system

Abstract

We provide the system. [Solution] A means of researching customer industries and corporate challenges using generative artificial intelligence based on input information, A method for analyzing research results and automatically generating proposal components, A means to acquire past proposals and related documents by integrating with existing systems, A means of using the acquired data for analysis and generating a draft of the proposal, A method for providing the user with a generated draft proposal and for the user to finalize the proposal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Currently, when a company creates a proposal for a customer, it takes a lot of time and effort, such as researching the industry and company issues, generating parts of the proposal, and using existing materials. As a result, the time required for proposal creation increases, and efficiency decreases. In addition, there is also a problem that the quality of the proposal is not constant because the data and information collected and analyzed manually are limited. Furthermore, it is difficult to efficiently use past proposals and related materials. Means for solving these problems and improving the efficiency and quality of proposal creation are required. The purpose of this invention is to solve these problems, reduce the workload of users, and improve the efficiency of proposal creation.

Means for Solving the Problems

[0005] This invention provides a means for researching customer industries and corporate challenges using generative artificial intelligence based on input information, and a means for analyzing the research results and automatically generating proposal components. Furthermore, by including a means for integrating with existing systems to acquire past proposals and related materials, it provides a means for using the collected materials for analysis and generating a proposal draft. The invention also provides a system that includes a means for providing the generated proposal draft to the user and for the user to finalize the proposal, thereby improving the efficiency and quality of proposal creation. Additionally, it includes means for preparing to sell the generated proposal creation support function to external customers, and means for verifying the validity of user-provided information and returning error messages if inappropriate information is entered, thereby enhancing reliability and convenience. In this way, the time and effort required for proposal creation can be significantly reduced, and the quality of proposals can be improved.

[0006] "Generative artificial intelligence" refers to a system that uses natural language processing and machine learning to generate appropriate data or extract specific knowledge based on input information.

[0007] "Research" refers to investigative activities conducted to collect specific information or data, and to using this information as a basis for analysis and decision-making.

[0008] "Proposal components" refer to the various elements and sections that make up a proposal, such as industry analysis, problem definition, and proposed solutions.

[0009] "Existing systems" refer to systems and databases that have been used in the past, and which store past information and materials that will be referenced when creating proposals.

[0010] A "draft proposal" is a document generated as a preliminary step before a formal proposal is submitted. It is an initial proposal format necessary for evaluation and revision.

[0011] "Analysis" is the process of examining collected data and extracting meaningful information, and is carried out to reveal patterns and trends in the data.

[0012] An "error message" is a warning message that a system displays to inform a user of input errors or inappropriate actions.

[0013] The "proposal creation support function" is a set of functions provided to efficiently create proposals, and includes processes such as research, analysis, data acquisition, and draft generation.

[0014] A "user" is an individual or corporate operator who uses this system to create a proposal.

[0015] An "external customer" is an external company or organization that purchases and uses the functions of this system. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on input information. The processing of this system's program is described below in natural language.

[0038] Information input phase

[0039] User enters information

[0040] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, manufacturing industry, proposal for efficiency improvements."

[0041] Research phase

[0042] The server receives the information.

[0043] The server receives information entered by the user and verifies its format. Validation checks are performed as needed.

[0044] The server calls a generative artificial intelligence.

[0045] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct it to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[0046] Data Analysis Phase

[0047] The server analyzes the data.

[0048] The server analyzes the data received from the generative artificial intelligence. Based on the analysis results, it automatically generates parts of the proposal. For example, it generates sections including "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[0049] Data collection phase

[0050] The server integrates with the existing system.

[0051] The server integrates with existing systems to retrieve past proposals and related documents. For example, it can retrieve past proposals to a specific company and incorporate that information into new proposals.

[0052] Proposal generation phase

[0053] The server generates a draft proposal.

[0054] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions.

[0055] Proposal submission phase

[0056] The server provides the user with a draft proposal.

[0057] The server sends the generated draft proposal to the user, who then reviews it on their terminal. The user makes final adjustments based on the draft and completes the proposal.

[0058] External sales preparation phase

[0059] Servers are ready for sale to external customers.

[0060] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations, and explains how to use the system.

[0061] The above describes a specific embodiment of the proposal creation support system of the present invention.

[0062] The following describes the processing flow.

[0063] Step 1:

[0064] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is then sent to the server.

[0065] Step 2:

[0066] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[0067] Step 3:

[0068] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0069] Step 4:

[0070] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data. Specifically, it extracts highly relevant information from the collected data and classifies and organizes it as components of a proposal (industry analysis, problem analysis, solutions, etc.).

[0071] Step 5:

[0072] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." This retrieved material will then be used as reference data for the new proposal.

[0073] Step 6:

[0074] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[0075] Step 7:

[0076] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their terminal and reviews its contents. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[0077] Step 8:

[0078] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[0079] The above is the specific processing flow of the proposal creation support system.

[0080] (Example 1)

[0081] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0082] Traditional proposal writing processes are inefficient, requiring a great deal of manual work such as information gathering, analysis, and referencing past proposals. Furthermore, creating proposals based on accurate information demands specialized knowledge, requiring significant time and effort. Additionally, the preparation process for providing proposal writing support systems to external clients is cumbersome. This creates a significant obstacle, especially for companies aiming to improve operational efficiency.

[0083] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0084] In this invention, the server includes means for the user to input information into an input form on the terminal, means for the server to receive the input information and check its format and validity, means for the server to call a generation AI model based on the input information and perform research, means for the server to analyze the data received from the generation AI model and generate proposal components based on the analysis results, means for the server to acquire past proposals and related materials in cooperation with existing systems, means for the server to generate a draft proposal using the acquired materials and analysis results, and means for the server to provide the generated draft proposal to the user so that the user can finalize the proposal. This enables the efficient and highly accurate automatic generation of proposals and smooth preparation for sales to external customers.

[0085] "User" refers to the end user who inputs information to create a proposal using the system.

[0086] A "terminal" refers to a hardware device used by a user to input information, and specifically includes personal computers, smartphones, and tablets.

[0087] A "server" refers to a computer system that receives input from users and performs processing using AI models for information analysis and generation.

[0088] An "input form" refers to a web-based interface that allows users to input the information necessary for creating a proposal from their device.

[0089] A "generative AI model" refers to an artificial intelligence model that automatically performs research and generates data based on the information provided.

[0090] "Research" refers to the process of collecting information on a specified topic using a generative AI model.

[0091] "Data analysis" refers to the analytical process of processing data received from a generative AI model to generate components for a proposal.

[0092] "Parts of a proposal" refer to the individual sections or elements that make up a proposal, such as industry analysis and problem analysis.

[0093] "Existing systems" refers to databases and storage systems that store past proposals and related documents that the servers are connected to.

[0094] A "draft proposal" refers to the initial version of a proposal generated by the server, an incomplete document before the user finalizes it.

[0095] "External customers" refer to third-party companies or individuals who purchase the system's proposal creation support functionality.

[0096] "Sales preparation" refers to the process of preliminary preparations such as marketing, demonstrations, and document creation for providing a system to external customers.

[0097] "Validation check" refers to the process of verifying whether the information entered by the user is accurate and complete, and returns an error message if inaccurate or incomplete information is entered.

[0098] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on the input information. The processing of this system's program will be described in detail below.

[0099] Users input information for creating proposals using their devices. These devices can include personal computers or smartphones. Specifically, the information provided by the user might include phrases like "Company A, Manufacturing Industry, Proposal for Efficiency Improvement." The input form is a web form using HTML or JavaScript (registered trademark). For example, the user might input specific details such as "Company A, New Product Development, Proposal for Innovative Technology."

[0100] When information is entered, the server receives it. The server uses a message queue system such as Apache® Kafka or RabbitMQ to receive the information and check its format and validity. It checks the format of the received information to ensure that all required fields are filled in and that no inappropriate information is included. To verify validity, it checks whether the entered content is in the correct format and returns an error message if inappropriate information is entered.

[0101] The server uses properly formatted information to generate AI models (for example, OpenAI's GPT-4 model) to perform research. For example, it might be instructed to research "the latest trends and case studies of efficiency improvements in the manufacturing industry." The prompt in this case would be, "Please tell me about the latest trends and success stories of efficiency improvements in the manufacturing industry."

[0102] When the AI ​​model provides data, the server analyzes it. Data analysis uses Python's Pandas and NumPy libraries. Based on the analysis results, the server automatically generates proposal components. Specifically, it embeds the generated data into a template and creates sections such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[0103] Furthermore, the server integrates with existing systems to retrieve past proposals and related documents. The server uses databases such as MySQL® or PostgreSQL to extract the necessary data and incorporate it into the new proposal. This makes it possible to retrieve past "proposals to a certain company" and reflect them in the new proposal.

[0104] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions. Document generation tools such as LaTeX and Markdown are used to generate the proposal. Specifically, a template engine is used to embed the data in the appropriate places and convert it into the final document format.

[0105] The generated draft proposal is sent from the server to the user. This is done via email or a dedicated web interface, and the user reviews the draft proposal on their device. The user then makes any necessary final adjustments based on the submitted draft proposal to complete the proposal.

[0106] Finally, the server prepares to provide proposal creation support functions to external customers. Specifically, this includes preparing digital marketing materials and demonstrations. Marketing materials are created using Adobe Creative Cloud, and demonstrations are conducted using Zoom and Microsoft Teams.

[0107] The above describes a specific embodiment of the proposal creation support system of this invention.

[0108] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0109] Step 1:

[0110] User enters information

[0111] The user enters information into an input form on their device. This information includes company name, industry, and proposal details, all necessary for creating a proposal. The input form is implemented as a web form using HTML and JavaScript. Once the input data is submitted, the device sends that data to the server.

[0112] Specific actions

[0113] Fill in the input form with specific details such as "Company Name, Manufacturing Industry, Proposal for Efficiency Improvement," and click the "Submit" button.

[0114] Input: Information entered by the user (company name, industry, proposal details)

[0115] Output: Information is sent from the terminal to the server.

