents and stores them in a database. This database is categorized based on the format and content of the proposal documents and is structured to allow for quick extraction of relevant information.

[0644] 2. Training the generative AI:

[0645] The server uses the proposal data stored in the database to train a generative AI model, which has the ability to automatically generate new proposals with high accuracy.

[0646] 3. Data Collection:

[0647] Machines operating in factories collect production data in real time, including machine operation status, parts consumption, and inventory status.

[0648] 4. User Input:

[0649] Users access the system through a terminal and input basic information about the corporate customer and information about the product they wish to propose. This can be done easily using the interface.

[0650] 5. Data extraction and proposal generation:

[0651] The server integrates user-entered information with real-time production data, extracts the appropriate format and content from the database, and then uses generative AI to generate new proposal materials based on the extracted information.

[0652] 6. Proposal materials provision and editing:

[0653] The generated proposal material is provided to the user, who can use an interface to check the material through a terminal and edit the content as necessary.

[0654] 7. Save the Final Version:

[0655] The final proposal document edited by the user is sent back to the server and saved in the database, allowing other users to reuse the new proposal document.

[0656] Hardware and Software Used

[0657] Hardware:

[0658] Machines operating in factories (production machines with sensors)

[0659] Servers (requiring high performance computing)

[0660] User devices (smartphones, tablets, computers)

[0661] software:

[0662] Deep learning frameworks (e.g., Keras)

[0663] Database Management Systems

[0664] User interface tools (web or mobile app)

[0665] Specific examples

[0666] In a factory, the following prompts can be used:

[0667] Prompt Sentence Examples

[0668] Based on the information below, please create next week's production plan and parts procurement proposal materials.

[0669] Customer name: Manufacturing A

[0670] Industry: Auto parts manufacturing

[0671] Number of employees: 1,200

[0672] Production planning data: [List data here]

[0673] Product name: New engine parts

[0674] Features: Lightweight, high strength

[0675] Price: 5,000 yen / piece

[0676] This system allows factory managers to utilize real-time data to quickly and efficiently create production plans and automatically generate parts procurement proposals, thereby improving production efficiency and reducing costs.

[0677] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0678] Step 1:

[0679] The server collects the format and content of proposal documents used in the past and stores them in a database. Specifically, the server collects existing proposal documents as electronic data and stores them in a database. In the database, this data is structured so that it is categorized based on industry and format. The input is the past proposal document data, and the output is a structured database.

[0680] Step 2:

[0681] The server trains the generative AI model using proposal data stored in the database. The server extracts the format and content of proposal documents from the database and supplies them to the generative AI model to train the model. The input is the proposal data extracted from the database, and the output is the trained generative AI model.

[0682] Step 3:

[0683] Machines operating in a factory collect production data in real time. This data is obtained from the machine's sensors and is related to the operating status, parts consumption, and inventory status. This data is sent to a server. The input is the real-time data from the machine's sensors, and the output is the production data sent to the server.

[0684] Step 4:

[0685] The user uses a terminal to input basic information about the corporate customer and information about the product they are proposing. The user inputs this information through a dedicated interface, and the terminal sends the information to the server. The input is the corporate customer information and product information entered by the user, and the output is the information sent to the server.

[0686] Step 5:

[0687] The server integrates the information entered by the user with real-time production data and extracts the appropriate format and content from the database. The server processes the data as needed based on this information and reconstructs the appropriate data. The input is the information entered by the user and real-time production data, and the output is the extracted format and content.

[0688] Step 6:

[0689] The server generates new proposal materials using the generative AI model. The server inputs the extracted format and content into the generative AI model and automatically generates new proposal materials. The input is the extracted format and content, and the output is the generated new proposal materials.

[0690] Step 7:

[0691] The generated proposal materials are provided to the user. The server sends the generated proposal materials to the terminal, where the user can review and edit them. The input is the generated proposal materials, and the output is the user's review and editing.

[0692] Step 8:

[0693] The user submits the final edited proposal to the server, which stores it in a database. The server indexes the new proposal so that it can be reused by other users in the future. The input is the final edited proposal by the user, and the output is the proposal stored in the database.

[0694] 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.

[0695] System Configuration

[0696] The system of the present invention includes a server, a terminal, a user interface, a database, and an emotion engine. The server is responsible for storing data, training the generative AI, extracting information, generating proposal materials, and processing emotion data. The terminal provides an interface for users to interact with the system and input and edit information. Users are responsible for creating and editing proposal materials for corporate clients. The emotion engine recognizes user emotions and reflects that information in the generation of proposal materials.

[0697] Initial settings and database creation

[0698] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[0699] Training generative AI

[0700] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0701] User interaction and data entry

[0702] Users access the system through their terminals and input information to create proposal materials. Specifically, users enter basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price) into the interface. At this time, the emotion engine recognizes the user's emotions and collects emotion data.

[0703] Receiving and analyzing information

[0704] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[0705] Format and content extraction

[0706] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[0707] Proposal generation

[0708] The server uses the extracted format and content to run the generative AI to generate new proposal materials. At this time, the emotion engine adjusts the content and tone of the materials based on the user's emotional data collected. For example, if the user is expressing positive emotions, the proposal materials will reflect a positive tone.

[0709] Providing proposal materials

[0710] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[0711] Review and edit proposal materials

[0712] The user can review the provided proposal materials on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requests. The emotion engine also continuously monitors changes in the user's emotions and reflects them in the editing process.

[0713] Finalize and send

[0714] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[0715] Saving proposal materials

[0716] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[0717] Specific examples

[0718] User operation example

[0719] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[0720] System working example

[0721] The server analyzes the input information and emotion data, and selects the appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document.

[0722] The generated proposal is then provided to the user via their device, who can review it and fine-tune it to suit the client's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the proposal as needed.

[0723] The final edited proposal document is sent to the server and stored in the database, where other sales representatives can use it as a reference when creating their own proposal documents.

[0724] The present invention makes it possible to efficiently create high-quality proposal materials that take into account the emotional state of the user, thereby improving overall sales capabilities.

[0725] The processing flow will be explained below.

[0726] Step 1: Building the database

[0727] The server collects the format and content of past proposal documents, structures them, and stores them in a database. This database is categorized by the industry and category of the proposal, allowing for quick search and retrieval of information.

[0728] Step 2: Training the generative AI

[0729] The server trains the AI ​​using the proposal data stored in the database. The trained AI can then generate optimal proposals with high accuracy based on new information entered by the user.

[0730] Step 3: User Login and Data Entry

[0731] The user logs in to the system using a terminal, and then enters basic information about the corporate client (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) through an interface for creating proposal materials.

[0732] Step 4: Emotion Recognition with the Emotion Engine

[0733] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotional state, and this emotional data is reflected in the creation of proposal materials.

[0734] Step 5: Receiving and analyzing information

[0735] The server receives and analyzes the basic information, product information, and emotion data sent by the user. Based on the analysis results, it prepares to search for related data in the database.

[0736] Step 6: Extracting format and content

[0737] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it extracts the proposal format and related content for the manufacturing industry.

[0738] Step 7: Generate a proposal

[0739] The server uses the extracted format and content to run a generative AI to generate a new proposal. At this stage, emotional data from the emotion engine is also incorporated, and the proposal incorporates a tone and style that reflects the user's emotional state.

[0740] Step 8: Submit your proposal

[0741] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user has the opportunity to review the proposal and fine-tune its content.

[0742] Step 9: Review and edit your proposal

[0743] The user reviews the proposal displayed on their device in detail. They then use the interface to edit the content of the proposal, making any necessary corrections or adding additional information. While editing, the emotion engine continues to monitor the user's emotional state and optimizes the tone and style of the proposal.

[0744] Step 10: Finalize and submit

[0745] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the completed proposal document is sent to the server.

[0746] Step 11: Save your proposal

[0747] The server saves the final proposal documents it receives in a database, where they are indexed and stored for future reference by other sales representatives.

[0748] The above steps realize a process for creating proposal materials that utilizes an emotion engine, making it possible to generate high-quality materials that take into account the user's emotional state.

[0749] Example 2

[0750] 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."

[0751] Conventional systems for creating proposal materials were unable to effectively utilize past data and had difficulty automatically generating proposal materials that reflected user emotions. In particular, reading user emotions and creating materials that reflected them had to be done manually, which was inefficient. Furthermore, the content of proposal materials was uniform and lacked customization for individual customers, resulting in a low success rate for proposals. A new system that solves these problems is needed.

[0752] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing the format and content of proposal materials used in the past in a database, a means for training the generation AI based on the format and content of the proposal materials, and a means for recognizing the user's emotions and reflecting the data in the proposal materials. This makes it possible to quickly and efficiently generate customized proposal materials that reflect the user's emotions while effectively utilizing past data.

[0753] The "database" is a collection of information that stores the format and content of proposal materials used in the past and is categorized by industry and category.

[0754] "Generative AI" is an artificial intelligence that is trained based on proposal document data in a database and automatically generates new proposal documents using input information and emotional data from users.

[0755] A "user" is an entity that inputs information into the system to create proposal materials, and checks and edits the generated proposal materials.

[0756] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions and tone of voice, and reflects that data in the content and tone of proposal materials.

[0757] A "terminal" is a device through which a user accesses the system and enters and edits information.

[0758] A "proposal document" is a document that summarizes the content of a proposal to a corporate client, and is automatically generated by generation AI.

[0759] "Format" refers to the structure and layout of a proposal document, and is suitable for a particular industry or purpose.

[0760] "Information extraction" is the process of searching and retrieving the required format and content from within a database.

[0761] "Emotion data" is data that represents the emotional state obtained by the emotion engine from the user's facial expression and voice.

[0762] MODE FOR CARRYING OUT THE INVENTION

[0763] The present invention is a system that includes a server, a terminal, a user interface, a database, and an emotion engine. Here, the role of each component and its specific operation will be explained.

[0764] 1. Server configuration and operation

[0765] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for fast and efficient information retrieval.

[0766] The generative AI is trained using data stored in the database, using open-source machine learning frameworks (e.g., TensorFlow, PyTorch).

[0767] The server receives the information and emotion data sent by the user, analyzes them, and based on the analysis results, searches and extracts relevant data from the database.

[0768] The server inputs the extracted format and content into the generation AI to generate new proposal materials, adjusting the content and tone of the proposal materials based on the user's emotional data recognized by the emotion engine.

[0769] 2. Terminal configuration and operation

[0770] The terminal provides an interface for users to interact with the system and input information. This interface is implemented using HTML and JavaScript, and allows users to enter basic information about corporate customers and details of the products they are proposing.

[0771] The terminal provides the generated proposal material to the user, who can then check the material and edit it as necessary.

[0772] The terminal has the function of sending the proposal document that the user has completed editing to the server, where it is analyzed again for final confirmation and saved in the database.

[0773] 3. User Operation

[0774] Users access the system through a terminal and input information to create proposal materials. Specifically, they input basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price).

[0775] The emotion engine recognizes emotions from the user's facial expressions and tone of voice and collects this emotion data.

[0776] 4. Emotion Engine

[0777] The emotion engine recognizes the user's emotions and reflects that data in the proposal materials. Specifically, if the user shows positive emotions, the proposal materials will reflect a positive tone.

[0778] Specific examples

[0779] Example of user action:

[0780] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[0781] Example of a working system:

[0782] The server analyzes the input information and emotion data and selects an appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document. The generated proposal document is provided to the user via their device, who reviews it and fine-tunes it to suit the customer's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the document as needed. The final edited proposal document is sent to the server and stored in a database. Other sales representatives can use this document as a reference when creating their own proposal documents.

[0783] Prompt Sentence Examples

[0784] Company Information: Smart Tech Co., Ltd.

[0785] Industry: Manufacturing

[0786] Size: Medium-sized company

[0787] Proposed product: ERP software

[0788] Product features: Integrated management, automation, real-time analysis

[0789] Price: 1 million yen for a yearly contract

[0790] This makes it possible to efficiently create high-quality proposal materials that take into account the user's emotional state, thereby improving overall sales capabilities.

[0791] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0792] Step 1:

[0793] The server collects past proposal materials and stores them in a database.

[0794] Input: Previously used proposal materials (PDF, Word, etc.)

[0795] Processing: Analyze the format and content of the documents, then classify and store them in a database. Specifically, extract text data from the documents and organize them by industry and category.

[0796] Output: A database containing classified proposals

[0797] Step 2:

[0798] The server trains the generative AI using proposal data in the database.

[0799] Input: Text data of proposal documents stored in a database

[0800] Processing: Use machine learning frameworks (e.g., TensorFlow, PyTorch) to train generative AI on the format and content of the proposal.