[0116] Step 2:

[0117] The server receives the information and checks its format and validity.

[0118] The server processes the information received from the terminal and checks the format and validity of the input data. Using a message queue system such as Apache Kafka or RabbitMQ, it verifies after receiving the data whether the format is correct and whether all required fields are present. If the validity is not confirmed, it generates an error message and sends it back to the terminal.

[0119] Specific actions

[0120] The system checks whether the received data is in the correct format, and if the data is inappropriate, it returns an error message such as "Company name is not entered."

[0121] Input: Information sent from the device

[0122] Output: Formatted information, or error message.

[0123] Step 3:

[0124] The server calls the generated AI model to perform research.

[0125] The server calls a generating AI model (such as OpenAI's GPT-4) based on the input information. It issues specific research instructions and collects the necessary data. It uses specific sentences as prompts, such as "Please tell me about the latest trends and examples of efficiency improvements in the manufacturing industry."

[0126] Specific actions

[0127] This process sends a prompt to a generative AI model to retrieve information about a specified topic. The retrieved data is also temporarily stored.

[0128] Input: Formatted information

[0129] Output: Research data received from the generative AI model

[0130] Step 4:

[0131] The server analyzes the data and generates parts for the proposal.

[0132] The server analyzes the data received from the generated AI model using Python libraries such as Pandas and NumPy. Based on the analysis results, it automatically generates components for the proposal document.

[0133] Specific actions

[0134] Based on the analysis results, sections of the proposal document such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories" are generated. Unnecessary data is filtered out during the analysis process.

[0135] Input: Data received from the generated AI model

[0136] Output: Proposal parts (sections)

[0137] Step 5:

[0138] The server retrieves data in conjunction with the existing system.

[0139] The server retrieves past proposals and related documents from existing databases such as MySQL and PostgreSQL. This makes it possible to reference past data in new proposals.

[0140] Specific actions

[0141] Use SQL queries to extract necessary data from the database and incorporate the processing results into a draft of the new proposal.

[0142] Input: Request for necessary past proposals and related documents

[0143] Output: Past proposals and related document data

[0144] Step 6:

[0145] The server generates the draft proposal.

[0146] The server generates a draft proposal based on the collected data and analysis results. This draft proposal includes industry analysis, problem analysis, and proposed solutions. It is then converted into a document format using document generation tools such as LaTeX or Markdown.

[0147] Specific actions

[0148] A template engine is used to embed proposal components in the appropriate locations. Finally, it is converted to formats such as PDF and Word.

[0149] Input: Analysis results and existing documents

[0150] Output: Draft proposal

[0151] Step 7:

[0152] The server provides the user with a draft proposal.

[0153] The server sends the generated draft proposal to the user. This is done via email or a dedicated web interface. The user reviews the draft proposal on their terminal and makes any necessary final adjustments.

[0154] Specific actions

[0155] The draft proposal will be generated in formats such as PDF files and provided via email attachment or web dashboard.

[0156] Input: Generated proposal draft

[0157] Output: Draft proposal provided to the user

[0158] Step 8:

[0159] The server prepares for sale to external customers.

[0160] The server prepares to provide proposal creation support functions to external customers. It also prepares digital marketing materials and demonstrations.

[0161] Specific actions

[0162] We will create marketing materials using Adobe Creative Cloud and conduct demonstrations using Zoom, Microsoft Teams, and other tools.

[0163] Input: System sales materials and demonstration content

[0164] Output: Marketing materials and demonstrations provided to external customers.

[0165] (Application Example 1)

[0166] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0167] In modern business processes, particularly in the operation of logistics centers, the creation of proposals quickly and effectively is essential. However, traditional methods require considerable time and effort, and make it difficult to efficiently utilize the latest information and past proposals. Furthermore, there is a lack of systems that allow for information input, confirmation, and modification on mobile devices, hindering operational efficiency. Against this backdrop, there is a need for a system that efficiently researches industry trends and specific case studies and automatically generates high-quality proposals.

[0168] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0169] In this invention, the server includes means for researching target fields and issues using generative artificial intelligence based on input information, means for analyzing the research results and automatically generating parts of a proposal document, and means for linking with an existing database to acquire past proposal documents and related materials. This enables users to quickly create proposals based on the latest industry trends and specific examples, and to easily input, confirm, and modify information via a mobile device. Furthermore, the system's convenience and reliability are improved by including means for preparing to sell the generated proposal document creation support function to external consumers, and means for verifying the validity of information provided by users and returning error messages if inappropriate information is entered.

[0170] "Inputted information" refers to the data and detailed information that the user provides to the system for creating the proposal.

[0171] "Generative artificial intelligence" refers to an artificial intelligence model that can automatically generate and analyze information based on provided data.

[0172] "Target field" refers to the specific industry or field that is the subject of research or proposal writing.

[0173] A "problem" refers to an issue that needs to be solved or an area for improvement within the field in question.

[0174] The "research method" refers to a function that uses generative artificial intelligence based on input information to investigate the latest industry trends and success stories.

[0175] "Means of analysis" refers to the function of analyzing data obtained from research and extracting useful information for the proposal.

[0176] "Parts of the proposal document" refers to each section or element that makes up the proposal.

[0177] "Automatic generation method" refers to a function that automatically generates a proposal document based on the analyzed results.

[0178] An "existing database" is a system that stores past proposals, related documents, industry data, and other similar information.

[0179] "Means of collaboration" refers to the function of communicating with existing databases and retrieving necessary data.

[0180] A "mobile device" is a portable information processing device such as a smartphone or tablet.

[0181] A "user" is an individual or organization that uses the system to create a proposal.

[0182] "External consumers" refers to external individuals or corporations who purchase or use the services of this system.

[0183] "Means of preparing for sale" refers to the function of preparing to offer the generated proposal creation support function to the market.

[0184] "Means of validating validity" refers to a function that verifies whether the information entered by the user is accurate.

[0185] An "error message" is a message sent to the user when there is a problem with the information they have entered.

[0186] "Reliability" refers to a system's ability to deliver accurate and consistent results.

[0187] The system for implementing this invention enables operators of logistics centers and other facilities to efficiently prepare proposals. This system consists of the following main phases.

[0188] Information input phase

[0189] Users use mobile devices (smartphones or tablets) to input the information necessary to create a proposal. For example, they enter the client name, industry name, and the purpose of the proposal. This information is collected via the input form and sent to the server.

[0190] Research phase

[0191] The server receives the input information and uses generative artificial intelligence (such as the OpenAI API) to research the latest trends and success stories related to the target field and challenges. An example of a prompt used here is, "Please research the latest trends and success stories in the logistics industry."

[0192] Data Analysis Phase

[0193] The server analyzes the data received from the generative artificial intelligence and automatically generates the proposal document. This includes details of the latest efficiency technologies and success stories. Based on the analysis results, a concrete proposal document is constructed.

[0194] Data collection phase

[0195] The server integrates with existing databases (such as proposal management systems) to retrieve past proposal documents and related materials. This information is then incorporated into the content of new proposals.

[0196] Proposal generation phase

[0197] The server generates a draft proposal document based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and details of the proposed solutions.

[0198] Proposal submission phase

[0199] The generated proposal draft is provided to the user's mobile device, allowing them to review the draft and make revisions as needed. This enables the user to finalize the proposal quickly and effectively.

[0200] External sales preparation phase

[0201] The server prepares to sell the generated proposal document creation support function to external consumers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system.

[0202] Furthermore, the system includes a function to verify the validity of information provided by users and return an error message if inappropriate information is entered. This improves the reliability and usability of the system.

[0203] Ultimately, this system enables logistics center operators to quickly propose operational efficiency improvements and enhancements, and to easily input, verify, and modify information via mobile devices. In this way, the entire proposal creation process is significantly streamlined.

[0204] The following is an example of a prompt statement:

[0205] 1. "Please research the latest trends and success stories in the logistics industry."

[0206] 2. "Please explain how the latest trends in efficiency technologies can be applied to logistics centers."

[0207] The main hardware used will be smartphones, tablets, and servers, while the software will include the OpenAI API, APIs for existing proposal management systems, Python, and the Requests library.

[0208] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0209] Step 1:

[0210] The user enters information using a mobile device. Specifically, they fill in information such as the client name, industry name, and the purpose of the proposal in an input form. This information is then sent from the device to the server.

[0211] Input: Client name, industry, purpose of the proposal, etc.

[0212] Output: Input information sent to the server.

[0213] Step 2:

[0214] Based on the information received by the server, prompts are sent to the generative AI model. For example, a prompt such as "Research the latest trends and success stories in the logistics industry" might be sent to the generative AI model (e.g., via the OpenAI API).

[0215] Input: Client name, industry, purpose of the proposal.

[0216] Output: Prompts for the generative AI model and research result data from the generative AI model.

[0217] Step 3:

[0218] The server analyzes the research results obtained from the generated AI model. Specifically, it performs text analysis on the acquired data and extracts and organizes important information that should be included in the proposed document.

[0219] Input: Research result data from a generated AI model.

[0220] Output: Analysis results with important information organized.

[0221] Step 4:

[0222] The server connects with the existing database (proposal management system) to retrieve past proposal documents and related materials. If necessary, the server sends an API request to download the materials.

[0223] Input: Information such as client name and industry.

[0224] Output: Past proposal documents and related materials.

[0225] Step 5:

[0226] The server automatically generates a draft of the proposal document based on the analysis results and acquired data. Specifically, it generates each section that makes up the entire proposal document, such as industry analysis and solutions.

[0227] Input: Analysis results, past proposal documents, and related materials.

[0228] Output: Draft of the proposal document.

[0229] Step 6:

[0230] The server provides a draft of the proposal document to the mobile device, allowing the user to review and modify it. The user then makes revisions on the device and finalizes the proposal document.

[0231] Input: Draft of the proposal document.

[0232] Output: Finalized proposal document.