[0801] Output: A trained generative AI model

[0802] Step 3:

[0803] A user accesses the system through a terminal and inputs information to create a proposal document.

[0804] Input: Basic information about the corporate customer (company name, industry, size) and information about the proposed product (product name, features, price)

[0805] Processing: Collect input data using an information input interface (HTML, JavaScript).

[0806] Output: User input data

[0807] Step 4:

[0808] The emotion engine recognizes the user's emotions and collects that data.

[0809] Input: User's facial expression, tone of voice

[0810] Processing: Emotion recognition algorithms are used to analyze facial expressions and vocal tones.

[0811] Output: Emotion data

[0812] Step 5:

[0813] The server receives the information and emotion data sent by the user and analyzes them.

[0814] Input: User input data, emotion data

[0815] Processing: Analysis algorithms are used to check the consistency of the input data with the sentiment data and extract relevant data.

[0816] Output: Parsed input data and emotion data

[0817] Step 6:

[0818] Based on the analysis results, the server extracts the appropriate format and relevant content from the database.

[0819] Input: Parsed input data and emotion data

[0820] Processing: Using database search algorithms, we extract the most appropriate format and relevant content, for example, selecting the suggested format and content for the manufacturing industry.

[0821] Output: Extracted format and content

[0822] Step 7:

[0823] The server uses the extracted format and content to run a generative AI to generate new proposal materials.

[0824] Input: Extracted format, content, and sentiment data

[0825] Processing: Run the generative AI model to generate a pitch deck, adjusting the tone and content of the deck based on the sentiment data.

[0826] Output: Generated proposal

[0827] Step 8:

[0828] The server temporarily stores the generated proposal materials and provides them to the user through the terminal.

[0829] Input: Generated proposal

[0830] Processing: The proposal materials are temporarily stored and prepared for transmission to the user via the terminal.

[0831] Output: Proposal document ready for user review

[0832] Step 9:

[0833] The user checks the provided proposal materials on the terminal and makes any necessary corrections or additions using the interface.

[0834] Input: Generated proposal

[0835] Processing: The user reviews the proposal and makes corrections or additions via the user interface. The emotion engine also monitors changes in emotion during editing.

[0836] Output: Edited proposal

[0837] Step 10:

[0838] The user completes the edits and finalizes the proposal.

[0839] Input: Edited proposal

[0840] Processing: By pressing the Confirm button, the proposal materials are sent to the server.

[0841] Output: Final, confirmed proposal

[0842] Step 11:

[0843] The server stores the received final proposal document in a database.

[0844] Input: Final, confirmed proposal

[0845] Processing: Store in a database and index for future reference when creating proposals.

[0846] Output: Saved proposal

[0847] (Application example 2)

[0848] 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."

[0849] Conventional proposal material creation systems do not take into account the user's emotional state, resulting in problems with the materials provided not being in line with the user's emotions or situation. Furthermore, when personalizing the purchasing experience in a virtual store, there was a lack of a mechanism to respond to the user's real-time emotional changes. This made it difficult to effectively improve the user's purchasing motivation and satisfaction.

[0850] 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.

[0851] In this invention, the server includes means for storing the format and content of previously used proposals in a database, means for training a generation AI based on the format and content of the proposals, means for receiving information entered by a user for creating a proposal, means for extracting appropriate formats and content from the database based on the received information, means for generating a new proposal using the generation AI based on the extracted format and content, means for providing the generated proposal to the user, means for the user to review and edit the provided proposal, means for saving the final edited proposal in the database, means for analyzing the user's emotions in real time using an emotion recognition engine, and means for adjusting the content and tone of the proposal based on the user's emotional state, thereby making it possible to provide proposal materials and purchasing experiences that reflect the user's emotions.

[0852] "Proposal format" refers to the layout and structure of documents such as proposals and reports, and is a template or format that improves the readability of the content and the ease with which information is conveyed.

[0853] "Proposal content" refers to text or data containing detailed information about a specific proposal or project, and is an element that explains the key points and advantages of a specific proposal.

[0854] A "database" is a structured collection of data, a system that allows for efficient information storage, management, and retrieval.

[0855] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to automatically generate new data and documents, for example, to create proposals and reports.

[0856] "User" refers to the entity that uses this system to create, edit, and check proposals, and in most cases is a corporate sales representative or presentation person.

[0857] An "emotion recognition engine" is a system that automatically analyzes and recognizes emotions from a user's facial expressions and voice, and is a technology that optimizes the system's operation based on that information.

[0858] "Proposal tone adjustment" is the process of adapting the presentation and wording of a proposal's content to suit the user's emotional state.

[0859] A "personalized shopping experience" is a method for increasing user satisfaction by providing a shopping experience that is customized based on the preferences, needs, and emotions of each individual user.

[0860] The present invention provides a system for generating a new proposal based on the format and content of an existing proposal, and for adjusting the content and tone of the proposal depending on the user's emotional state. A specific embodiment of this system is described below.

[0861] System Configuration

[0862] The system includes a server, a terminal, a user interface, a database, and an emotion recognition engine. The server is responsible for storing data, training the generative AI, extracting information, and generating proposals. The emotion recognition engine recognizes users' emotions and reflects that information in the generation and adjustment of proposals.

[0863] Initial settings and database creation

[0864] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[0865] Training generative AI

[0866] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0867] User interaction and data entry

[0868] Users access the system through their terminals and input information to create proposals. Specifically, users enter basic information about the corporate client (company name, industry, size) and information about the product they are proposing (product name, features, price) into the interface. At this time, an emotion recognition engine recognizes the user's emotions and collects data.

[0869] Receiving and analyzing information

[0870] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[0871] Format and content extraction

[0872] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user proposes ERP software to a manufacturing customer, the server extracts the proposal format and related content for the manufacturing industry.

[0873] Proposal generation

[0874] The server uses the extracted format and content to run a generative AI to generate a new proposal. The emotion recognition engine then adjusts the content and tone of the proposal based on the user's emotional data collected. For example, if the user expresses positive emotions, the proposal will reflect a positive tone.

[0875] Proposal submission

[0876] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[0877] Review and edit the proposal

[0878] The user can review the provided proposal on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requirements. The emotion recognition engine also continuously monitors the user's emotional changes and reflects them in the editing process.

[0879] Finalize and send

[0880] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[0881] Save the proposal

[0882] The server stores the final proposal it receives in a database, where it indexes the proposal so that other sales representatives can refer to it when creating future proposals.

[0883] Hardware and software used

[0884] Facial Recognition Camera: Commonly Used Webcam

[0885] Smart glasses or head-mounted displays (HMDs): For example, Oculus Quest 2

[0886] Emotion Recognition: Pipeline Methods in the Transformers Library

[0887] VR Interface: Virtual 3D VR Library

[0888] Specific examples

[0889] A user visits a virtual store and puts on smart glasses. The system analyzes the user's facial expressions and voice, and if the user appears happy, it will proactively suggest products (e.g., new or popular items). On the other hand, if the user appears tired, it will suggest relaxation goods. This personalizes the user's shopping experience and increases satisfaction.

[0890] Example prompts to input to the generative AI model

[0891] "If the user is feeling relaxed, suggest products that will help them relax."

[0892] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0893] Processing Steps

[0894] Step 1:

[0895] Initial settings and database creation

[0896] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick information retrieval.

[0897] Input: Past proposal data

[0898] Output: A structured database

[0899] Step 2:

[0900] Training generative AI

[0901] The server uses the proposal data in the database to train the generative AI model, giving it the ability to adapt to new situations and generate high-quality proposals.

[0902] Input: Proposal data in the database

[0903] Output: A trained generative AI model

[0904] Step 3:

[0905] User interaction and data entry

[0906] Users access the system using a terminal and enter basic information (company name, industry, size) and details of the proposed product (product name, features, price) to create a proposal. At this time, the emotion recognition engine analyzes the user's emotions in real time and collects data.

[0907] Input: User's basic information, item information, facial expressions and voice data

[0908] Output: User input information and emotion data

[0909] Step 4:

[0910] Receiving and analyzing information

[0911] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data from the database based on the analysis results.

[0912] Input: User input information, emotion data

[0913] Output: Analysis results, search criteria

[0914] Step 5:

[0915] Format and content extraction

[0916] Based on the analysis results, the server extracts the appropriate format and content from the database, for example, selecting a proposal format for the manufacturing industry and related content.

[0917] Input: Analysis results, database

[0918] Output: appropriate format and content

[0919] Step 6:

[0920] Proposal generation

[0921] The server uses the extracted format and content to run a generative AI to generate a new proposal, adjusting the tone and content of the proposal based on the user's emotional data collected by the emotion recognition engine.

[0922] Input: Extracted format, content, and sentiment data

[0923] Output: New proposal

[0924] Step 7:

[0925] Proposal submission

[0926] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[0927] Enter: New Proposal

[0928] Output: Temporarily save the proposal and provide it to the user

[0929] Step 8:

[0930] Review and edit the proposal

[0931] The user can use the device to check the proposal and make any necessary corrections or additions. The emotion recognition engine monitors the user's emotional changes and reflects them in the editing process.

[0932] Input: Proposal, edits, sentiment data

[0933] Output: Revised and added proposal

[0934] Step 9:

[0935] Finalize and send

[0936] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[0937] Input: Final edited proposal

[0938] Output: Send the final proposal to the server

[0939] Step 10:

[0940] Save the proposal

[0941] The server stores the final proposals it receives in a database and indexes them for future reference.

[0942] Input: Final proposal

[0943] Output: Stored in database, indexed

[0944] 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.

[0945] 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.

[0946] 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.

[0947] [Third embodiment]

[0948] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0949] 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.

[0950] 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).

[0951] 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.

[0952] 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.

[0953] 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).

[0954] 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.

[0955] 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.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] 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."

[0960] System Configuration

[0961] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generation AI, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[0962] Initial settings and database creation

[0963] The server first collects the formats and contents of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type and industry, and is structured so that information can be quickly extracted when needed.

[0964] Training generative AI

[0965] The server trains the generative AI using the proposal data stored in the database. The trained generative AI is then able to generate new proposals with high accuracy.

[0966] User interaction and data entry

[0967] Users access the system through a terminal and input information to create new proposal materials. Specifically, users use an interface to enter basic information about corporate clients (e.g., company name, industry, size) and information about the products they are proposing (e.g., product name, features, price).

[0968] Data extraction and proposal generation

[0969] When the server receives the information entered by the user, it searches and extracts the appropriate format and relevant content from the database. Based on the extracted data, it uses generative AI to generate a new proposal document. This generated proposal document is structured based on the selected format and includes the specific information requested by the user.

[0970] Review and edit proposal materials

[0971] The terminal provides the generated proposal materials to the user. The user uses an interface to check the displayed proposal materials and edit the content as necessary. The user can adjust the content of the materials appropriately and finalize them.

[0972] Saving proposal materials

[0973] The final edited proposal is sent from the device to a server and saved in a database, where the server indexes and stores the new proposal for future reuse by other users.

[0974] Specific examples

[0975] User operation example

[0976] When a salesperson creates a proposal document for a new corporate client, the salesperson logs into the system and enters basic information about the client and details of the products they are proposing.

[0977] For example, suppose the client is a manufacturing company with 500 employees and the proposed product is new ERP software.

[0978] System working example

[0979] The server receives the input information and selects the appropriate format from past proposal documents for the manufacturing industry.

[0980] Based on the selected format, the server uses trained generative AI to generate new proposal materials.

[0981] For example, the proposal document includes trends in the manufacturing industry, the benefits of ERP software, and past implementation examples.

[0982] Review and edit

[0983] The generated proposal is provided to the user via a terminal, who can review the proposal and make modifications to suit their specific needs.

[0984] For example, adding customized solutions to proposals based on specific customer requirements.

[0985] Save and reuse

[0986] The final proposal is sent to a server and stored in a database, which indexes and stores the new proposal for future use by other salespeople.

[0987] This system enables all sales representatives to efficiently create high-quality proposal materials, improving overall sales capabilities.

[0988] The processing flow will be explained below.

[0989] Step 1: Building the database

[0990] The server collects the format and content of previously used proposal documents, structures them, and stores them in a database that is categorized by industry and category, allowing for quick search and retrieval of information.

[0991] Step 2: Training the generative AI

[0992] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[0993] Step 3: User login and input

[0994] The user logs into the system through a terminal and enters basic information about the corporate customer (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) into the interface, which is necessary to create a proposal document.

[0995] Step 4: Receiving and analyzing information

[0996] The server receives the information sent by the user, analyzes it, and prepares to search for related data in the database based on the analysis results.

[0997] Step 5: Extracting format and content

[0998] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[0999] Step 6: Generate a proposal

[1000] The server uses the extracted format and content to run a generative AI to generate new proposals, which are customized based on the information provided by the user.

[1001] Step 7: Submit your proposal

[1002] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[1003] Step 8: Review and edit your proposal

[1004] The user can review the provided proposal materials on their device and use the interface to make any necessary corrections or additions, for example, to tailor the content to meet the specific needs of the client.

[1005] Step 9: Finalize and submit

[1006] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[1007] Step 10: Save your proposal

[1008] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[1009] The above steps create a system that enables sales representatives to efficiently create high-quality proposal materials.

[1010] Example 1

[1011] 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."

[1012] The traditional proposal document creation process had problems with high quality variation and low efficiency because each sales representative created their own documents. Furthermore, there was often no database to utilize past success stories, making it difficult to share know-how. Furthermore, creating new documents took time and effort, making it difficult to respond quickly when a quick response was required.

[1013] 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.

[1014] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generative AI model based on the format and content of the proposal materials, means for receiving information entered by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generative AI model based on the extracted format and content, means for providing the generated proposal materials to the user, means for the user to review and edit the provided proposal materials, means for saving the final edited proposal materials in the database, and means for indexing the proposal materials to make them reusable. This enables consistent and rapid creation of high-quality proposal materials, thereby realizing the sharing of know-how and improved business efficiency.

[1015] "Previously used proposal materials" are materials that contain proposal content and formats that have already been used in practice.

[1016] "Format" refers to the layout, format, design, and general components of the proposal.

[1017] "Content" refers to the specific information, data, examples, and explanatory text contained in the proposal materials.

[1018] A "database" is a system that can efficiently store, manage, search, and update structured data.

[1019] A "generative AI model" refers to an artificial intelligence algorithm that learns from input data and automatically generates new proposal materials.

[1020] "User" refers to a person who uses the system to create, review, and edit proposal materials.

[1021] "Information" refers to data such as basic customer information and proposed product information that the user inputs to create proposal materials.

[1022] "Means of receiving" refers to the technology or method by which the system receives information entered by the user.

[1023] "Format and content extraction means" refers to the techniques and methods used to select appropriate format and content from the database.

[1024] "New proposal materials" refers to proposal documents automatically generated by a generative AI model based on user input information and past data.

[1025] "Means for providing" refers to the technology or method for displaying, transmitting, or making accessible the generated proposal materials to the user.

[1026] "Means for reviewing and editing" refers to techniques and methods that allow users to review, correct, and supplement the generated proposal materials.

[1027] "Final edited proposal material" refers to the proposal material that has been checked and corrected as necessary by the user.

[1028] "Means of indexing proposal documents to make them reusable" refers to techniques and methods for adding easily searchable tags and data to proposal documents for future use.

[1029] System Configuration

[1030] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generative AI model, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[1031] Initial settings and database creation

[1032] The server first collects the format and content of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type (e.g., pptx, pdf, docx) and industry (manufacturing, IT, healthcare, etc.), and is structured so that information can be quickly extracted when needed. To do this, the server uses Python's Pandas library to format the data.

[1033] Training generative AI

[1034] The server uses the stored proposal data to train the generative AI model. This training uses machine learning frameworks such as TensorFlow and PyTorch. The specific training procedure involves preprocessing the data, splitting it into a training dataset and a test dataset, and then inputting the data into the generative AI model for training.

[1035] User interaction and data entry

[1036] Users log in to the system via their terminal and enter information to create proposal documents. This input is done using a dedicated form on a web browser. The form is built using HTML5 and JavaScript and includes fields for entering the company name, industry, number of employees, proposed product name, features, price, etc. When the user performs input operations, the data is sent to the server in JSON format.

[1037] Data extraction and proposal generation

[1038] When the server receives the information entered by the user, it searches the database for the appropriate format and content based on that information. This search is performed using an SQL query. For example, to search for manufacturing data, the query "SELECT FROM Proposal Documents WHERE Industry = 'Manufacturing'" is used. Then, based on the search results, a generative AI model is used to generate new proposal documents. The generative AI model generates personalized proposal content based on the user's input, including instructions provided by the prompt.

[1039] Specific examples

[1040] Prompt: "Write a proposal for ERP software for a 500-person manufacturing company."

[1041] Review and edit proposal materials

[1042] The device provides the generated proposal documents to the user, who then reviews them using an interface on the device. This interface was designed using JavaScript and React, allowing the user to make real-time edits to the proposal documents. For example, they can add information about specific features of the proposed software or edit existing information.

[1043] Saving proposal materials

[1044] The final edited proposal document is sent from the device to the server and saved in a database. This saving process also stores metadata, including the file name and the date and time of saving. The server uses the Python Django framework to save the proposal document and its metadata in a database, using MySQL or PostgreSQL. After saving, the document is indexed so that other sales representatives can reuse it in the future.

[1045] This enables the system to help sales representatives create efficient, high-quality proposal materials, improving overall sales performance.

[1046] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1047] Step 1:

[1048] The server collects the format and content of past proposal documents and stores them in a database. During this process, the server uses the Python Pandas library to format the collected proposal documents into the appropriate format.

[1049] Input: Previously used proposal materials

[1050] Data processing: Use Pandas to format the data and categorize it by format.

[1051] Output: Formatted proposal data stored in a database

[1052] Step 2:

[1053] The server uses the proposal data stored in the database to train the generative AI model, using machine learning frameworks such as TensorFlow and PyTorch, which involves steps of preprocessing, data partitioning, and model training.

[1054] Input: Proposal data in the database

[1055] Data Computing: Preprocessing and model training using TensorFlow and PyTorch

[1056] Output: A trained generative AI model

[1057] Step 3:

[1058] Users log in to the system via their terminal and enter information to create proposal documents. The input form is built using HTML5 and JavaScript, and users enter information such as company name, industry, number of employees, proposed product name, features, and price.

[1059] Input: Company name, industry, number of employees, product information to be proposed, etc.

[1060] Data processing: Convert input information into JSON format and send it to the server

[1061] Output: User input data received from server in JSON format

[1062] Step 4:

[1063] The server uses the received user input to extract the appropriate format and content from the database, using SQL queries to quickly retrieve the relevant data.

[1064] Input: User input information in JSON format

[1065] Data Search: Use SQL queries to find the right format and content

[1066] Output: Extracted format and content

[1067] Step 5:

[1068] The server generates new proposal documents using a generative AI model based on the extracted format and content. This generation process involves inputting prompts containing user input information into the generative AI model.

[1069] Input: Extracted format and content, user-entered information

[1070] Data computation: Generative AI models are fed with user information and prompts to generate new proposals.

[1071] Output: The new proposal that was generated

[1072] Step 6:

[1073] The device provides the generated proposal documents to the user, who can then review and edit them as needed using the device's interface, which is built with JavaScript and React.

[1074] Input: Generated new proposal

[1075] Behavior: Displays material to the user and provides an editing interface

[1076] Output: User-reviewed and edited proposal

[1077] Step 7:

[1078] The user checks and edits the proposal material to finalize it, and the terminal transmits the edited proposal material to the server.

[1079] Input: Generated proposal, user modifications

[1080] Data processing: Creating the final proposal document reflecting the user's modifications

[1081] Output: Final edited proposal

[1082] Step 8:

[1083] The server then stores the final edited proposal in a database, indexes it, and makes it reusable, along with metadata such as the file name and the date and time it was saved.

[1084] Input: Final edited proposal

[1085] Data storage: Stored in database and indexed

[1086] Output: Final proposal and index stored in database

[1087] (Application example 1)

[1088] 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."

[1089] Conventional proposal generation systems do not necessarily enable sales representatives to efficiently create proposal materials for corporate customers. Real-time data collection and analysis is particularly important for in-factory production planning and parts procurement proposals, but this requires a lot of manual work, which takes time and effort. This can lead to insufficient optimization of production lines and cost reductions. Furthermore, because the quality of proposal materials depends on the experience and skills of sales representatives, it is difficult to maintain consistent quality.

[1090] 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.

[1091] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generation AI based on the format and content of the proposal materials, means for receiving information input by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generation AI based on the extracted format and content, means for machines operating in a factory to collect production data in real time and generate proposal materials related to parts shortages and production plan optimization, means for providing the generated proposal materials to a user, means for the user to review and edit the provided proposal materials, and means for saving the final edited proposal materials in a database. This makes it possible to utilize real-time data for in-factory production plans and parts procurement proposals, and to automatically generate high-quality proposal materials quickly and efficiently.

[1092] A "proposal document" is a document that summarizes the details of the products or services that are proposed to corporate clients.

[1093] A "database" is a collection of electronic data that is structured to store information systematically and make it easy to search and retrieve.

[1094] "Generative AI" is a system or program that uses artificial intelligence technology to automatically generate new information or documents.

[1095] "User" means an individual or company employee who uses the system to create and edit proposal materials.

[1096] "Format" refers to the layout and structure of the proposal materials, specifically including the placement of text and design elements.

[1097] "Content" refers to the specific information in the documents and data contained in the proposal materials, including product features, prices, implementation examples, etc.

[1098] An "interface" is a screen or tool that allows a user to interact with a system and facilitates the input and editing of information.

[1099] "Real-time data" refers to data collected in real time by machines and sensors operating within a factory to determine the current situation.

[1100] "Production planning" refers to the product manufacturing schedule and resource allocation plan in a factory.

[1101] "Parts shortage" refers to a situation where a necessary part is not available on the production line.

[1102] This invention relates to a system that works in conjunction with machines operating in a factory and uses real-time data to automatically generate proposal materials related to parts shortages and optimization of production plans. The system includes the following elements:

[1103] 1. Database construction:

[1104] The server collects the format and content of past proposal documents and stores them in a database. This database is categorized based on the format and content of the proposal documents and is structured to allow for quick extraction of relevant information.

[1105] 2. Training the generative AI:

[1106] The server uses the proposal data stored in the database to train a generative AI model, which has the ability to automatically generate new proposals with high accuracy.

[1107] 3. Data Collection:

[1108] Machines operating in factories collect production data in real time, including machine operation status, parts consumption, and inventory status.

[1109] 4. User Input:

[1110] Users access the system through a terminal and input basic information about the corporate customer and information about the product they wish to propose. This can be done easily using the interface.

[1111] 5. Data extraction and proposal generation:

[1112] The server integrates user-entered information with real-time production data, extracts the appropriate format and content from the database, and then uses generative AI to generate new proposal materials based on the extracted information.

[1113] 6. Proposal materials provision and editing:

[1114] The generated proposal material is provided to the user, who can use an interface to check the material through a terminal and edit the content as necessary.

[1115] 7. Save the Final Version:

[1116] The final proposal document edited by the user is sent back to the server and saved in the database, allowing other users to reuse the new proposal document.

[1117] Hardware and Software Used

[1118] Hardware:

[1119] Machines operating in factories (production machines with sensors)

[1120] Servers (requiring high performance computing)

[1121] User devices (smartphones, tablets, computers)

[1122] software:

[1123] Deep learning frameworks (e.g., Keras)

[1124] Database Management Systems

[1125] User interface tools (web or mobile app)

[1126] Specific examples

[1127] In a factory, the following prompts can be used:

[1128] Prompt Sentence Examples

[1129] Based on the information below, please create next week's production plan and parts procurement proposal materials.

[1130] Customer name: Manufacturing A

[1131] Industry: Auto parts manufacturing

[1132] Number of employees: 1,200

[1133] Production planning data: [List data here]

[1134] Product name: New engine parts

[1135] Features: Lightweight, high strength

[1136] Price: 5,000 yen / piece

[1137] This system allows factory managers to utilize real-time data to quickly and efficiently create production plans and automatically generate parts procurement proposals, thereby improving production efficiency and reducing costs.

[1138] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1139] Step 1:

[1140] The server collects the format and content of proposal documents used in the past and stores them in a database. Specifically, the server collects existing proposal documents as electronic data and stores them in a database. In the database, this data is structured so that it is categorized based on industry and format. The input is the past proposal document data, and the output is a structured database.

[1141] Step 2:

[1142] The server trains the generative AI model using proposal data stored in the database. The server extracts the format and content of proposal documents from the database and supplies them to the generative AI model to train the model. The input is the proposal data extracted from the database, and the output is the trained generative AI model.

[1143] Step 3:

[1144] Machines operating in a factory collect production data in real time. This data is obtained from the machine's sensors and is related to the operating status, parts consumption, and inventory status. This data is sent to a server. The input is the real-time data from the machine's sensors, and the output is the production data sent to the server.