[0233] Step 7:

[0234] Prepare marketing materials and demonstrations to provide external consumers with the proposal document creation support function generated by the server.

[0235] Input: A sample of the overall system functionality and proposed document.

[0236] Output: Marketing materials, demo content.

[0237] Through the steps outlined above, users will be able to create high-quality proposal documents efficiently and quickly.

[0238] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0239] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates a proposal based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposal and user satisfaction.

[0240] Information input phase

[0241] User enters information

[0242] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotion data from the user's facial expressions and input.

[0243] Research phase

[0244] The server receives the information.

[0245] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed.

[0246] The server calls a generative artificial intelligence.

[0247] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0248] Data Analysis Phase

[0249] The server analyzes the data.

[0250] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates parts for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[0251] Data collection phase

[0252] The server integrates with the existing system.

[0253] The server integrates with existing systems to retrieve past proposals and related documents. For example, the server accesses an existing proposal database to retrieve "past proposals for a certain company." This retrieved material is then used as reference data for new proposals.

[0254] Proposal generation phase

[0255] The server generates a draft proposal.

[0256] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format. Furthermore, it adjusts the tone and content of the proposal, taking into account user sentiment data analyzed by the sentiment engine.

[0257] Proposal submission phase

[0258] The server provides the user with a draft proposal.

[0259] The server provides the user with a draft proposal. The user receives the draft proposal on their device and reviews its contents. The emotion engine analyzes the user's real-time reactions and provides support messages if negative emotions are detected. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[0260] External sales preparation phase

[0261] The server is preparing to sell its proposal creation support function to external customers.

[0262] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[0263] The above is a specific implementation of a proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[0264] The following describes the processing flow.

[0265] Step 1:

[0266] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotional data from the user's facial expressions, input speed, and other factors.

[0267] Step 2:

[0268] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[0269] Step 3:

[0270] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0271] Step 4:

[0272] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates components for the proposal (industry analysis, problem analysis, proposed solutions, etc.). For example, it generates sections including "latest trends in efficiency technologies" and "details of success stories."

[0273] Step 5:

[0274] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." These retrieved documents will then be used as reference data for the new proposal.

[0275] Step 6:

[0276] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[0277] Step 7:

[0278] The emotion engine analyzes the emotion data collected from the user. If the user feels anxiety or stress during the proposal creation, the server generates an appropriate support message and displays it on the terminal. For example, a message such as "Do you need additional information about this part?" will be displayed.

[0279] Step 8:

[0280] The server provides the user with a draft proposal. The user receives the draft proposal on the terminal and checks the content. The emotion engine analyzes the user's real-time reaction. If positive emotions are shown, it is confirmed that the content of the proposal is appropriate. If negative emotions are detected, additional corrections and advice are provided.

[0281] Step 9:

[0282] The user completes the final proposal based on the draft proposal. The user makes additional edits and customizations on the terminal. During the process of completing the proposal, the emotion engine monitors the user's feedback and provides further support if necessary.

[0283] Step 10:

[0284] The server prepares to sell the proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations and explains how to use the system. This enables external customers to efficiently create proposals using the system.

[0285] The above is the specific processing flow of the proposal creation support system combined with the emotion engine. This system aims to improve the efficiency and quality of proposal creation and enhance user satisfaction.

[0286] (Example 2)

[0287] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0288] In proposal creation, there are challenges in automatically verifying the validity of user input and ensuring that the content and tone of the proposal meet user expectations, thereby improving user satisfaction. Furthermore, there is a lack of means to improve proposal quality by considering user emotions, thus creating a need for both increased efficiency and higher quality in proposal creation.

[0289] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0290] In this invention, the server includes means for receiving user-inputted information and verifying its validity; means for researching industries and issues based on the input information using generative artificial intelligence; means for analyzing the research results and automatically generating sections for the proposal; means for acquiring past data in cooperation with existing systems; means for using the acquired data for analysis and generating a draft proposal; means for acquiring user emotion data using an emotion recognition engine and adjusting the tone and content of the proposal; and means for providing the generated draft proposal to the user, analyzing the user's reaction in real time, and providing support messages. This makes it possible to automatically verify the validity of the user's input information and improve user satisfaction and the quality of the proposal by ensuring that the generated proposal has a tone and content that reflects the user's emotions.

[0291] "Means for receiving user-entered information and verifying its validity" refers to a function that allows a server to receive information entered by a user into the system and check whether that information is accurate and complete.

[0292] "A means of researching industries and issues based on input information using generative artificial intelligence" refers to a function in which a server utilizes generative artificial intelligence to collect the latest industry information and issues related to the information entered by the user from the internet or internal databases.

[0293] "A means of analyzing research results and automatically generating sections of a proposal" refers to a function in which the server analyzes research results obtained from a generative artificial intelligence and automatically creates each section of the proposal based on that information.

[0294] "Methods for retrieving past documents by linking with existing systems" refers to a function that allows the server to link with existing document management systems and databases to retrieve proposals and related documents created in the past.

[0295] "A means of using acquired data for analysis and generating a draft proposal" refers to a function that uses past data acquired by the server for analysis and creates a draft of a new proposal based on that data.

[0296] "A means of acquiring user emotional data using an emotion recognition engine and adjusting the tone and content of the proposal" refers to a function in which the server uses an emotion recognition engine to collect user emotional data and then appropriately adjusts the tone and content of the proposal based on the results.

[0297] "A means of providing users with generated draft proposals, analyzing user reactions in real time, and providing support messages" refers to a function in which the server provides users with generated draft proposals, analyzes users' real-time reactions through an emotion recognition engine, and sends support messages as needed.

[0298] "Means of preparing to sell the generated proposal creation support function to external customers" refers to the function that prepares the server to sell the proposal creation support function to external users. This preparation includes creating marketing materials and demonstrations.

[0299] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates proposals based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposals and user satisfaction.

[0300] First, the user enters the necessary information for creating the proposal into the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server, and at the same time, the emotion engine collects emotion data from the user's facial expressions and input.

[0301] Next, the server checks the received information for validation. It verifies whether the entered company name, industry, and purpose of the proposal are valid, and checks the format and required fields as needed. If inappropriate information is entered, the server returns an error message to the user.

[0302] Next, the server invokes a generative artificial intelligence (e.g., GPT-4) and instructs it to research industries and issues based on the input information. For example, it might be instructed to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI searches the internet and internal databases to collect relevant information.

[0303] The server analyzes research results sent from the generative artificial intelligence and automatically generates sections for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[0304] Subsequently, the server integrates with the existing system to retrieve past proposals and related documents. It accesses the existing document management system (DMS) and retrieves "past proposals to a certain company." These documents are used as reference materials for the new proposal.

[0305] Next, the server generates a draft proposal based on the collected research results and the obtained materials. The emotion recognition engine adjusts the tone and content based on the user's emotion data. For example, when the user is nervous, the style of the proposal is made more friendly.

[0306] The server provides the generated draft proposal to the user, and the user checks the draft proposal on the terminal. The emotion recognition engine analyzes the user's real-time reaction and provides a support message when negative emotions are detected.

[0307] Finally, the server prepares to sell the proposal creation support function to external customers. This includes creating marketing materials and demonstrations. For example, prepare a video of the function description, a user manual, etc., and conduct sales promotion activities.

[0308] As a specific example, when the user inputs information such as "a certain company, manufacturing industry, proposal for efficiency improvement", an example of the prompt sentence for the generation-based artificial intelligence is as follows.

[0309] "Research on the latest efficiency improvement technologies and their success stories in the manufacturing industry. In particular, provide information focusing on the trends of automation and data analysis technologies in the manufacturing line. Also, investigate in detail the representative success stories in the past five years."

[0310] With this system, the user can easily create a high-quality proposal, and the quality of the proposal and the user's satisfaction are greatly improved.

[0311] The flow of the specific process in Example 2 will be described using FIG. 13.

[0312] Step 1:

[0313] The user inputs information

[0314] The user enters necessary information such as company name, industry, and purpose of the proposal into the input form on the terminal. An example of the information to be entered is "Company X, manufacturing industry, proposal for efficiency improvement."

[0315] Input: Company name, industry, purpose of proposal

[0316] Output: Input data sent to the server

[0317] Step 2:

[0318] The server receives the information and verifies its validity.

[0319] The server receives information sent by the user and checks the format of the entered data and whether all required fields are present. For example, it verifies whether the company name is entered correctly and whether the industry name is valid. If inappropriate information is entered, an error message is returned to the user.

[0320] Input: Data entered by the user

[0321] Output: Valid data, error messages (if necessary)

[0322] Step 3:

[0323] The server invokes a generative artificial intelligence to instruct it on research.

[0324] Based on the input information, the server issues research instructions to a generative artificial intelligence (e.g., GPT-4). It generates a prompt and sends an instruction to the generative AI to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[0325] Input: Valid input data

[0326] Output: Prompt message, data to send to the generative AI.

[0327] Step 4:

[0328] Generative artificial intelligence begins research

[0329] Generative artificial intelligence searches the internet and internal databases, collecting relevant information according to instructions. It then sends the research results to a server. For example, it might collect data on the latest efficiency technologies and success stories.

[0330] Input: Prompt message

[0331] Output: Research results data

[0332] Step 5:

[0333] The server analyzes the data and generates sections for the proposal.

[0334] The server receives research results returned by the generative artificial intelligence and analyzes them. Based on the analysis, it automatically generates sections for the proposal. For example, it creates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[0335] Input: Research result data

[0336] Output: Section data of the proposal

[0337] Step 6:

[0338] The server retrieves data in conjunction with the existing system.

[0339] The server integrates with existing systems such as document management systems (DMS) to retrieve past proposals and related documents. For example, it can retrieve "past proposals to a certain company" and use them as reference material for new proposals.

[0340] Input: Information about existing systems, company name

[0341] Output: Historical document data

[0342] Step 7:

[0343] The server generates a draft proposal.