[1145] Step 4:

[1146] The user uses a terminal to input basic information about the corporate customer and information about the product they are proposing. The user inputs this information through a dedicated interface, and the terminal sends the information to the server. The input is the corporate customer information and product information entered by the user, and the output is the information sent to the server.

[1147] Step 5:

[1148] The server integrates the information entered by the user with real-time production data and extracts the appropriate format and content from the database. The server processes the data as needed based on this information and reconstructs the appropriate data. The input is the information entered by the user and real-time production data, and the output is the extracted format and content.

[1149] Step 6:

[1150] The server generates new proposal materials using the generative AI model. The server inputs the extracted format and content into the generative AI model and automatically generates new proposal materials. The input is the extracted format and content, and the output is the generated new proposal materials.

[1151] Step 7:

[1152] The generated proposal materials are provided to the user. The server sends the generated proposal materials to the terminal, where the user can review and edit them. The input is the generated proposal materials, and the output is the user's review and editing.

[1153] Step 8:

[1154] The user submits the final edited proposal to the server, which stores it in a database. The server indexes the new proposal so that it can be reused by other users in the future. The input is the final edited proposal by the user, and the output is the proposal stored in the database.

[1155] 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.

[1156] System Configuration

[1157] The system of the present invention includes a server, a terminal, a user interface, a database, and an emotion engine. The server is responsible for storing data, training the generative AI, extracting information, generating proposal materials, and processing emotion data. The terminal provides an interface for users to interact with the system and input and edit information. Users are responsible for creating and editing proposal materials for corporate clients. The emotion engine recognizes user emotions and reflects that information in the generation of proposal materials.

[1158] Initial settings and database creation

[1159] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[1160] Training generative AI

[1161] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[1162] User interaction and data entry

[1163] Users access the system through their terminals and input information to create proposal materials. Specifically, users enter basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price) into the interface. At this time, the emotion engine recognizes the user's emotions and collects emotion data.

[1164] Receiving and analyzing information

[1165] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[1166] Format and content extraction

[1167] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[1168] Proposal generation

[1169] The server uses the extracted format and content to run the generative AI to generate new proposal materials. At this time, the emotion engine adjusts the content and tone of the materials based on the user's emotional data collected. For example, if the user is expressing positive emotions, the proposal materials will reflect a positive tone.

[1170] Providing proposal materials

[1171] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[1172] Review and edit proposal materials

[1173] The user can review the provided proposal materials on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requests. The emotion engine also continuously monitors changes in the user's emotions and reflects them in the editing process.

[1174] Finalize and send

[1175] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[1176] Saving proposal materials

[1177] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[1178] Specific examples

[1179] User operation example

[1180] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[1181] System working example

[1182] The server analyzes the input information and emotion data, and selects the appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document.

[1183] The generated proposal is then provided to the user via their device, who can review it and fine-tune it to suit the client's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the proposal as needed.

[1184] The final edited proposal document is sent to the server and stored in the database, where other sales representatives can use it as a reference when creating their own proposal documents.

[1185] The present invention makes it possible to efficiently create high-quality proposal materials that take into account the emotional state of the user, thereby improving overall sales capabilities.

[1186] The processing flow will be explained below.

[1187] Step 1: Building the database

[1188] The server collects the format and content of past proposal documents, structures them, and stores them in a database. This database is categorized by the industry and category of the proposal, allowing for quick search and retrieval of information.

[1189] Step 2: Training the generative AI

[1190] The server trains the AI ​​using the proposal data stored in the database. The trained AI can then generate optimal proposals with high accuracy based on new information entered by the user.

[1191] Step 3: User Login and Data Entry

[1192] The user logs in to the system using a terminal, and then enters basic information about the corporate client (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) through an interface for creating proposal materials.

[1193] Step 4: Emotion Recognition with the Emotion Engine

[1194] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotional state, and this emotional data is reflected in the creation of proposal materials.

[1195] Step 5: Receiving and analyzing information

[1196] The server receives and analyzes the basic information, product information, and emotion data sent by the user. Based on the analysis results, it prepares to search for related data in the database.

[1197] Step 6: Extracting format and content

[1198] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it extracts the proposal format and related content for the manufacturing industry.

[1199] Step 7: Generate a proposal

[1200] The server uses the extracted format and content to run a generative AI to generate a new proposal. At this stage, emotional data from the emotion engine is also incorporated, and the proposal incorporates a tone and style that reflects the user's emotional state.

[1201] Step 8: Submit your proposal

[1202] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user has the opportunity to review the proposal and fine-tune its content.

[1203] Step 9: Review and edit your proposal

[1204] The user reviews the proposal displayed on their device in detail. They then use the interface to edit the content of the proposal, making any necessary corrections or adding additional information. While editing, the emotion engine continues to monitor the user's emotional state and optimizes the tone and style of the proposal.

[1205] Step 10: Finalize and submit

[1206] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the completed proposal document is sent to the server.

[1207] Step 11: Save your proposal

[1208] The server saves the final proposal documents it receives in a database, where they are indexed and stored for future reference by other sales representatives.

[1209] The above steps realize a process for creating proposal materials that utilizes an emotion engine, making it possible to generate high-quality materials that take into account the user's emotional state.

[1210] Example 2

[1211] 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."

[1212] Conventional systems for creating proposal materials were unable to effectively utilize past data and had difficulty automatically generating proposal materials that reflected user emotions. In particular, reading user emotions and creating materials that reflected them had to be done manually, which was inefficient. Furthermore, the content of proposal materials was uniform and lacked customization for individual customers, resulting in a low success rate for proposals. A new system that solves these problems is needed.

[1213] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing the format and content of proposal materials used in the past in a database, a means for training the generation AI based on the format and content of the proposal materials, and a means for recognizing the user's emotions and reflecting the data in the proposal materials. This makes it possible to quickly and efficiently generate customized proposal materials that reflect the user's emotions while effectively utilizing past data.

[1214] The "database" is a collection of information that stores the format and content of proposal materials used in the past and is categorized by industry and category.

[1215] "Generative AI" is an artificial intelligence that is trained based on proposal document data in a database and automatically generates new proposal documents using input information and emotional data from users.

[1216] A "user" is an entity that inputs information into the system to create proposal materials, and checks and edits the generated proposal materials.

[1217] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions and tone of voice, and reflects that data in the content and tone of proposal materials.

[1218] A "terminal" is a device through which a user accesses the system and enters and edits information.

[1219] A "proposal document" is a document that summarizes the content of a proposal to a corporate client, and is automatically generated by generation AI.

[1220] "Format" refers to the structure and layout of a proposal document, and is suitable for a particular industry or purpose.

[1221] "Information extraction" is the process of searching and retrieving the required format and content from within a database.

[1222] "Emotion data" is data that represents the emotional state obtained by the emotion engine from the user's facial expression and voice.

[1223] MODE FOR CARRYING OUT THE INVENTION

[1224] The present invention is a system that includes a server, a terminal, a user interface, a database, and an emotion engine. Here, the role of each component and its specific operation will be explained.

[1225] 1. Server configuration and operation

[1226] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for fast and efficient information retrieval.

[1227] The generative AI is trained using data stored in the database, using open-source machine learning frameworks (e.g., TensorFlow, PyTorch).

[1228] The server receives the information and emotion data sent by the user, analyzes them, and based on the analysis results, searches and extracts relevant data from the database.

[1229] The server inputs the extracted format and content into the generation AI to generate new proposal materials, adjusting the content and tone of the proposal materials based on the user's emotional data recognized by the emotion engine.

[1230] 2. Terminal configuration and operation

[1231] The terminal provides an interface for users to interact with the system and input information. This interface is implemented using HTML and JavaScript, and allows users to enter basic information about corporate customers and details of the products they are proposing.

[1232] The terminal provides the generated proposal material to the user, who can then check the material and edit it as necessary.

[1233] The terminal has the function of sending the proposal document that the user has completed editing to the server, where it is analyzed again for final confirmation and saved in the database.

[1234] 3. User Operation

[1235] Users access the system through a terminal and input information to create proposal materials. Specifically, they input basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price).

[1236] The emotion engine recognizes emotions from the user's facial expressions and tone of voice and collects this emotion data.

[1237] 4. Emotion Engine

[1238] The emotion engine recognizes the user's emotions and reflects that data in the proposal materials. Specifically, if the user shows positive emotions, the proposal materials will reflect a positive tone.

[1239] Specific examples

[1240] Example of user action:

[1241] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[1242] Example of a working system:

[1243] The server analyzes the input information and emotion data and selects an appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document. The generated proposal document is provided to the user via their device, who reviews it and fine-tunes it to suit the customer's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the document as needed. The final edited proposal document is sent to the server and stored in a database. Other sales representatives can use this document as a reference when creating their own proposal documents.

[1244] Prompt Sentence Examples

[1245] Company Information: Smart Tech Co., Ltd.

[1246] Industry: Manufacturing

[1247] Size: Medium-sized company

[1248] Proposed product: ERP software

[1249] Product features: Integrated management, automation, real-time analysis

[1250] Price: 1 million yen for a yearly contract

[1251] This makes it possible to efficiently create high-quality proposal materials that take into account the user's emotional state, thereby improving overall sales capabilities.

[1252] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1253] Step 1:

[1254] The server collects past proposal materials and stores them in a database.

[1255] Input: Previously used proposal materials (PDF, Word, etc.)

[1256] Processing: Analyze the format and content of the documents, then classify and store them in a database. Specifically, extract text data from the documents and organize them by industry and category.

[1257] Output: A database containing classified proposals

[1258] Step 2:

[1259] The server trains the generative AI using proposal data in the database.

[1260] Input: Text data of proposal documents stored in a database

[1261] Processing: Use machine learning frameworks (e.g., TensorFlow, PyTorch) to train generative AI on the format and content of the proposal.

[1262] Output: A trained generative AI model

[1263] Step 3:

[1264] A user accesses the system through a terminal and inputs information to create a proposal document.

[1265] Input: Basic information about the corporate customer (company name, industry, size) and information about the proposed product (product name, features, price)

[1266] Processing: Collect input data using an information input interface (HTML, JavaScript).

[1267] Output: User input data

[1268] Step 4:

[1269] The emotion engine recognizes the user's emotions and collects that data.

[1270] Input: User's facial expression, tone of voice

[1271] Processing: Emotion recognition algorithms are used to analyze facial expressions and vocal tones.

[1272] Output: Emotion data

[1273] Step 5:

[1274] The server receives the information and emotion data sent by the user and analyzes them.

[1275] Input: User input data, emotion data

[1276] Processing: Analysis algorithms are used to check the consistency of the input data with the sentiment data and extract relevant data.

[1277] Output: Parsed input data and emotion data

[1278] Step 6:

[1279] Based on the analysis results, the server extracts the appropriate format and relevant content from the database.

[1280] Input: Parsed input data and emotion data

[1281] Processing: Using database search algorithms, we extract the most appropriate format and relevant content, for example, selecting the suggested format and content for the manufacturing industry.

[1282] Output: Extracted format and content

[1283] Step 7:

[1284] The server uses the extracted format and content to run a generative AI to generate new proposal materials.

[1285] Input: Extracted format, content, and sentiment data

[1286] Processing: Run the generative AI model to generate a pitch deck, adjusting the tone and content of the deck based on the sentiment data.

[1287] Output: Generated proposal

[1288] Step 8:

[1289] The server temporarily stores the generated proposal materials and provides them to the user through the terminal.

[1290] Input: Generated proposal

[1291] Processing: The proposal materials are temporarily stored and prepared for transmission to the user via the terminal.

[1292] Output: Proposal document ready for user review

[1293] Step 9:

[1294] The user checks the provided proposal materials on the terminal and makes any necessary corrections or additions using the interface.

[1295] Input: Generated proposal

[1296] Processing: The user reviews the proposal and makes corrections or additions via the user interface. The emotion engine also monitors changes in emotion during editing.

[1297] Output: Edited proposal

[1298] Step 10:

[1299] The user completes the edits and finalizes the proposal.

[1300] Input: Edited proposal

[1301] Processing: By pressing the Confirm button, the proposal materials are sent to the server.

[1302] Output: Final, confirmed proposal

[1303] Step 11:

[1304] The server stores the received final proposal document in a database.

[1305] Input: Final, confirmed proposal

[1306] Processing: Store in a database and index for future reference when creating proposals.

[1307] Output: Saved proposal

[1308] (Application example 2)

[1309] 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."

[1310] Conventional proposal material creation systems do not take into account the user's emotional state, resulting in problems with the materials provided not being in line with the user's emotions or situation. Furthermore, when personalizing the purchasing experience in a virtual store, there was a lack of a mechanism to respond to the user's real-time emotional changes. This made it difficult to effectively improve the user's purchasing motivation and satisfaction.

[1311] 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.

[1312] In this invention, the server includes means for storing the format and content of previously used proposals in a database, means for training a generation AI based on the format and content of the proposals, means for receiving information entered by a user for creating a proposal, means for extracting appropriate formats and content from the database based on the received information, means for generating a new proposal using the generation AI based on the extracted format and content, means for providing the generated proposal to the user, means for the user to review and edit the provided proposal, means for saving the final edited proposal in the database, means for analyzing the user's emotions in real time using an emotion recognition engine, and means for adjusting the content and tone of the proposal based on the user's emotional state, thereby making it possible to provide proposal materials and purchasing experiences that reflect the user's emotions.

[1313] "Proposal format" refers to the layout and structure of documents such as proposals and reports, and is a template or format that improves the readability of the content and the ease with which information is conveyed.

[1314] "Proposal content" refers to text or data containing detailed information about a specific proposal or project, and is an element that explains the key points and advantages of a specific proposal.

[1315] A "database" is a structured collection of data, a system that allows for efficient information storage, management, and retrieval.

[1316] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to automatically generate new data and documents, for example, to create proposals and reports.

[1317] "User" refers to the entity that uses this system to create, edit, and check proposals, and in most cases is a corporate sales representative or presentation person.

[1318] An "emotion recognition engine" is a system that automatically analyzes and recognizes emotions from a user's facial expressions and voice, and is a technology that optimizes the system's operation based on that information.

[1319] "Proposal tone adjustment" is the process of adapting the presentation and wording of a proposal's content to suit the user's emotional state.

[1320] A "personalized shopping experience" is a method for increasing user satisfaction by providing a shopping experience that is customized based on the preferences, needs, and emotions of each individual user.

[1321] The present invention provides a system for generating a new proposal based on the format and content of an existing proposal, and for adjusting the content and tone of the proposal depending on the user's emotional state. A specific embodiment of this system is described below.

[1322] System Configuration

[1323] The system includes a server, a terminal, a user interface, a database, and an emotion recognition engine. The server is responsible for storing data, training the generative AI, extracting information, and generating proposals. The emotion recognition engine recognizes users' emotions and reflects that information in the generation and adjustment of proposals.

[1324] Initial settings and database creation

[1325] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[1326] Training generative AI

[1327] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[1328] User interaction and data entry

[1329] Users access the system through their terminals and input information to create proposals. Specifically, users enter basic information about the corporate client (company name, industry, size) and information about the product they are proposing (product name, features, price) into the interface. At this time, an emotion recognition engine recognizes the user's emotions and collects data.

[1330] Receiving and analyzing information

[1331] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[1332] Format and content extraction

[1333] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user proposes ERP software to a manufacturing customer, the server extracts the proposal format and related content for the manufacturing industry.

[1334] Proposal generation

[1335] The server uses the extracted format and content to run a generative AI to generate a new proposal. The emotion recognition engine then adjusts the content and tone of the proposal based on the user's emotional data collected. For example, if the user expresses positive emotions, the proposal will reflect a positive tone.

[1336] Proposal submission

[1337] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[1338] Review and edit the proposal

[1339] The user can review the provided proposal on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requirements. The emotion recognition engine also continuously monitors the user's emotional changes and reflects them in the editing process.

[1340] Finalize and send

[1341] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[1342] Save the proposal

[1343] The server stores the final proposal it receives in a database, where it indexes the proposal so that other sales representatives can refer to it when creating future proposals.

[1344] Hardware and software used

[1345] Facial Recognition Camera: Commonly Used Webcam

[1346] Smart glasses or head-mounted displays (HMDs): For example, Oculus Quest 2

[1347] Emotion Recognition: Pipeline Methods in the Transformers Library

[1348] VR Interface: Virtual 3D VR Library

[1349] Specific examples

[1350] A user visits a virtual store and puts on smart glasses. The system analyzes the user's facial expressions and voice, and if the user appears happy, it will proactively suggest products (e.g., new or popular items). On the other hand, if the user appears tired, it will suggest relaxation goods. This personalizes the user's shopping experience and increases satisfaction.

[1351] Example prompts to input to the generative AI model

[1352] "If the user is feeling relaxed, suggest products that will help them relax."

[1353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1354] Processing Steps

[1355] Step 1:

[1356] Initial settings and database creation

[1357] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick information retrieval.

[1358] Input: Past proposal data

[1359] Output: A structured database

[1360] Step 2:

[1361] Training generative AI

[1362] The server uses the proposal data in the database to train the generative AI model, giving it the ability to adapt to new situations and generate high-quality proposals.

[1363] Input: Proposal data in the database

[1364] Output: A trained generative AI model

[1365] Step 3:

[1366] User interaction and data entry

[1367] Users access the system using a terminal and enter basic information (company name, industry, size) and details of the proposed product (product name, features, price) to create a proposal. At this time, the emotion recognition engine analyzes the user's emotions in real time and collects data.

[1368] Input: User's basic information, item information, facial expressions and voice data

[1369] Output: User input information and emotion data

[1370] Step 4:

[1371] Receiving and analyzing information

[1372] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data from the database based on the analysis results.

[1373] Input: User input information, emotion data

[1374] Output: Analysis results, search criteria

[1375] Step 5:

[1376] Format and content extraction

[1377] Based on the analysis results, the server extracts the appropriate format and content from the database, for example, selecting a proposal format for the manufacturing industry and related content.

[1378] Input: Analysis results, database

[1379] Output: appropriate format and content

[1380] Step 6:

[1381] Proposal generation

[1382] The server uses the extracted format and content to run a generative AI to generate a new proposal, adjusting the tone and content of the proposal based on the user's emotional data collected by the emotion recognition engine.

[1383] Input: Extracted format, content, and sentiment data

[1384] Output: New proposal

[1385] Step 7:

[1386] Proposal submission

[1387] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[1388] Enter: New Proposal

[1389] Output: Temporarily save the proposal and provide it to the user

[1390] Step 8:

[1391] Review and edit the proposal

[1392] The user can use the device to check the proposal and make any necessary corrections or additions. The emotion recognition engine monitors the user's emotional changes and reflects them in the editing process.

[1393] Input: Proposal, edits, sentiment data

[1394] Output: Revised and added proposal

[1395] Step 9:

[1396] Finalize and send

[1397] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[1398] Input: Final edited proposal

[1399] Output: Send the final proposal to the server

[1400] Step 10:

[1401] Save the proposal

[1402] The server stores the final proposals it receives in a database and indexes them for future reference.

[1403] Input: Final proposal

[1404] Output: Stored in database, indexed

[1405] 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.

[1406] 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.

[1407] 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.

[1408] [Fourth embodiment]

[1409] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1410] 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.

[1411] 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).

[1412] 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.

[1413] 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.

[1414] 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).

[1415] 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.

[1416] 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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."

[1422] System Configuration

[1423] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generation AI, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[1424] Initial settings and database creation

[1425] The server first collects the formats and contents of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type and industry, and is structured so that information can be quickly extracted when needed.

[1426] Training generative AI

[1427] The server trains the generative AI using the proposal data stored in the database. The trained generative AI is then able to generate new proposals with high accuracy.

[1428] User interaction and data entry

[1429] Users access the system through a terminal and input information to create new proposal materials. Specifically, users use an interface to enter basic information about corporate clients (e.g., company name, industry, size) and information about the products they are proposing (e.g., product name, features, price).

[1430] Data extraction and proposal generation

[1431] When the server receives the information entered by the user, it searches and extracts the appropriate format and relevant content from the database. Based on the extracted data, it uses generative AI to generate a new proposal document. This generated proposal document is structured based on the selected format and includes the specific information requested by the user.

[1432] Review and edit proposal materials

[1433] The terminal provides the generated proposal materials to the user. The user uses an interface to check the displayed proposal materials and edit the content as necessary. The user can adjust the content of the materials appropriately and finalize them.

[1434] Saving proposal materials

[1435] The final edited proposal is sent from the device to a server and saved in a database, where the server indexes and stores the new proposal for future reuse by other users.

[1436] Specific examples

[1437] User operation example

[1438] When a salesperson creates a proposal document for a new corporate client, the salesperson logs into the system and enters basic information about the client and details of the products they are proposing.

[1439] For example, suppose the client is a manufacturing company with 500 employees and the proposed product is new ERP software.

[1440] System working example

[1441] The server receives the input information and selects the appropriate format from past proposal documents for the manufacturing industry.

[1442] Based on the selected format, the server uses trained generative AI to generate new proposal materials.

[1443] For example, the proposal document includes trends in the manufacturing industry, the benefits of ERP software, and past implementation examples.

[1444] Review and edit

[1445] The generated proposal is provided to the user via a terminal, who can review the proposal and make modifications to suit their specific needs.

[1446] For example, adding customized solutions to proposals based on specific customer requirements.

[1447] Save and reuse

[1448] The final proposal is sent to a server and stored in a database, which indexes and stores the new proposal for future use by other salespeople.

[1449] This system enables all sales representatives to efficiently create high-quality proposal materials, improving overall sales capabilities.

[1450] The processing flow will be explained below.

[1451] Step 1: Building the database

[1452] The server collects the format and content of previously used proposal documents, structures them, and stores them in a database that is categorized by industry and category, allowing for quick search and retrieval of information.

[1453] Step 2: Training the generative AI

[1454] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[1455] Step 3: User login and input

[1456] The user logs into the system through a terminal and enters basic information about the corporate customer (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) into the interface, which is necessary to create a proposal document.

[1457] Step 4: Receiving and analyzing information

[1458] The server receives the information sent by the user, analyzes it, and prepares to search for related data in the database based on the analysis results.

[1459] Step 5: Extracting format and content

[1460] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[1461] Step 6: Generate a proposal

[1462] The server uses the extracted format and content to run a generative AI to generate new proposals, which are customized based on the information provided by the user.

[1463] Step 7: Submit your proposal

[1464] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[1465] Step 8: Review and edit your proposal

[1466] The user can review the provided proposal materials on their device and use the interface to make any necessary corrections or additions, for example, to tailor the content to meet the specific needs of the client.

[1467] Step 9: Finalize and submit

[1468] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[1469] Step 10: Save your proposal

[1470] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[1471] The above steps create a system that enables sales representatives to efficiently create high-quality proposal materials.

[1472] Example 1

[1473] 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."

[1474] The traditional proposal document creation process had problems with high quality variation and low efficiency because each sales representative created their own documents. Furthermore, there was often no database to utilize past success stories, making it difficult to share know-how. Furthermore, creating new documents took time and effort, making it difficult to respond quickly when a quick response was required.

[1475] 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.

[1476] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generative AI model based on the format and content of the proposal materials, means for receiving information entered by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generative AI model based on the extracted format and content, means for providing the generated proposal materials to the user, means for the user to review and edit the provided proposal materials, means for saving the final edited proposal materials in the database, and means for indexing the proposal materials to make them reusable. This enables consistent and rapid creation of high-quality proposal materials, thereby realizing the sharing of know-how and improved business efficiency.

[1477] "Previously used proposal materials" are materials that contain proposal content and formats that have already been used in practice.

[1478] "Format" refers to the layout, format, design, and general components of the proposal.

[1479] "Content" refers to the specific information, data, examples, and explanatory text contained in the proposal materials.

[1480] A "database" is a system that can efficiently store, manage, search, and update structured data.

[1481] A "generative AI model" refers to an artificial intelligence algorithm that learns from input data and automatically generates new proposal materials.

[1482] "User" refers to a person who uses the system to create, review, and edit proposal materials.

[1483] "Information" refers to data such as basic customer information and proposed product information that the user inputs to create proposal materials.

[1484] "Means of receiving" refers to the technology or method by which the system receives information entered by the user.

[1485] "Format and content extraction means" refers to the techniques and methods used to select appropriate format and content from the database.

[1486] "New proposal materials" refers to proposal documents automatically generated by a generative AI model based on user input information and past data.

[1487] "Means for providing" refers to the technology or method for displaying, transmitting, or making accessible the generated proposal materials to the user.

[1488] "Means for reviewing and editing" refers to techniques and methods that allow users to review, correct, and supplement the generated proposal materials.

[1489] "Final edited proposal material" refers to the proposal material that has been checked and corrected as necessary by the user.

[1490] "Means of indexing proposal documents to make them reusable" refers to techniques and methods for adding easily searchable tags and data to proposal documents for future use.