[0344] The server generates a draft proposal based on research results and acquired materials. It uses an emotion recognition engine to obtain user emotion data and adjusts the tone and content of the proposal accordingly. For example, if the user is nervous, the writing style is made more approachable.

[0345] Input: Research results data, historical data, sentiment data

[0346] Output: Draft proposal data

[0347] Step 8:

[0348] The server provides the user with a draft proposal.

[0349] The server sends the generated draft proposal to the user. The user reviews the draft proposal on their device and makes revisions as needed. Simultaneously, the emotion recognition engine analyzes the user's reactions and provides a support message if negative emotions are detected.

[0350] Input: Proposal draft data, real-time sentiment data

[0351] Output: Display of a draft proposal to the user, support messages (if necessary)

[0352] Step 9:

[0353] The server prepares to sell its proposal creation support function to external customers.

[0354] The server creates marketing materials and demonstrations to sell the proposal creation support function to external customers. For example, it prepares feature explanation videos and user manuals, and carries out sales promotion activities.

[0355] Input: Information on the proposal creation support function

[0356] Output: Marketing materials, demonstration content

[0357] The above outlines the specific processing steps and details of the proposal creation support system. Through these steps, users can efficiently create high-quality proposals.

[0358] (Application Example 2)

[0359] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0360] Conventional proposal creation support systems automatically generate proposals based on information provided by the user, but they have the problem of not being able to adequately respond to customer needs and reactions because they provide proposals with uniform content and tone without considering the user's feelings. Furthermore, because they lack a mechanism to collect and reflect customer feelings and feedback in real time, it is difficult to immediately provide appropriate proposal content in sales activities at physical stores.

[0361] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0362] This invention includes a server that, based on input information, uses generative artificial intelligence to research customer industries and corporate challenges; analyzes the research results and automatically generates proposal components; collaborates with existing systems to acquire past proposals and related materials; uses the acquired materials for analysis and generates a draft proposal; provides the generated draft proposal to the user, allowing the user to finalize the proposal; and collects emotional data in real time and adjusts the content and tone of the draft proposal. This improves the quality of proposals and enables optimal proposals based on the customer's real-time emotions and needs.

[0363] "Inputted information" refers to the collection of data that users provide through input forms or devices on the system.

[0364] "Generative artificial intelligence" is an artificial intelligence technology that automatically analyzes data based on the information provided and generates relevant information.

[0365] "Research" is the process of collecting and analyzing information about the challenges facing a particular industry or company.

[0366] "Analysis" is the process of examining collected data and information in detail, extracting meaning, and understanding it.

[0367] "Proposal components" refer to some elements or sections that make up the final proposal, and include specific content and data.

[0368] "Existing systems" refer to information processing systems and databases that have been implemented in the past.

[0369] "Reference materials" refer to existing documents that are useful for creating a proposal, such as past proposals and related reference data.

[0370] A "draft proposal" is an initial document used to create the final proposal, and it contains the proposal content and data.

[0371] A "user" is an individual or company representative who uses the proposal creation support system.

[0372] "Emotional data" refers to emotional information obtained by analyzing the facial expressions and statements of users and customers.

[0373] "Real-time" refers to a time frame in which data is processed as soon as it is generated, and results are provided immediately.

[0374] "Tone" refers to the style of language and expression used in the content of a proposal or document.

[0375] This invention includes the following configuration and processes for realizing a proposal creation support system.

[0376] System Configuration

[0377] 1. Hardware Configuration

[0378] Smart glasses: Equipped with a camera to detect customer facial expressions and a display to show draft proposals.

[0379] Server: Receives and analyzes data, generates proposals, and processes sentiment data.

[0380] Edge devices: Assist in real-time processing of camera images.

[0381] 2. Software Configuration

[0382] Emotion Engine: Analyzes customer emotion data in real time from camera footage.

[0383] Proposal Generator: Generates proposal components based on user input data and sentiment data.

[0384] Generative artificial intelligence: Automatically generates proposal content based on research results.

[0385] Operation details

[0386] Information input phase

[0387] The user interacts with customers while wearing smart glasses. The smart glasses' camera captures the customer's facial expressions, and the microphone records the conversation. This data is sent to a server in real time, and simultaneously, an emotion engine is activated to analyze the customer's emotional data.

[0388] Research phase

[0389] The server uses generative artificial intelligence to research customer industries and company challenges based on the input information. Relevant information is collected and analyzed from the internet and internal databases.

[0390] Data Analysis Phase

[0391] Data, including research results, is sent to the server, and proposal components are automatically generated. This includes the latest technological trends and success stories.

[0392] Data collection phase

[0393] The server integrates with existing systems to retrieve past proposals and related documents. These documents are used for analysis to improve the quality of proposals.

[0394] Proposal generation phase

[0395] The server combines all collected data and analysis results to generate a draft proposal. Based on the emotional data obtained from the emotion engine, the content and tone of the proposal are adjusted.

[0396] Proposal submission phase

[0397] The generated proposal draft is displayed in real time on the smart glasses' screen. The salesperson uses this proposal to provide appropriate explanations to the customer and further optimizes the proposal by collecting real-time feedback from the customer.

[0398] Detailed processing instructions

[0399] The server uses Python and OpenCV to process video data and utilizes an emotion recognition engine (EmotionEngine) to perform facial expression analysis. Based on the actual emotion data, a proposal generation engine (ProposalGenerator) operates to generate proposal content. Through the coordination of each hardware and software component, optimized proposals are provided in real time, aiming to improve customer satisfaction.

[0400] Example of a prompt

[0401] "Please generate a portion of the proposal for product XYZ based on the following data. The sentiment data is [Joy: 0.8, Surprise: 0.2], and the customer appears to be interested in the product's cost-effectiveness."

[0402] Based on this prompt, the generative AI model generates appropriate proposal components, which the server then combines to complete the draft proposal. In this way, a high-quality proposal based on the user's emotional data and needs can be provided.

[0403] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0404] Step 1:

[0405] Information input phase

[0406] The user interacts with a customer while wearing smart glasses. During this interaction, a camera built into the glasses captures the customer's facial expressions, and a microphone records the conversation. The collected data is transmitted to a server in real time. The server uses the received video and audio data as input, and an emotion engine analyzes it to extract the customer's emotional data (e.g., joy, surprise, sadness). This emotional data is then output. The specific actions involved in each step include capturing camera footage, recording audio, and transmitting the data.

[0407] Step 2:

[0408] Research phase

[0409] The server uses generative artificial intelligence to conduct research based on information entered by the user (customer industry, company challenges, etc.). This research extracts relevant information from the internet and internal databases and collects optimal suggestions for the user. The input is information about the customer industry and company challenges, and the output is relevant research data (e.g., latest trends, success stories, etc.). Specifically, it performs information retrieval and data extraction.

[0410] Step 3:

[0411] Data Analysis Phase

[0412] The server receives research results and sentiment data as input and analyzes them. The research results are analyzed by generative artificial intelligence, and proposal components are automatically generated. Furthermore, the tone and content of the proposal are adjusted based on the sentiment data. The output consists of each component of the proposal. Specifically, the process includes data analysis and the generation of proposal components.

[0413] Step 4:

[0414] Data collection phase

[0415] The server integrates with existing systems to retrieve past proposals and related documents. This process involves accessing a database of past proposals and collecting information and reference materials previously provided by users. The input is existing database information, and the output is the retrieved past proposals and reference materials. Specific operations include accessing the database and retrieving the documents.

[0416] Step 5:

[0417] Proposal generation phase

[0418] The server combines all collected data and analysis results to generate a draft proposal. This draft includes content that reflects research results, historical documents, and sentiment data. Inputs include research results, historical documents, and sentiment data, and output is the generated draft proposal. Specific operations include data integration and proposal draft generation.

[0419] Step 6:

[0420] Proposal submission phase

[0421] The generated proposal draft is displayed in real time on the smart glasses' screen. This allows salespeople to immediately present the proposal to customers. The input is the proposal draft, and the output is the proposal displayed on the smart glasses' screen. Specific operations include displaying data.

[0422] In this way, data is entered at each processing step, and after going through each process, the proposal is finally displayed on smart glasses.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0424] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0426] [Second Embodiment]

[0427] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0428] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0429] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0431] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0433] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0434] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0435] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0438] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0439] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on input information. The processing of this system's program is described below in natural language.

[0440] Information input phase

[0441] User enters information

[0442] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, manufacturing industry, proposal for efficiency improvements."

[0443] Research phase

[0444] The server receives the information.

[0445] The server receives information entered by the user and verifies its format. Validation checks are performed as needed.

[0446] The server calls a generative artificial intelligence.

[0447] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct it to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[0448] Data Analysis Phase

[0449] The server analyzes the data.

[0450] The server analyzes the data received from the generative artificial intelligence. Based on the analysis results, it automatically generates parts of the proposal. For example, it generates sections including "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[0451] Data collection phase

[0452] The server integrates with the existing system.

[0453] The server integrates with existing systems to retrieve past proposals and related documents. For example, it can retrieve past proposals to a specific company and incorporate that information into new proposals.

[0454] Proposal generation phase

[0455] The server generates a draft proposal.

[0456] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions.

[0457] Proposal submission phase

[0458] The server provides the user with a draft proposal.

[0459] The server sends the generated draft proposal to the user, who then reviews it on their terminal. The user makes final adjustments based on the draft and completes the proposal.

[0460] External sales preparation phase

[0461] Servers are ready for sale to external customers.

[0462] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations, and explains how to use the system.

[0463] The above describes a specific embodiment of the proposal creation support system of the present invention.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is then sent to the server.

[0467] Step 2:

[0468] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[0469] Step 3:

[0470] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0471] Step 4:

[0472] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data. Specifically, it extracts highly relevant information from the collected data and classifies and organizes it as components of a proposal (industry analysis, problem analysis, solutions, etc.).

[0473] Step 5:

[0474] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." This retrieved material will then be used as reference data for the new proposal.

[0475] Step 6:

[0476] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[0477] Step 7:

[0478] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their terminal and reviews its contents. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[0479] Step 8:

[0480] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[0481] The above is the specific processing flow of the proposal creation support system.