[1491] System Configuration

[1492] The system of the present invention includes a server, a terminal, a user interface, and a database. The server is responsible for storing data, training the generative AI model, extracting information, and generating proposal materials. The terminal provides an interface for users to interact with the system and input and edit information. The user is responsible for creating and editing proposal materials for corporate clients.

[1493] Initial settings and database creation

[1494] The server first collects the format and content of proposal documents previously used by high-performing salespeople and stores them in a database. This database can be categorized by format type (e.g., pptx, pdf, docx) and industry (manufacturing, IT, healthcare, etc.), and is structured so that information can be quickly extracted when needed. To do this, the server uses Python's Pandas library to format the data.

[1495] Training generative AI

[1496] The server uses the stored proposal data to train the generative AI model. This training uses machine learning frameworks such as TensorFlow and PyTorch. The specific training procedure involves preprocessing the data, splitting it into a training dataset and a test dataset, and then inputting the data into the generative AI model for training.

[1497] User interaction and data entry

[1498] Users log in to the system via their terminal and enter information to create proposal documents. This input is done using a dedicated form on a web browser. The form is built using HTML5 and JavaScript and includes fields for entering the company name, industry, number of employees, proposed product name, features, price, etc. When the user performs input operations, the data is sent to the server in JSON format.

[1499] Data extraction and proposal generation

[1500] When the server receives the information entered by the user, it searches the database for the appropriate format and content based on that information. This search is performed using an SQL query. For example, to search for manufacturing data, the query "SELECT FROM Proposal Documents WHERE Industry = 'Manufacturing'" is used. Then, based on the search results, a generative AI model is used to generate new proposal documents. The generative AI model generates personalized proposal content based on the user's input, including instructions provided by the prompt.

[1501] Specific examples

[1502] Prompt: "Write a proposal for ERP software for a 500-person manufacturing company."

[1503] Review and edit proposal materials

[1504] The device provides the generated proposal documents to the user, who then reviews them using an interface on the device. This interface was designed using JavaScript and React, allowing the user to make real-time edits to the proposal documents. For example, they can add information about specific features of the proposed software or edit existing information.

[1505] Saving proposal materials

[1506] The final edited proposal document is sent from the device to the server and saved in a database. This saving process also stores metadata, including the file name and the date and time of saving. The server uses the Python Django framework to save the proposal document and its metadata in a database, using MySQL or PostgreSQL. After saving, the document is indexed so that other sales representatives can reuse it in the future.

[1507] This enables the system to help sales representatives create efficient, high-quality proposal materials, improving overall sales performance.

[1508] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1509] Step 1:

[1510] The server collects the format and content of past proposal documents and stores them in a database. During this process, the server uses the Python Pandas library to format the collected proposal documents into the appropriate format.

[1511] Input: Previously used proposal materials

[1512] Data processing: Use Pandas to format the data and categorize it by format.

[1513] Output: Formatted proposal data stored in a database

[1514] Step 2:

[1515] The server uses the proposal data stored in the database to train the generative AI model, using machine learning frameworks such as TensorFlow and PyTorch, which involves steps of preprocessing, data partitioning, and model training.

[1516] Input: Proposal data in the database

[1517] Data Computing: Preprocessing and model training using TensorFlow and PyTorch

[1518] Output: A trained generative AI model

[1519] Step 3:

[1520] Users log in to the system via their terminal and enter information to create proposal documents. The input form is built using HTML5 and JavaScript, and users enter information such as company name, industry, number of employees, proposed product name, features, and price.

[1521] Input: Company name, industry, number of employees, product information to be proposed, etc.

[1522] Data processing: Convert input information into JSON format and send it to the server

[1523] Output: User input data received from server in JSON format

[1524] Step 4:

[1525] The server uses the received user input to extract the appropriate format and content from the database, using SQL queries to quickly retrieve the relevant data.

[1526] Input: User input information in JSON format

[1527] Data Search: Use SQL queries to find the right format and content

[1528] Output: Extracted format and content

[1529] Step 5:

[1530] The server generates new proposal documents using a generative AI model based on the extracted format and content. This generation process involves inputting prompts containing user input information into the generative AI model.

[1531] Input: Extracted format and content, user-entered information

[1532] Data computation: Generative AI models are fed with user information and prompts to generate new proposals.

[1533] Output: The new proposal that was generated

[1534] Step 6:

[1535] The device provides the generated proposal documents to the user, who can then review and edit them as needed using the device's interface, which is built with JavaScript and React.

[1536] Input: Generated new proposal

[1537] Behavior: Displays material to the user and provides an editing interface

[1538] Output: User-reviewed and edited proposal

[1539] Step 7:

[1540] The user checks and edits the proposal material to finalize it, and the terminal transmits the edited proposal material to the server.

[1541] Input: Generated proposal, user modifications

[1542] Data processing: Creating the final proposal document reflecting the user's modifications

[1543] Output: Final edited proposal

[1544] Step 8:

[1545] The server then stores the final edited proposal in a database, indexes it, and makes it reusable, along with metadata such as the file name and the date and time it was saved.

[1546] Input: Final edited proposal

[1547] Data storage: Stored in database and indexed

[1548] Output: Final proposal and index stored in database

[1549] (Application example 1)

[1550] 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."

[1551] Conventional proposal generation systems do not necessarily enable sales representatives to efficiently create proposal materials for corporate customers. Real-time data collection and analysis is particularly important for in-factory production planning and parts procurement proposals, but this requires a lot of manual work, which takes time and effort. This can lead to insufficient optimization of production lines and cost reductions. Furthermore, because the quality of proposal materials depends on the experience and skills of sales representatives, it is difficult to maintain consistent quality.

[1552] 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.

[1553] In this invention, the server includes means for storing the format and content of previously used proposal materials in a database, means for training a generation AI based on the format and content of the proposal materials, means for receiving information input by a user for creating proposal materials, means for extracting appropriate formats and content from the database based on the received information, means for generating new proposal materials using the generation AI based on the extracted format and content, means for machines operating in a factory to collect production data in real time and generate proposal materials related to parts shortages and production plan optimization, means for providing the generated proposal materials to a user, means for the user to review and edit the provided proposal materials, and means for saving the final edited proposal materials in a database. This makes it possible to utilize real-time data for in-factory production plans and parts procurement proposals, and to automatically generate high-quality proposal materials quickly and efficiently.

[1554] A "proposal document" is a document that summarizes the details of the products or services that are proposed to corporate clients.

[1555] A "database" is a collection of electronic data that is structured to store information systematically and make it easy to search and retrieve.

[1556] "Generative AI" is a system or program that uses artificial intelligence technology to automatically generate new information or documents.

[1557] "User" means an individual or company employee who uses the system to create and edit proposal materials.

[1558] "Format" refers to the layout and structure of the proposal materials, specifically including the placement of text and design elements.

[1559] "Content" refers to the specific information in the documents and data contained in the proposal materials, including product features, prices, implementation examples, etc.

[1560] An "interface" is a screen or tool that allows a user to interact with a system and facilitates the input and editing of information.

[1561] "Real-time data" refers to data collected in real time by machines and sensors operating within a factory to determine the current situation.

[1562] "Production planning" refers to the product manufacturing schedule and resource allocation plan in a factory.

[1563] "Parts shortage" refers to a situation where a necessary part is not available on the production line.

[1564] This invention relates to a system that works in conjunction with machines operating in a factory and uses real-time data to automatically generate proposal materials related to parts shortages and optimization of production plans. The system includes the following elements:

[1565] 1. Database construction:

[1566] The server collects the format and content of past proposal documents and stores them in a database. This database is categorized based on the format and content of the proposal documents and is structured to allow for quick extraction of relevant information.

[1567] 2. Training the generative AI:

[1568] The server uses the proposal data stored in the database to train a generative AI model, which has the ability to automatically generate new proposals with high accuracy.

[1569] 3. Data Collection:

[1570] Machines operating in factories collect production data in real time, including machine operation status, parts consumption, and inventory status.

[1571] 4. User Input:

[1572] Users access the system through a terminal and input basic information about the corporate customer and information about the product they wish to propose. This can be done easily using the interface.

[1573] 5. Data extraction and proposal generation:

[1574] The server integrates user-entered information with real-time production data, extracts the appropriate format and content from the database, and then uses generative AI to generate new proposal materials based on the extracted information.

[1575] 6. Proposal materials provision and editing:

[1576] The generated proposal material is provided to the user, who can use an interface to check the material through a terminal and edit the content as necessary.

[1577] 7. Save the Final Version:

[1578] The final proposal document edited by the user is sent back to the server and saved in the database, allowing other users to reuse the new proposal document.

[1579] Hardware and Software Used

[1580] Hardware:

[1581] Machines operating in factories (production machines with sensors)

[1582] Servers (requiring high performance computing)

[1583] User devices (smartphones, tablets, computers)

[1584] software:

[1585] Deep learning frameworks (e.g., Keras)

[1586] Database Management Systems

[1587] User interface tools (web or mobile app)

[1588] Specific examples

[1589] In a factory, the following prompts can be used:

[1590] Prompt Sentence Examples

[1591] Based on the information below, please create next week's production plan and parts procurement proposal materials.

[1592] Customer name: Manufacturing A

[1593] Industry: Auto parts manufacturing

[1594] Number of employees: 1,200

[1595] Production planning data: [List data here]

[1596] Product name: New engine parts

[1597] Features: Lightweight, high strength

[1598] Price: 5,000 yen / piece

[1599] This system allows factory managers to utilize real-time data to quickly and efficiently create production plans and automatically generate parts procurement proposals, thereby improving production efficiency and reducing costs.

[1600] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1601] Step 1:

[1602] The server collects the format and content of proposal documents used in the past and stores them in a database. Specifically, the server collects existing proposal documents as electronic data and stores them in a database. In the database, this data is structured so that it is categorized based on industry and format. The input is the past proposal document data, and the output is a structured database.

[1603] Step 2:

[1604] The server trains the generative AI model using proposal data stored in the database. The server extracts the format and content of proposal documents from the database and supplies them to the generative AI model to train the model. The input is the proposal data extracted from the database, and the output is the trained generative AI model.

[1605] Step 3:

[1606] Machines operating in a factory collect production data in real time. This data is obtained from the machine's sensors and is related to the operating status, parts consumption, and inventory status. This data is sent to a server. The input is the real-time data from the machine's sensors, and the output is the production data sent to the server.

[1607] Step 4:

[1608] The user uses a terminal to input basic information about the corporate customer and information about the product they are proposing. The user inputs this information through a dedicated interface, and the terminal sends the information to the server. The input is the corporate customer information and product information entered by the user, and the output is the information sent to the server.

[1609] Step 5:

[1610] The server integrates the information entered by the user with real-time production data and extracts the appropriate format and content from the database. The server processes the data as needed based on this information and reconstructs the appropriate data. The input is the information entered by the user and real-time production data, and the output is the extracted format and content.

[1611] Step 6:

[1612] The server generates new proposal materials using the generative AI model. The server inputs the extracted format and content into the generative AI model and automatically generates new proposal materials. The input is the extracted format and content, and the output is the generated new proposal materials.

[1613] Step 7:

[1614] The generated proposal materials are provided to the user. The server sends the generated proposal materials to the terminal, where the user can review and edit them. The input is the generated proposal materials, and the output is the user's review and editing.

[1615] Step 8:

[1616] The user submits the final edited proposal to the server, which stores it in a database. The server indexes the new proposal so that it can be reused by other users in the future. The input is the final edited proposal by the user, and the output is the proposal stored in the database.

[1617] 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.

[1618] System Configuration

[1619] The system of the present invention includes a server, a terminal, a user interface, a database, and an emotion engine. The server is responsible for storing data, training the generative AI, extracting information, generating proposal materials, and processing emotion data. The terminal provides an interface for users to interact with the system and input and edit information. Users are responsible for creating and editing proposal materials for corporate clients. The emotion engine recognizes user emotions and reflects that information in the generation of proposal materials.

[1620] Initial settings and database creation

[1621] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[1622] Training generative AI

[1623] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[1624] User interaction and data entry

[1625] Users access the system through their terminals and input information to create proposal materials. Specifically, users enter basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price) into the interface. At this time, the emotion engine recognizes the user's emotions and collects emotion data.

[1626] Receiving and analyzing information

[1627] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[1628] Format and content extraction

[1629] The server then extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it will extract the proposal format and related content for the manufacturing industry.

[1630] Proposal generation

[1631] The server uses the extracted format and content to run the generative AI to generate new proposal materials. At this time, the emotion engine adjusts the content and tone of the materials based on the user's emotional data collected. For example, if the user is expressing positive emotions, the proposal materials will reflect a positive tone.