[0482] (Example 1)

[0483] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0484] Traditional proposal writing processes are inefficient, requiring a great deal of manual work such as information gathering, analysis, and referencing past proposals. Furthermore, creating proposals based on accurate information demands specialized knowledge, requiring significant time and effort. Additionally, the preparation process for providing proposal writing support systems to external clients is cumbersome. This creates a significant obstacle, especially for companies aiming to improve operational efficiency.

[0485] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0486] In this invention, the server includes means for the user to input information into an input form on the terminal, means for the server to receive the input information and check its format and validity, means for the server to call a generation AI model based on the input information and perform research, means for the server to analyze the data received from the generation AI model and generate proposal components based on the analysis results, means for the server to acquire past proposals and related materials in cooperation with existing systems, means for the server to generate a draft proposal using the acquired materials and analysis results, and means for the server to provide the generated draft proposal to the user so that the user can finalize the proposal. This enables the efficient and highly accurate automatic generation of proposals and smooth preparation for sales to external customers.

[0487] "User" refers to the end user who inputs information to create a proposal using the system.

[0488] A "terminal" refers to a hardware device used by a user to input information, and specifically includes personal computers, smartphones, and tablets.

[0489] A "server" refers to a computer system that receives input from users and performs processing using AI models for information analysis and generation.

[0490] An "input form" refers to a web-based interface that allows users to input the information necessary for creating a proposal from their device.

[0491] A "generative AI model" refers to an artificial intelligence model that automatically performs research and generates data based on the information provided.

[0492] "Research" refers to the process of collecting information on a specified topic using a generative AI model.

[0493] "Data analysis" refers to the analytical process of processing data received from a generative AI model to generate components for a proposal.

[0494] "Parts of a proposal" refer to the individual sections or elements that make up a proposal, such as industry analysis and problem analysis.

[0495] "Existing systems" refers to databases and storage systems that store past proposals and related documents that the servers are connected to.

[0496] A "draft proposal" refers to the initial version of a proposal generated by the server, an incomplete document before the user finalizes it.

[0497] "External customers" refer to third-party companies or individuals who purchase the system's proposal creation support functionality.

[0498] "Sales preparation" refers to the process of preliminary preparations such as marketing, demonstrations, and document creation for providing a system to external customers.

[0499] "Validation check" refers to the process of verifying whether the information entered by the user is accurate and complete, and returns an error message if inaccurate or incomplete information is entered.

[0500] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on the input information. The processing of this system's program will be described in detail below.

[0501] Users input information for creating proposals using their devices. These devices can include PCs and smartphones. Specifically, the information provided by users might include "Company A, Manufacturing Industry, Proposal for Efficiency Improvement." The input form is a web form using HTML or JavaScript. For example, the user might input specific details such as "Company A, New Product Development, Proposal for Innovative Technology."

[0502] When information is entered, the server receives it. The server uses a message queue system such as Apache Kafka or RabbitMQ to receive the information and check its format and validity. It checks the format of the received information to ensure that all required fields are filled in and that no inappropriate information is included. To verify validity, it checks whether the entered content is in the correct format and returns an error message if inappropriate information is entered.

[0503] The server uses properly formatted information to generate AI models (for example, OpenAI's GPT-4 model) and conduct research. For example, it might be instructed to research "the latest trends and case studies of efficiency improvements in the manufacturing industry." The prompt in this case would be, "Please tell me about the latest trends and success stories of efficiency improvements in the manufacturing industry."

[0504] When the AI ​​model provides data, the server analyzes it. Data analysis uses Python's Pandas and NumPy libraries. Based on the analysis results, the server automatically generates proposal components. Specifically, it embeds the generated data into a template and creates sections such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[0505] Furthermore, the server integrates with existing systems to retrieve past proposals and related documents. The server uses databases such as MySQL or PostgreSQL to extract the necessary data and incorporate it into the new proposal. This makes it possible to retrieve past "proposals to a certain company" and reflect them in the new proposal.

[0506] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions. Document generation tools such as LaTeX and Markdown are used to generate the proposal. Specifically, a template engine is used to embed the data in the appropriate places and convert it into the final document format.

[0507] The generated draft proposal is sent from the server to the user. This is done via email or a dedicated web interface, and the user reviews the draft proposal on their device. The user then makes any necessary final adjustments based on the submitted draft proposal to complete the proposal.

[0508] Finally, the server prepares to provide proposal creation support functions to external customers. Specifically, this includes preparing digital marketing materials and demonstrations. Marketing materials are created using Adobe Creative Cloud, and demonstrations are conducted using Zoom or Microsoft Teams.

[0509] The above describes a specific embodiment of the proposal creation support system of this invention.

[0510] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0511] Step 1:

[0512] User enters information

[0513] The user enters information into an input form on their device. This information includes company name, industry, and proposal details, all necessary for creating a proposal. The input form is implemented as a web form using HTML and JavaScript. Once the input data is submitted, the device sends that data to the server.

[0514] Specific actions

[0515] Fill in the input form with specific details such as "Company Name, Manufacturing Industry, Proposal for Efficiency Improvement," and click the "Submit" button.

[0516] Input: Information entered by the user (company name, industry, proposal details)

[0517] Output: Information is sent from the terminal to the server.

[0518] Step 2:

[0519] The server receives the information and checks its format and validity.

[0520] The server processes the information received from the terminal and checks the format and validity of the input data. Using a message queue system such as Apache Kafka or RabbitMQ, it verifies after receiving the data whether the format is correct and whether all required fields are present. If the validity is not confirmed, it generates an error message and sends it back to the terminal.

[0521] Specific actions

[0522] The system checks whether the received data is in the correct format, and if the data is inappropriate, it returns an error message such as "Company name is not entered."

[0523] Input: Information sent from the device

[0524] Output: Formatted information, or error message.

[0525] Step 3:

[0526] The server calls the generated AI model to perform research.

[0527] The server calls a generating AI model (such as OpenAI's GPT-4) based on the input information. It issues specific research instructions and collects the necessary data. It uses specific sentences as prompts, such as "Please tell me about the latest trends and examples of efficiency improvements in the manufacturing industry."

[0528] Specific actions

[0529] This process sends a prompt to a generative AI model to retrieve information about a specified topic. The retrieved data is also temporarily stored.

[0530] Input: Formatted information

[0531] Output: Research data received from the generative AI model

[0532] Step 4:

[0533] The server analyzes the data and generates parts for the proposal.

[0534] The server analyzes the data received from the generated AI model using Python libraries such as Pandas and NumPy. Based on the analysis results, it automatically generates components for the proposal document.

[0535] Specific actions

[0536] Based on the analysis results, sections of the proposal document such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories" are generated. Unnecessary data is filtered out during the analysis process.

[0537] Input: Data received from the generated AI model

[0538] Output: Proposal parts (sections)

[0539] Step 5:

[0540] The server retrieves data in conjunction with the existing system.

[0541] The server retrieves past proposals and related documents from existing databases such as MySQL and PostgreSQL. This makes it possible to reference past data in new proposals.

[0542] Specific actions

[0543] Use SQL queries to extract necessary data from the database and incorporate the processing results into a draft of the new proposal.

[0544] Input: Request for necessary past proposals and related documents

[0545] Output: Past proposals and related document data

[0546] Step 6:

[0547] The server generates the draft proposal.

[0548] The server generates a draft proposal based on the collected data and analysis results. This draft proposal includes industry analysis, problem analysis, and proposed solutions. It is then converted into a document format using document generation tools such as LaTeX or Markdown.

[0549] Specific actions

[0550] A template engine is used to embed proposal components in the appropriate locations. Finally, it is converted to formats such as PDF and Word.

[0551] Input: Analysis results and existing documents

[0552] Output: Draft proposal

[0553] Step 7:

[0554] The server provides the user with a draft proposal.

[0555] The server sends the generated draft proposal to the user. This is done via email or a dedicated web interface. The user reviews the draft proposal on their terminal and makes any necessary final adjustments.

[0556] Specific actions

[0557] The draft proposal will be generated in formats such as PDF files and provided via email attachment or web dashboard.

[0558] Input: Generated proposal draft

[0559] Output: Draft proposal provided to the user

[0560] Step 8:

[0561] The server prepares for sale to external customers.

[0562] The server prepares to provide proposal creation support functions to external customers. It also prepares digital marketing materials and demonstrations.

[0563] Specific actions

[0564] We will create marketing materials using Adobe Creative Cloud and conduct demonstrations using Zoom, Microsoft Teams, and other tools.

[0565] Input: System sales materials and demonstration content

[0566] Output: Marketing materials and demonstrations provided to external customers.

[0567] (Application Example 1)

[0568] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0569] In modern business processes, particularly in the operation of logistics centers, the creation of proposals quickly and effectively is essential. However, traditional methods require considerable time and effort, and make it difficult to efficiently utilize the latest information and past proposals. Furthermore, there is a lack of systems that allow for information input, confirmation, and modification on mobile devices, hindering operational efficiency. Against this backdrop, there is a need for a system that efficiently researches industry trends and specific case studies and automatically generates high-quality proposals.

[0570] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0571] In this invention, the server includes means for researching target fields and issues using generative artificial intelligence based on input information, means for analyzing the research results and automatically generating parts of a proposal document, and means for linking with an existing database to acquire past proposal documents and related materials. This enables users to quickly create proposals based on the latest industry trends and specific examples, and to easily input, confirm, and modify information via a mobile device. Furthermore, the system's convenience and reliability are improved by including means for preparing to sell the generated proposal document creation support function to external consumers, and means for verifying the validity of information provided by users and returning error messages if inappropriate information is entered.

[0572] "Inputted information" refers to the data and detailed information that the user provides to the system for creating the proposal.

[0573] "Generative artificial intelligence" refers to an artificial intelligence model that can automatically generate and analyze information based on provided data.

[0574] "Target field" refers to the specific industry or field that is the subject of research or proposal writing.