[1632] Providing proposal materials

[1633] The server temporarily stores the generated proposal documents and provides them to the user via the terminal, at which point the user can check the proposal documents.

[1634] Review and edit proposal materials

[1635] The user can review the provided proposal materials on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requests. The emotion engine also continuously monitors changes in the user's emotions and reflects them in the editing process.

[1636] Finalize and send

[1637] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the proposal document is sent to the server.

[1638] Saving proposal materials

[1639] The server stores the final version of the proposal document it receives in a database, and indexes the saved proposal document so that other sales representatives can refer to it when creating future proposal documents.

[1640] Specific examples

[1641] User operation example

[1642] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[1643] System working example

[1644] The server analyzes the input information and emotion data, and selects the appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document.

[1645] The generated proposal is then provided to the user via their device, who can review it and fine-tune it to suit the client's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the proposal as needed.

[1646] The final edited proposal document is sent to the server and stored in the database, where other sales representatives can use it as a reference when creating their own proposal documents.

[1647] The present invention makes it possible to efficiently create high-quality proposal materials that take into account the emotional state of the user, thereby improving overall sales capabilities.

[1648] The processing flow will be explained below.

[1649] Step 1: Building the database

[1650] The server collects the format and content of past proposal documents, structures them, and stores them in a database. This database is categorized by the industry and category of the proposal, allowing for quick search and retrieval of information.

[1651] Step 2: Training the generative AI

[1652] The server trains the AI ​​using the proposal data stored in the database. The trained AI can then generate optimal proposals with high accuracy based on new information entered by the user.

[1653] Step 3: User Login and Data Entry

[1654] The user logs in to the system using a terminal, and then enters basic information about the corporate client (e.g., company name, industry, size) and information about the product to be proposed (e.g., product name, features, price) through an interface for creating proposal materials.

[1655] Step 4: Emotion Recognition with the Emotion Engine

[1656] The device's built-in emotion engine analyzes the user's facial expressions and tone of voice to recognize their current emotional state, and this emotional data is reflected in the creation of proposal materials.

[1657] Step 5: Receiving and analyzing information

[1658] The server receives and analyzes the basic information, product information, and emotion data sent by the user. Based on the analysis results, it prepares to search for related data in the database.

[1659] Step 6: Extracting format and content

[1660] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user is proposing ERP software to a manufacturing customer, it extracts the proposal format and related content for the manufacturing industry.

[1661] Step 7: Generate a proposal

[1662] The server uses the extracted format and content to run a generative AI to generate a new proposal. At this stage, emotional data from the emotion engine is also incorporated, and the proposal incorporates a tone and style that reflects the user's emotional state.

[1663] Step 8: Submit your proposal

[1664] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user has the opportunity to review the proposal and fine-tune its content.

[1665] Step 9: Review and edit your proposal

[1666] The user reviews the proposal displayed on their device in detail. They then use the interface to edit the content of the proposal, making any necessary corrections or adding additional information. While editing, the emotion engine continues to monitor the user's emotional state and optimizes the tone and style of the proposal.

[1667] Step 10: Finalize and submit

[1668] The user completes the editing and confirms the final version of the proposal document. By pressing the confirm button, the completed proposal document is sent to the server.

[1669] Step 11: Save your proposal

[1670] The server saves the final proposal documents it receives in a database, where they are indexed and stored for future reference by other sales representatives.

[1671] The above steps realize a process for creating proposal materials that utilizes an emotion engine, making it possible to generate high-quality materials that take into account the user's emotional state.

[1672] Example 2

[1673] 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."

[1674] Conventional systems for creating proposal materials were unable to effectively utilize past data and had difficulty automatically generating proposal materials that reflected user emotions. In particular, reading user emotions and creating materials that reflected them had to be done manually, which was inefficient. Furthermore, the content of proposal materials was uniform and lacked customization for individual customers, resulting in a low success rate for proposals. A new system that solves these problems is needed.

[1675] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for storing the format and content of proposal materials used in the past in a database, a means for training the generation AI based on the format and content of the proposal materials, and a means for recognizing the user's emotions and reflecting the data in the proposal materials. This makes it possible to quickly and efficiently generate customized proposal materials that reflect the user's emotions while effectively utilizing past data.

[1676] The "database" is a collection of information that stores the format and content of proposal materials used in the past and is categorized by industry and category.

[1677] "Generative AI" is an artificial intelligence that is trained based on proposal document data in a database and automatically generates new proposal documents using input information and emotional data from users.

[1678] A "user" is an entity that inputs information into the system to create proposal materials, and checks and edits the generated proposal materials.

[1679] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions and tone of voice, and reflects that data in the content and tone of proposal materials.

[1680] A "terminal" is a device through which a user accesses the system and enters and edits information.

[1681] A "proposal document" is a document that summarizes the content of a proposal to a corporate client, and is automatically generated by generation AI.

[1682] "Format" refers to the structure and layout of a proposal document, and is suitable for a particular industry or purpose.

[1683] "Information extraction" is the process of searching and retrieving the required format and content from within a database.

[1684] "Emotion data" is data that represents the emotional state obtained by the emotion engine from the user's facial expression and voice.

[1685] MODE FOR CARRYING OUT THE INVENTION

[1686] The present invention is a system that includes a server, a terminal, a user interface, a database, and an emotion engine. Here, the role of each component and its specific operation will be explained.

[1687] 1. Server configuration and operation

[1688] The server collects the format and content of previously used proposal materials and stores them in a database, which is categorized by industry and category, allowing for fast and efficient information retrieval.

[1689] The generative AI is trained using data stored in the database, using open-source machine learning frameworks (e.g., TensorFlow, PyTorch).

[1690] The server receives the information and emotion data sent by the user, analyzes them, and based on the analysis results, searches and extracts relevant data from the database.

[1691] The server inputs the extracted format and content into the generation AI to generate new proposal materials, adjusting the content and tone of the proposal materials based on the user's emotional data recognized by the emotion engine.

[1692] 2. Terminal configuration and operation

[1693] The terminal provides an interface for users to interact with the system and input information. This interface is implemented using HTML and JavaScript, and allows users to enter basic information about corporate customers and details of the products they are proposing.

[1694] The terminal provides the generated proposal material to the user, who can then check the material and edit it as necessary.

[1695] The terminal has the function of sending the proposal document that the user has completed editing to the server, where it is analyzed again for final confirmation and saved in the database.

[1696] 3. User Operation

[1697] Users access the system through a terminal and input information to create proposal materials. Specifically, they input basic information about the corporate client (e.g., company name, industry, size) and information about the product they are proposing (e.g., product name, features, price).

[1698] The emotion engine recognizes emotions from the user's facial expressions and tone of voice and collects this emotion data.

[1699] 4. Emotion Engine

[1700] The emotion engine recognizes the user's emotions and reflects that data in the proposal materials. Specifically, if the user shows positive emotions, the proposal materials will reflect a positive tone.

[1701] Specific examples

[1702] Example of user action:

[1703] When a salesperson creates a proposal for a new corporate client, they log in to the system and enter basic information about the client and details of the product they are proposing. At the same time, the emotion engine recognizes the user's emotions from their facial expressions and tone of voice and collects data.

[1704] Example of a working system:

[1705] The server analyzes the input information and emotion data and selects an appropriate format from past proposal documents for the manufacturing industry. If the user expresses positive emotions, the emotion engine reflects a positive tone in the content of the proposal document. The generated proposal document is provided to the user via their device, who reviews it and fine-tunes it to suit the customer's specific needs. During editing, the emotion engine continues to monitor the user's emotions and further adjusts the tone and style of the document as needed. The final edited proposal document is sent to the server and stored in a database. Other sales representatives can use this document as a reference when creating their own proposal documents.

[1706] Prompt Sentence Examples

[1707] Company Information: Smart Tech Co., Ltd.

[1708] Industry: Manufacturing

[1709] Size: Medium-sized company

[1710] Proposed product: ERP software

[1711] Product features: Integrated management, automation, real-time analysis

[1712] Price: 1 million yen for a yearly contract

[1713] This makes it possible to efficiently create high-quality proposal materials that take into account the user's emotional state, thereby improving overall sales capabilities.

[1714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1715] Step 1:

[1716] The server collects past proposal materials and stores them in a database.

[1717] Input: Previously used proposal materials (PDF, Word, etc.)

[1718] Processing: Analyze the format and content of the documents, then classify and store them in a database. Specifically, extract text data from the documents and organize them by industry and category.

[1719] Output: A database containing classified proposals

[1720] Step 2:

[1721] The server trains the generative AI using proposal data in the database.

[1722] Input: Text data of proposal documents stored in a database

[1723] Processing: Use machine learning frameworks (e.g., TensorFlow, PyTorch) to train generative AI on the format and content of the proposal.

[1724] Output: A trained generative AI model

[1725] Step 3:

[1726] A user accesses the system through a terminal and inputs information to create a proposal document.

[1727] Input: Basic information about the corporate customer (company name, industry, size) and information about the proposed product (product name, features, price)

[1728] Processing: Collect input data using an information input interface (HTML, JavaScript).

[1729] Output: User input data

[1730] Step 4:

[1731] The emotion engine recognizes the user's emotions and collects that data.

[1732] Input: User's facial expression, tone of voice

[1733] Processing: Emotion recognition algorithms are used to analyze facial expressions and vocal tones.

[1734] Output: Emotion data

[1735] Step 5:

[1736] The server receives the information and emotion data sent by the user and analyzes them.

[1737] Input: User input data, emotion data

[1738] Processing: Analysis algorithms are used to check the consistency of the input data with the sentiment data and extract relevant data.

[1739] Output: Parsed input data and emotion data

[1740] Step 6:

[1741] Based on the analysis results, the server extracts the appropriate format and relevant content from the database.

[1742] Input: Parsed input data and emotion data

[1743] Processing: Using database search algorithms, we extract the most appropriate format and relevant content, for example, selecting the suggested format and content for the manufacturing industry.

[1744] Output: Extracted format and content

[1745] Step 7:

[1746] The server uses the extracted format and content to run a generative AI to generate new proposal materials.

[1747] Input: Extracted format, content, and sentiment data

[1748] Processing: Run the generative AI model to generate a pitch deck, adjusting the tone and content of the deck based on the sentiment data.

[1749] Output: Generated proposal

[1750] Step 8:

[1751] The server temporarily stores the generated proposal materials and provides them to the user through the terminal.

[1752] Input: Generated proposal

[1753] Processing: The proposal materials are temporarily stored and prepared for transmission to the user via the terminal.

[1754] Output: Proposal document ready for user review

[1755] Step 9:

[1756] The user checks the provided proposal materials on the terminal and makes any necessary corrections or additions using the interface.

[1757] Input: Generated proposal

[1758] Processing: The user reviews the proposal and makes corrections or additions via the user interface. The emotion engine also monitors changes in emotion during editing.

[1759] Output: Edited proposal

[1760] Step 10:

[1761] The user completes the edits and finalizes the proposal.

[1762] Input: Edited proposal

[1763] Processing: By pressing the Confirm button, the proposal materials are sent to the server.

[1764] Output: Final, confirmed proposal

[1765] Step 11:

[1766] The server stores the received final proposal document in a database.

[1767] Input: Final, confirmed proposal

[1768] Processing: Store in a database and index for future reference when creating proposals.

[1769] Output: Saved proposal

[1770] (Application example 2)

[1771] 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."

[1772] Conventional proposal material creation systems do not take into account the user's emotional state, resulting in problems with the materials provided not being in line with the user's emotions or situation. Furthermore, when personalizing the purchasing experience in a virtual store, there was a lack of a mechanism to respond to the user's real-time emotional changes. This made it difficult to effectively improve the user's purchasing motivation and satisfaction.

[1773] 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.

[1774] In this invention, the server includes means for storing the format and content of previously used proposals in a database, means for training a generation AI based on the format and content of the proposals, means for receiving information entered by a user for creating a proposal, means for extracting appropriate formats and content from the database based on the received information, means for generating a new proposal using the generation AI based on the extracted format and content, means for providing the generated proposal to the user, means for the user to review and edit the provided proposal, means for saving the final edited proposal in the database, means for analyzing the user's emotions in real time using an emotion recognition engine, and means for adjusting the content and tone of the proposal based on the user's emotional state, thereby making it possible to provide proposal materials and purchasing experiences that reflect the user's emotions.

[1775] "Proposal format" refers to the layout and structure of documents such as proposals and reports, and is a template or format that improves the readability of the content and the ease with which information is conveyed.