[0575] A "problem" refers to an issue that needs to be solved or an area for improvement within the field in question.

[0576] The "research method" refers to a function that uses generative artificial intelligence based on input information to investigate the latest industry trends and success stories.

[0577] "Means of analysis" refers to the function of analyzing data obtained from research and extracting useful information for the proposal.

[0578] "Parts of the proposal document" refers to each section or element that makes up the proposal.

[0579] "Automatic generation method" refers to a function that automatically generates a proposal document based on the analyzed results.

[0580] An "existing database" is a system that stores past proposals, related documents, industry data, and other similar information.

[0581] "Means of collaboration" refers to the function of communicating with existing databases and retrieving necessary data.

[0582] A "mobile device" is a portable information processing device such as a smartphone or tablet.

[0583] A "user" is an individual or organization that uses the system to create a proposal.

[0584] "External consumers" refers to external individuals or corporations who purchase or use the services of this system.

[0585] "Means of preparing for sale" refers to the function of preparing to offer the generated proposal creation support function to the market.

[0586] "Means of validating validity" refers to a function that verifies whether the information entered by the user is accurate.

[0587] An "error message" is a message sent to the user when there is a problem with the information they have entered.

[0588] "Reliability" refers to a system's ability to deliver accurate and consistent results.

[0589] The system for implementing this invention enables operators of logistics centers and other facilities to efficiently prepare proposals. This system consists of the following main phases.

[0590] Information input phase

[0591] Users use mobile devices (smartphones or tablets) to input the information necessary to create a proposal. For example, they enter the client name, industry name, and the purpose of the proposal. This information is collected via the input form and sent to the server.

[0592] Research phase

[0593] The server receives the input information and uses generative artificial intelligence (such as the OpenAI API) to research the latest trends and success stories related to the target field and challenges. An example of a prompt used here is, "Please research the latest trends and success stories in the logistics industry."

[0594] Data Analysis Phase

[0595] The server analyzes the data received from the generative artificial intelligence and automatically generates the proposal document. This includes details of the latest efficiency technologies and success stories. Based on the analysis results, a concrete proposal document is constructed.

[0596] Data collection phase

[0597] The server integrates with existing databases (such as proposal management systems) to retrieve past proposal documents and related materials. This information is then incorporated into the content of new proposals.

[0598] Proposal generation phase

[0599] The server generates a draft proposal document based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and details of the proposed solutions.

[0600] Proposal submission phase

[0601] The generated proposal draft is provided to the user's mobile device, allowing them to review the draft and make revisions as needed. This enables the user to finalize the proposal quickly and effectively.

[0602] External sales preparation phase

[0603] The server prepares to sell the generated proposal document creation support function to external consumers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system.

[0604] Furthermore, the system includes a function to verify the validity of information provided by users and return an error message if inappropriate information is entered. This improves the reliability and usability of the system.

[0605] Ultimately, this system enables logistics center operators to quickly propose operational efficiency improvements and enhancements, and to easily input, verify, and modify information via mobile devices. In this way, the entire proposal creation process is significantly streamlined.

[0606] The following is an example of a prompt statement:

[0607] 1. "Please research the latest trends and success stories in the logistics industry."

[0608] 2. "Please explain how the latest trends in efficiency technologies can be applied to logistics centers."

[0609] The main hardware used will be smartphones, tablets, and servers, while the software will include the OpenAI API, APIs for existing proposal management systems, Python, and the Requests library.

[0610] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0611] Step 1:

[0612] The user enters information using a mobile device. Specifically, they fill in information such as the client name, industry name, and the purpose of the proposal in an input form. This information is then sent from the device to the server.

[0613] Input: Client name, industry, purpose of the proposal, etc.

[0614] Output: Input information sent to the server.

[0615] Step 2:

[0616] Based on the information received by the server, prompts are sent to the generative AI model. For example, a prompt such as "Research the latest trends and success stories in the logistics industry" might be sent to the generative AI model (e.g., via the OpenAI API).

[0617] Input: Client name, industry, purpose of the proposal.

[0618] Output: Prompts for the generative AI model and research result data from the generative AI model.

[0619] Step 3:

[0620] The server analyzes the research results obtained from the generated AI model. Specifically, it performs text analysis on the acquired data and extracts and organizes important information that should be included in the proposed document.

[0621] Input: Research result data from a generated AI model.

[0622] Output: Analysis results with important information organized.

[0623] Step 4:

[0624] The server connects with the existing database (proposal management system) to retrieve past proposal documents and related materials. If necessary, the server sends an API request to download the materials.

[0625] Input: Information such as client name and industry.

[0626] Output: Past proposal documents and related materials.

[0627] Step 5:

[0628] The server automatically generates a draft of the proposal document based on the analysis results and acquired data. Specifically, it generates each section that makes up the entire proposal document, such as industry analysis and solutions.

[0629] Input: Analysis results, past proposal documents, and related materials.

[0630] Output: Draft of the proposal document.

[0631] Step 6:

[0632] The server provides a draft of the proposal document to the mobile device, allowing the user to review and modify it. The user then makes revisions on the device and finalizes the proposal document.

[0633] Input: Draft of the proposal document.

[0634] Output: Finalized proposal document.

[0635] Step 7:

[0636] Prepare marketing materials and demonstrations to provide external consumers with the proposal document creation support function generated by the server.

[0637] Input: A sample of the overall system functionality and proposed document.

[0638] Output: Marketing materials, demo content.

[0639] Through the steps outlined above, users will be able to create high-quality proposal documents efficiently and quickly.

[0640] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0641] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates a proposal based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposal and user satisfaction.

[0642] Information input phase

[0643] User enters information

[0644] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotion data from the user's facial expressions and input.

[0645] Research phase

[0646] The server receives the information.

[0647] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed.

[0648] The server calls a generative artificial intelligence.

[0649] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0650] Data Analysis Phase

[0651] The server analyzes the data.

[0652] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates parts for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[0653] Data collection phase

[0654] The server integrates with the existing system.

[0655] The server integrates with existing systems to retrieve past proposals and related documents. For example, the server accesses an existing proposal database to retrieve "past proposals for a certain company." This retrieved material is then used as reference data for new proposals.

[0656] Proposal generation phase

[0657] The server generates a draft proposal.

[0658] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format. Furthermore, it adjusts the tone and content of the proposal, taking into account user sentiment data analyzed by the sentiment engine.

[0659] Proposal submission phase

[0660] The server provides the user with a draft proposal.

[0661] The server provides the user with a draft proposal. The user receives the draft proposal on their device and reviews its contents. The emotion engine analyzes the user's real-time reactions and provides support messages if negative emotions are detected. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[0662] External sales preparation phase

[0663] The server is preparing to sell its proposal creation support function to external customers.

[0664] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[0665] The above is a specific implementation of a proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotional data from the user's facial expressions, input speed, and other factors.

[0669] Step 2:

[0670] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[0671] Step 3:

[0672] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0673] Step 4:

[0674] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates components for the proposal (industry analysis, problem analysis, proposed solutions, etc.). For example, it generates sections including "latest trends in efficiency technologies" and "details of success stories."

[0675] Step 5:

[0676] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." These retrieved documents will then be used as reference data for the new proposal.

[0677] Step 6:

[0678] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[0679] Step 7:

[0680] The emotion engine analyzes emotional data collected from the user, and if the user is experiencing anxiety or stress while creating a proposal, the server generates an appropriate support message and displays it on the terminal. For example, a message such as "Do you need any additional information on this section?" might be displayed.

[0681] Step 8:

[0682] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their device and reviews its contents. The sentiment engine analyzes the user's real-time reactions and, if positive sentiment is indicated, verifies that the proposal's content is appropriate. If negative sentiment is detected, additional revisions or advice are provided.

[0683] Step 9:

[0684] The user completes the final proposal based on the draft. The user makes additional edits and customizations on their device, and throughout the proposal completion process, the sentiment engine monitors the user's feedback and provides further support as needed.

[0685] Step 10:

[0686] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[0687] The above is the specific processing flow of the proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[0688] (Example 2)

[0689] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0690] In proposal creation, there are challenges in automatically verifying the validity of user input and ensuring that the content and tone of the proposal meet user expectations, thereby improving user satisfaction. Furthermore, there is a lack of means to improve proposal quality by considering user emotions, thus creating a need for both increased efficiency and higher quality in proposal creation.

[0691] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0692] In this invention, the server includes means for receiving user-inputted information and verifying its validity; means for researching industries and issues based on the input information using generative artificial intelligence; means for analyzing the research results and automatically generating sections for the proposal; means for acquiring past data in cooperation with existing systems; means for using the acquired data for analysis and generating a draft proposal; means for acquiring user emotion data using an emotion recognition engine and adjusting the tone and content of the proposal; and means for providing the generated draft proposal to the user, analyzing the user's reaction in real time, and providing support messages. This makes it possible to automatically verify the validity of the user's input information and improve user satisfaction and the quality of the proposal by ensuring that the generated proposal has a tone and content that reflects the user's emotions.

[0693] "Means for receiving user-entered information and verifying its validity" refers to a function that allows a server to receive information entered by a user into the system and check whether that information is accurate and complete.

[0694] "A means of researching industries and issues based on input information using generative artificial intelligence" refers to a function in which a server utilizes generative artificial intelligence to collect the latest industry information and issues related to the information entered by the user from the internet or internal databases.

[0695] "A means of analyzing research results and automatically generating sections of a proposal" refers to a function in which the server analyzes research results obtained from a generative artificial intelligence and automatically creates each section of the proposal based on that information.

[0696] "Methods for retrieving past documents by linking with existing systems" refers to a function that allows the server to link with existing document management systems and databases to retrieve proposals and related documents created in the past.

[0697] "A means of using acquired data for analysis and generating a draft proposal" refers to a function that uses past data acquired by the server for analysis and creates a draft of a new proposal based on that data.

[0698] "A means of acquiring user emotional data using an emotion recognition engine and adjusting the tone and content of the proposal" refers to a function in which the server uses an emotion recognition engine to collect user emotional data and then appropriately adjusts the tone and content of the proposal based on the results.

[0699] "A means of providing users with generated draft proposals, analyzing user reactions in real time, and providing support messages" refers to a function in which the server provides users with generated draft proposals, analyzes users' real-time reactions through an emotion recognition engine, and sends support messages as needed.

[0700] "Means of preparing to sell the generated proposal creation support function to external customers" refers to the function that prepares the server to sell the proposal creation support function to external users. This preparation includes creating marketing materials and demonstrations.

[0701] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates proposals based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposals and user satisfaction.

[0702] First, the user enters the necessary information for creating the proposal into the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server, and at the same time, the emotion engine collects emotion data from the user's facial expressions and input.

[0703] Next, the server checks the received information for validation. It verifies whether the entered company name, industry, and purpose of the proposal are valid, and checks the format and required fields as needed. If inappropriate information is entered, the server returns an error message to the user.

[0704] Next, the server invokes a generative artificial intelligence (e.g., GPT-4) and instructs it to research industries and issues based on the input information. For example, it might be instructed to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI searches the internet and internal databases to collect relevant information.

[0705] The server analyzes research results sent from the generative artificial intelligence and automatically generates sections for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[0706] Subsequently, the server integrates with the existing system to retrieve past proposals and related documents. It accesses the existing document management system (DMS) and retrieves "past proposals to a certain company." These documents are used as reference materials for the new proposal.

[0707] Next, the server generates a draft proposal based on the collected research results and acquired materials. The emotion recognition engine adjusts the tone and content based on the user's emotional data. For example, if the user is feeling nervous, the proposal's writing style will be made more approachable.

[0708] The server provides the user with a generated draft proposal, which the user then reviews on their device. The emotion recognition engine analyzes the user's real-time reactions and provides a support message if negative emotions are detected.

[0709] Finally, the server prepares to sell its proposal creation support function to external customers. This includes creating marketing materials and demonstrations. For example, it prepares feature explanation videos and user manuals, and conducts sales promotion activities.

[0710] As a concrete example, if a user inputs the information "a certain company, manufacturing industry, efficiency improvement proposal," an example of a prompt message for a generative artificial intelligence would be as follows:

[0711] "Research the latest efficiency technologies and success stories in the manufacturing industry. Specifically, provide information focusing on trends in manufacturing line automation and data analytics technologies. Also, thoroughly investigate representative success stories from the past five years."

[0712] This system allows users to easily create high-quality proposals, significantly improving both the quality of the proposals and user satisfaction.

[0713] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0714] Step 1:

[0715] User enters information

[0716] The user enters necessary information such as company name, industry, and purpose of the proposal into the input form on the terminal. An example of the information to be entered is "Company X, manufacturing industry, proposal for efficiency improvement."

[0717] Input: Company name, industry, purpose of proposal

[0718] Output: Input data sent to the server

[0719] Step 2:

[0720] The server receives the information and verifies its validity.

[0721] The server receives information sent by the user and checks the format of the entered data and whether all required fields are present. For example, it verifies whether the company name is entered correctly and whether the industry name is valid. If inappropriate information is entered, an error message is returned to the user.

[0722] Input: Data entered by the user

[0723] Output: Valid data, error messages (if necessary)

[0724] Step 3:

[0725] The server invokes a generative artificial intelligence to instruct it on research.

[0726] Based on the input information, the server issues research instructions to a generative artificial intelligence (e.g., GPT-4). It generates a prompt and sends an instruction to the generative AI to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[0727] Input: Valid input data

[0728] Output: Prompt message, data to send to the generative AI.

[0729] Step 4:

[0730] Generative artificial intelligence begins research

[0731] Generative artificial intelligence searches the internet and internal databases, collecting relevant information according to instructions. It then sends the research results to a server. For example, it might collect data on the latest efficiency technologies and success stories.

[0732] Input: Prompt message

[0733] Output: Research results data

[0734] Step 5:

[0735] The server analyzes the data and generates sections for the proposal.

[0736] The server receives research results returned by the generative artificial intelligence and analyzes them. Based on the analysis, it automatically generates sections for the proposal. For example, it creates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[0737] Input: Research result data

[0738] Output: Section data of the proposal

[0739] Step 6:

[0740] The server retrieves data in conjunction with the existing system.

[0741] The server integrates with existing systems such as document management systems (DMS) to retrieve past proposals and related documents. For example, it can retrieve "past proposals to a certain company" and use them as reference material for new proposals.

[0742] Input: Information about existing systems, company name

[0743] Output: Historical document data

[0744] Step 7:

[0745] The server generates a draft proposal.

[0746] The server generates a draft proposal based on research results and acquired materials. It uses an emotion recognition engine to obtain user emotion data and adjusts the tone and content of the proposal accordingly. For example, if the user is nervous, the writing style is made more approachable.

[0747] Input: Research results data, historical data, sentiment data

[0748] Output: Draft proposal data

[0749] Step 8:

[0750] The server provides the user with a draft proposal.

[0751] The server sends the generated draft proposal to the user. The user reviews the draft proposal on their device and makes revisions as needed. Simultaneously, the emotion recognition engine analyzes the user's reactions and provides a support message if negative emotions are detected.

[0752] Input: Proposal draft data, real-time sentiment data

[0753] Output: Display of a draft proposal to the user, support messages (if necessary)

[0754] Step 9:

[0755] The server prepares to sell its proposal creation support function to external customers.

[0756] The server creates marketing materials and demonstrations to sell the proposal creation support function to external customers. For example, it prepares feature explanation videos and user manuals, and carries out sales promotion activities.

[0757] Input: Information on the proposal creation support function

[0758] Output: Marketing materials, demonstration content

[0759] The above outlines the specific processing steps and details of the proposal creation support system. Through these steps, users can efficiently create high-quality proposals.

[0760] (Application Example 2)

[0761] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0762] Conventional proposal creation support systems automatically generate proposals based on information provided by the user, but they have the problem of not being able to adequately respond to customer needs and reactions because they provide proposals with uniform content and tone without considering the user's feelings. Furthermore, because they lack a mechanism to collect and reflect customer feelings and feedback in real time, it is difficult to immediately provide appropriate proposal content in sales activities at physical stores.

[0763] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0764] This invention includes a server that, based on input information, uses generative artificial intelligence to research customer industries and corporate challenges; analyzes the research results and automatically generates proposal components; collaborates with existing systems to acquire past proposals and related materials; uses the acquired materials for analysis and generates a draft proposal; provides the generated draft proposal to the user, allowing the user to finalize the proposal; and collects emotional data in real time and adjusts the content and tone of the draft proposal. This improves the quality of proposals and enables optimal proposals based on the customer's real-time emotions and needs.

[0765] "Inputted information" refers to the collection of data that users provide through input forms or devices on the system.

[0766] "Generative artificial intelligence" is an artificial intelligence technology that automatically analyzes data based on the information provided and generates relevant information.

[0767] "Research" is the process of collecting and analyzing information about the challenges facing a particular industry or company.

[0768] "Analysis" is the process of examining collected data and information in detail, extracting meaning, and understanding it.

[0769] "Proposal components" refer to some elements or sections that make up the final proposal, and include specific content and data.

[0770] "Existing systems" refer to information processing systems and databases that have been implemented in the past.

[0771] "Reference materials" refer to existing documents that are useful for creating a proposal, such as past proposals and related reference data.

[0772] A "draft proposal" is an initial document used to create the final proposal, and it contains the proposal content and data.

[0773] A "user" is an individual or company representative who uses the proposal creation support system.

[0774] "Emotional data" refers to emotional information obtained by analyzing the facial expressions and statements of users and customers.

[0775] "Real-time" refers to a time frame in which data is processed as soon as it is generated, and results are provided immediately.

[0776] "Tone" refers to the style of language and expression used in the content of a proposal or document.

[0777] This invention includes the following configuration and processes for realizing a proposal creation support system.

[0778] System Configuration

[0779] 1. Hardware Configuration

[0780] Smart glasses: Equipped with a camera to detect customer facial expressions and a display to show draft proposals.

[0781] Server: Receives and analyzes data, generates proposals, and processes sentiment data.

[0782] Edge devices: Assist in real-time processing of camera images.

[0783] 2. Software Configuration

[0784] Emotion Engine: Analyzes customer emotion data in real time from camera footage.

[0785] Proposal Generator: Generates proposal components based on user input data and sentiment data.

[0786] Generative artificial intelligence: Automatically generates proposal content based on research results.

[0787] Operation details

[0788] Information input phase

[0789] The user interacts with customers while wearing smart glasses. The smart glasses' camera captures the customer's facial expressions, and the microphone records the conversation. This data is sent to a server in real time, and simultaneously, an emotion engine is activated to analyze the customer's emotional data.

[0790] Research phase

[0791] The server uses generative artificial intelligence to research customer industries and company challenges based on the input information. Relevant information is collected and analyzed from the internet and internal databases.

[0792] Data Analysis Phase

[0793] Data, including research results, is sent to the server, and proposal components are automatically generated. This includes the latest technological trends and success stories.

[0794] Data collection phase

[0795] The server integrates with existing systems to retrieve past proposals and related documents. These documents are used for analysis to improve the quality of proposals.

[0796] Proposal generation phase

[0797] The server combines all collected data and analysis results to generate a draft proposal. Based on the emotional data obtained from the emotion engine, the content and tone of the proposal are adjusted.

[0798] Proposal submission phase

[0799] The generated proposal draft is displayed in real time on the smart glasses' screen. The salesperson uses this proposal to provide appropriate explanations to the customer and further optimizes the proposal by collecting real-time feedback from the customer.

[0800] Detailed processing instructions

[0801] The server uses Python and OpenCV to process video data and utilizes an emotion recognition engine (EmotionEngine) to perform facial expression analysis. Based on the actual emotion data, a proposal generation engine (ProposalGenerator) operates to generate proposal content. Through the coordination of each hardware and software component, optimized proposals are provided in real time, aiming to improve customer satisfaction.