[1776] "Proposal content" refers to text or data containing detailed information about a specific proposal or project, and is an element that explains the key points and advantages of a specific proposal.

[1777] A "database" is a structured collection of data, a system that allows for efficient information storage, management, and retrieval.

[1778] "Generative AI" refers to artificial intelligence techniques that use machine learning algorithms to automatically generate new data and documents, for example, to create proposals and reports.

[1779] "User" refers to the entity that uses this system to create, edit, and check proposals, and in most cases is a corporate sales representative or presentation person.

[1780] An "emotion recognition engine" is a system that automatically analyzes and recognizes emotions from a user's facial expressions and voice, and is a technology that optimizes the system's operation based on that information.

[1781] "Proposal tone adjustment" is the process of adapting the presentation and wording of a proposal's content to suit the user's emotional state.

[1782] A "personalized shopping experience" is a method for increasing user satisfaction by providing a shopping experience that is customized based on the preferences, needs, and emotions of each individual user.

[1783] The present invention provides a system for generating a new proposal based on the format and content of an existing proposal, and for adjusting the content and tone of the proposal depending on the user's emotional state. A specific embodiment of this system is described below.

[1784] System Configuration

[1785] The system includes a server, a terminal, a user interface, a database, and an emotion recognition engine. The server is responsible for storing data, training the generative AI, extracting information, and generating proposals. The emotion recognition engine recognizes users' emotions and reflects that information in the generation and adjustment of proposals.

[1786] Initial settings and database creation

[1787] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick search and retrieval of information.

[1788] Training generative AI

[1789] The server uses the proposal data in the database to train the generative AI, which is then able to generate high-quality proposals tailored to new situations.

[1790] User interaction and data entry

[1791] Users access the system through their terminals and input information to create proposals. Specifically, users enter basic information about the corporate client (company name, industry, size) and information about the product they are proposing (product name, features, price) into the interface. At this time, an emotion recognition engine recognizes the user's emotions and collects data.

[1792] Receiving and analyzing information

[1793] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data in the database based on the analysis results.

[1794] Format and content extraction

[1795] The server extracts the appropriate format and related content from the database based on the analysis results. For example, if a user proposes ERP software to a manufacturing customer, the server extracts the proposal format and related content for the manufacturing industry.

[1796] Proposal generation

[1797] The server uses the extracted format and content to run a generative AI to generate a new proposal. The emotion recognition engine then adjusts the content and tone of the proposal based on the user's emotional data collected. For example, if the user expresses positive emotions, the proposal will reflect a positive tone.

[1798] Proposal submission

[1799] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[1800] Review and edit the proposal

[1801] The user can review the provided proposal on their device and make any necessary corrections or additions using the interface. For example, they can adjust the content to meet specific customer requirements. The emotion recognition engine also continuously monitors the user's emotional changes and reflects them in the editing process.

[1802] Finalize and send

[1803] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[1804] Save the proposal

[1805] The server stores the final proposal it receives in a database, where it indexes the proposal so that other sales representatives can refer to it when creating future proposals.

[1806] Hardware and software used

[1807] Facial Recognition Camera: Commonly Used Webcam

[1808] Smart glasses or head-mounted displays (HMDs): For example, Oculus Quest 2

[1809] Emotion Recognition: Pipeline Methods in the Transformers Library

[1810] VR Interface: Virtual 3D VR Library

[1811] Specific examples

[1812] A user visits a virtual store and puts on smart glasses. The system analyzes the user's facial expressions and voice, and if the user appears happy, it will proactively suggest products (e.g., new or popular items). On the other hand, if the user appears tired, it will suggest relaxation goods. This personalizes the user's shopping experience and increases satisfaction.

[1813] Example prompts to input to the generative AI model

[1814] "If the user is feeling relaxed, suggest products that will help them relax."

[1815] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1816] Processing Steps

[1817] Step 1:

[1818] Initial settings and database creation

[1819] The server collects the format and content of previously used proposals and stores them in a database, which is categorized by industry and category, allowing for quick information retrieval.

[1820] Input: Past proposal data

[1821] Output: A structured database

[1822] Step 2:

[1823] Training generative AI

[1824] The server uses the proposal data in the database to train the generative AI model, giving it the ability to adapt to new situations and generate high-quality proposals.

[1825] Input: Proposal data in the database

[1826] Output: A trained generative AI model

[1827] Step 3:

[1828] User interaction and data entry

[1829] Users access the system using a terminal and enter basic information (company name, industry, size) and details of the proposed product (product name, features, price) to create a proposal. At this time, the emotion recognition engine analyzes the user's emotions in real time and collects data.

[1830] Input: User's basic information, item information, facial expressions and voice data

[1831] Output: User input information and emotion data

[1832] Step 4:

[1833] Receiving and analyzing information

[1834] The server receives the information and emotion data sent by the user, analyzes them, and prepares to search for related data from the database based on the analysis results.

[1835] Input: User input information, emotion data

[1836] Output: Analysis results, search criteria

[1837] Step 5:

[1838] Format and content extraction

[1839] Based on the analysis results, the server extracts the appropriate format and content from the database, for example, selecting a proposal format for the manufacturing industry and related content.

[1840] Input: Analysis results, database

[1841] Output: appropriate format and content

[1842] Step 6:

[1843] Proposal generation

[1844] The server uses the extracted format and content to run a generative AI to generate a new proposal, adjusting the tone and content of the proposal based on the user's emotional data collected by the emotion recognition engine.

[1845] Input: Extracted format, content, and sentiment data

[1846] Output: New proposal

[1847] Step 7:

[1848] Proposal submission

[1849] The server temporarily stores the generated proposal and provides it to the user via the terminal, at which point the user can review the proposal.

[1850] Enter: New Proposal

[1851] Output: Temporarily save the proposal and provide it to the user

[1852] Step 8:

[1853] Review and edit the proposal

[1854] The user can use the device to check the proposal and make any necessary corrections or additions. The emotion recognition engine monitors the user's emotional changes and reflects them in the editing process.

[1855] Input: Proposal, edits, sentiment data

[1856] Output: Revised and added proposal

[1857] Step 9:

[1858] Finalize and send

[1859] The user completes the editing and confirms the final version of the proposal. By pressing the confirm button, the proposal is sent to the server.

[1860] Input: Final edited proposal

[1861] Output: Send the final proposal to the server

[1862] Step 10:

[1863] Save the proposal

[1864] The server stores the final proposals it receives in a database and indexes them for future reference.

[1865] Input: Final proposal

[1866] Output: Stored in database, indexed

[1867] 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.

[1868] 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.

[1869] 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 robot 414.

[1870] 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.

[1871] 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.

[1872] 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.

[1873] 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).

[1874] 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.

[1875] 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."

[1876] 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.

[1877] 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).

[1878] 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.

[1879] 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.

[1880] 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.

[1881] 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.

[1882] 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.

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] The following is further disclosed regarding the above embodiment.

[1889] (Claim 1)

[1890] A means for storing the format and content of previously used proposal materials in a database;

[1891] means for training a generating AI based on the format and content of the proposal material;

[1892] A means for receiving information input by a user for creating a proposal document;

[1893] means for extracting the appropriate format and content from a database based on the received information;

[1894] A means for generating new proposal materials using a generation AI based on the extracted format and content;

[1895] A means for providing the generated proposal material to a user;

[1896] a means for users to review and edit the submitted proposal materials;

[1897] The system includes a means for storing the final edited proposal materials in a database.

[1898] (Claim 2)

[1899] 10. The system of claim 1, further comprising means for providing an interface for a user to input basic information about the corporate customer and information about the products to be proposed.

[1900] (Claim 3)

[1901] The system of claim 1, further comprising means for transmitting the proposal material generated by the generation AI to a terminal for a user to review and edit.

[1902] "Example 1"

[1903] (Claim 1)

[1904] A means for storing the format and content of previously used proposal materials in a database;

[1905] means for training a generative AI model based on the format and content of the proposal materials;

[1906] A means for receiving information input by a user for creating a proposal document;

[1907] means for extracting appropriate format and content from a database based on said received information;

[1908] A means for generating new proposal materials using a generation AI model based on the extracted format and content;

[1909] A means for providing the generated proposal material to a user;

[1910] a means for users to review and edit the submitted proposal materials;

[1911] A means of storing the final edited proposal materials in a database;

[1912] A system that includes a means for indexing proposal materials to make them reusable.

[1913] (Claim 2)

[1914] 10. The system of claim 1, further comprising means for providing an input device for a user to input basic information of the corporate customer and information on the products to be proposed.

[1915] (Claim 3)

[1916] 10. The system of claim 1, further comprising means for transmitting proposal materials generated by the generative AI model to a terminal for review and editing by a user.

[1917] "Application Example 1"

[1918] (Claim 1)

[1919] A means for storing the format and content of previously used proposal materials in a database;

[1920] A means for training a generating AI based on the format and content of the proposal material;

[1921] A means for receiving information input by a user for creating a proposal document;

[1922] means for extracting the appropriate format and content from a database based on the received information;

[1923] A means for generating new proposal materials using a generation AI based on the extracted format and content;

[1924] A means for machines operating in factories to collect production data in real time and generate proposals for parts shortages and optimization of production plans.

[1925] A means for providing the generated proposal material to a user;

[1926] a means for users to review and edit the submitted proposal materials;

[1927] The system includes a means for storing the final edited proposal materials in a database.

[1928] (Claim 2)

[1929] 10. The system of claim 1, further comprising: means for providing an interface for a user to input basic information of the corporate customer and suggested product information.

[1930] (Claim 3)

[1931] The system of claim 1, further comprising means for transmitting the proposal material generated by the generation AI to a terminal for a user to review and edit.

[1932] "Example 2: Combining Emotion Engines"

[1933] (Claim 1)

[1934] A means of storing the format and content of previously used proposal materials in a database;

[1935] means for training a generating AI based on the format and content of the proposal material;

[1936] A means for receiving information input by a user for creating a proposal document;

[1937] means for extracting the appropriate format and content from a database based on the received information;

[1938] A means for generating new proposal materials using a generation AI based on the extracted format and content;

[1939] A means for providing the generated proposal material to a user;

[1940] a means for users to review and edit the submitted proposal materials;

[1941] A means of storing the final edited proposal materials in a database;

[1942] A means of recognizing user emotions and reflecting that data in proposal materials,

[1943] a means for temporarily storing the generated proposal materials and providing them to the user through a terminal;

[1944] The system includes means for adjusting the content and tone of the proposal material using the emotional data when the user edits the proposal material.

[1945] (Claim 2)

[1946] 10. The system of claim 1, further comprising means for providing an interface for a user to input basic information about the corporate customer and information about the products to be proposed.

[1947] (Claim 3)

[1948] The system of claim 1, further comprising means for transmitting the proposal material generated by the generation AI to a terminal for a user to review and edit.

[1949] "Application example 2 when combining emotion engines"

[1950] (Claim 1)

[1951] a means for storing in a database the format and content of previously used proposals;

[1952] means for training a generative AI based on the format and content of the proposal;

[1953] means for receiving information entered by a user for creating a proposal;

[1954] means for extracting the appropriate format and content from a database based on the received information;

[1955] A means for generating a new proposal using a generation AI based on the extracted format and content;

[1956] means for providing the generated proposal to a user;

[1957] a means for the user to review and edit the submitted proposal;

[1958] A means of storing the final edited proposal in a database;

[1959] A means for analyzing a user's emotions in real time using an emotion recognition engine;

[1960] means for adjusting the content and tone of the proposal based on the user's emotional state;

[1961] A system including:

[1962] (Claim 2)

[1963] 10. The system of claim 1, further comprising means for providing an interface for a user to input basic information of the corporate customer and information on the proposed product.

[1964] (Claim 3)

[1965] 10. The system of claim 1, further comprising means for transmitting the proposal generated by the generation AI to a terminal for review and editing by a user. [Explanation of symbols]

[1966] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for storing the format and content of previously used proposal materials in a database; means for training a generating AI based on the format and content of the proposal material; A means for receiving information input by a user for creating a proposal document; means for extracting the appropriate format and content from a database based on the received information; A means for generating new proposal materials using a generation AI based on the extracted format and content; A means for providing the generated proposal material to a user; a means for users to review and edit the submitted proposal materials; The system includes a means for storing the final edited proposal materials in a database.

2. The system according to claim 1 , further comprising means for providing an interface for a user to input basic information about a corporate customer and information about a product to be proposed.

3. The system of claim 1 , further comprising means for transmitting the proposal material generated by the generation AI to a terminal for a user to review and edit.

Images