[0802] Example of a prompt

[0803] "Please generate a portion of the proposal for product XYZ based on the following data. The sentiment data is [Joy: 0.8, Surprise: 0.2], and the customer appears to be interested in the product's cost-effectiveness."

[0804] Based on this prompt, the generative AI model generates appropriate proposal components, which the server then combines to complete the draft proposal. In this way, a high-quality proposal based on the user's emotional data and needs can be provided.

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] Information input phase

[0808] The user interacts with a customer while wearing smart glasses. During this interaction, a camera built into the glasses captures the customer's facial expressions, and a microphone records the conversation. The collected data is transmitted to a server in real time. The server uses the received video and audio data as input, and an emotion engine analyzes it to extract the customer's emotional data (e.g., joy, surprise, sadness). This emotional data is then output. The specific actions involved in each step include capturing camera footage, recording audio, and transmitting the data.

[0809] Step 2:

[0810] Research phase

[0811] The server uses generative artificial intelligence to conduct research based on information entered by the user (customer industry, company challenges, etc.). This research extracts relevant information from the internet and internal databases and collects optimal suggestions for the user. The input is information about the customer industry and company challenges, and the output is relevant research data (e.g., latest trends, success stories, etc.). Specifically, it performs information retrieval and data extraction.

[0812] Step 3:

[0813] Data Analysis Phase

[0814] The server receives research results and sentiment data as input and analyzes them. The research results are analyzed by generative artificial intelligence, and proposal components are automatically generated. Furthermore, the tone and content of the proposal are adjusted based on the sentiment data. The output consists of each component of the proposal. Specifically, the process includes data analysis and the generation of proposal components.

[0815] Step 4:

[0816] Data collection phase

[0817] The server integrates with existing systems to retrieve past proposals and related documents. This process involves accessing a database of past proposals and collecting information and reference materials previously provided by users. The input is existing database information, and the output is the retrieved past proposals and reference materials. Specific operations include accessing the database and retrieving the documents.

[0818] Step 5:

[0819] Proposal generation phase

[0820] The server combines all collected data and analysis results to generate a draft proposal. This draft includes content that reflects research results, historical documents, and sentiment data. Inputs include research results, historical documents, and sentiment data, and output is the generated draft proposal. Specific operations include data integration and proposal draft generation.

[0821] Step 6:

[0822] Proposal submission phase

[0823] The generated proposal draft is displayed in real time on the smart glasses' screen. This allows salespeople to immediately present the proposal to customers. The input is the proposal draft, and the output is the proposal displayed on the smart glasses' screen. Specific operations include displaying data.

[0824] In this way, data is entered at each processing step, and after going through each process, the proposal is finally displayed on smart glasses.

[0825] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0826] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0827] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0828] [Third Embodiment]

[0829] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0830] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0831] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0832] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0833] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0834] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0835] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0836] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0837] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0838] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0839] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0840] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0841] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on input information. The processing of this system's program is described below in natural language.

[0842] Information input phase

[0843] User enters information

[0844] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, manufacturing industry, proposal for efficiency improvements."

[0845] Research phase

[0846] The server receives the information.

[0847] The server receives information entered by the user and verifies its format. Validation checks are performed as needed.

[0848] The server calls a generative artificial intelligence.

[0849] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct it to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[0850] Data Analysis Phase

[0851] The server analyzes the data.

[0852] The server analyzes the data received from the generative artificial intelligence. Based on the analysis results, it automatically generates parts of the proposal. For example, it generates sections including "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[0853] Data collection phase

[0854] The server integrates with the existing system.

[0855] The server integrates with existing systems to retrieve past proposals and related documents. For example, it can retrieve past proposals to a specific company and incorporate that information into new proposals.

[0856] Proposal generation phase

[0857] The server generates a draft proposal.

[0858] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions.

[0859] Proposal submission phase

[0860] The server provides the user with a draft proposal.

[0861] The server sends the generated draft proposal to the user, who then reviews it on their terminal. The user makes final adjustments based on the draft and completes the proposal.

[0862] External sales preparation phase

[0863] Servers are ready for sale to external customers.

[0864] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations, and explains how to use the system.

[0865] The above describes a specific embodiment of the proposal creation support system of the present invention.

[0866] The following describes the processing flow.

[0867] Step 1:

[0868] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is then sent to the server.

[0869] Step 2:

[0870] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[0871] Step 3:

[0872] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[0873] Step 4:

[0874] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data. Specifically, it extracts highly relevant information from the collected data and classifies and organizes it as components of a proposal (industry analysis, problem analysis, solutions, etc.).

[0875] Step 5:

[0876] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." This retrieved material will then be used as reference data for the new proposal.

[0877] Step 6:

[0878] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[0879] Step 7:

[0880] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their terminal and reviews its contents. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[0881] Step 8:

[0882] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[0883] The above is the specific processing flow of the proposal creation support system.

[0884] (Example 1)

[0885] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0886] Traditional proposal writing processes are inefficient, requiring a great deal of manual work such as information gathering, analysis, and referencing past proposals. Furthermore, creating proposals based on accurate information demands specialized knowledge, requiring significant time and effort. Additionally, the preparation process for providing proposal writing support systems to external clients is cumbersome. This creates a significant obstacle, especially for companies aiming to improve operational efficiency.

[0887] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0888] In this invention, the server includes means for the user to input information into an input form on the terminal, means for the server to receive the input information and check its format and validity, means for the server to call a generation AI model based on the input information and perform research, means for the server to analyze the data received from the generation AI model and generate proposal components based on the analysis results, means for the server to acquire past proposals and related materials in cooperation with existing systems, means for the server to generate a draft proposal using the acquired materials and analysis results, and means for the server to provide the generated draft proposal to the user so that the user can finalize the proposal. This enables the efficient and highly accurate automatic generation of proposals and smooth preparation for sales to external customers.

[0889] "User" refers to the end user who inputs information to create a proposal using the system.

[0890] A "terminal" refers to a hardware device used by a user to input information, and specifically includes personal computers, smartphones, and tablets.

[0891] A "server" refers to a computer system that receives input from users and performs processing using AI models for information analysis and generation.

[0892] An "input form" refers to a web-based interface that allows users to input the information necessary for creating a proposal from their device.

[0893] A "generative AI model" refers to an artificial intelligence model that automatically performs research and generates data based on the information provided.

[0894] "Research" refers to the process of collecting information on a specified topic using a generative AI model.

[0895] "Data analysis" refers to the analytical process of processing data received from a generative AI model to generate components for a proposal.

[0896] "Parts of a proposal" refer to the individual sections or elements that make up a proposal, such as industry analysis and problem analysis.

[0897] "Existing systems" refers to databases and storage systems that store past proposals and related documents that the servers are connected to.

[0898] A "draft proposal" refers to the initial version of a proposal generated by the server, an incomplete document before the user finalizes it.

[0899] "External customers" refer to third-party companies or individuals who purchase the system's proposal creation support functionality.

[0900] "Sales preparation" refers to the process of preliminary preparations such as marketing, demonstrations, and document creation for providing a system to external customers.

[0901] "Validation check" refers to the process of verifying whether the information entered by the user is accurate and complete, and returns an error message if inaccurate or incomplete information is entered.

[0902] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on the input information. The processing of this system's program will be described in detail below.

[0903] Users input information for creating proposals using their devices. These devices can include PCs and smartphones. Specifically, the information provided by users might include "Company A, Manufacturing Industry, Proposal for Efficiency Improvement." The input form is a web form using HTML or JavaScript. For example, the user might input specific details such as "Company A, New Product Development, Proposal for Innovative Technology."

[0904] When information is entered, the server receives it. The server uses a message queue system such as Apache Kafka or RabbitMQ to receive the information and check its format and validity. It checks the format of the received information to ensure that all required fields are filled in and that no inappropriate information is included. To verify validity, it checks whether the entered content is in the correct format and returns an error message if inappropriate information is entered.

[0905] The server uses properly formatted information to generate AI models (for example, OpenAI's GPT-4 model) and conduct research. For example, it might be instructed to research "the latest trends and case studies of efficiency improvements in the manufacturing industry." The prompt in this case would be, "Please tell me about the latest trends and success stories of efficiency improvements in the manufacturing industry."

[0906] When the AI ​​model provides data, the server analyzes it. Data analysis uses Python's Pandas and NumPy libraries. Based on the analysis results, the server automatically generates proposal components. Specifically, it embeds the generated data into a template and creates sections such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[0907] Furthermore, the server integrates with existing systems to retrieve past proposals and related documents. The server uses databases such as MySQL or PostgreSQL to extract the necessary data and incorporate it into the new proposal. This makes it possible to retrieve past "proposals to a certain company" and reflect them in the new proposal.

[0908] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions. Document generation tools such as LaTeX and Markdown are used to generate the proposal. Specifically, a template engine is used to embed the data in the appropriate places and convert it into the final document format.

[0909] The generated draft proposal is sent from the server to the user. This is done via email or a dedicated web interface, and the user reviews the draft proposal on their device. The user then makes any necessary final adjustments based on the submitted draft proposal to complete the proposal.

[0910] Finally, the server prepares to provide proposal creation support functions to external customers. Specifically, this includes preparing digital marketing materials and demonstrations. Marketing materials are created using Adobe Creative Cloud, and demonstrations are conducted using Zoom or Microsoft Teams.

[0911] The above describes a specific embodiment of the proposal creation support system of this invention.

[0912] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0913] Step 1:

[0914] User enters information

[0915] The user enters information into an input form on their device. This information includes company name, industry, and proposal details, all necessary for creating a proposal. The input form is implemented as a web form using HTML and JavaScript. Once the input data is submitted, the device sends that data to the server.

[0916] Specific actions

[0917] Fill in the input form with specific details such as "Company Name, Manufacturing Industry, Proposal for Efficiency Improvement," and click the "Submit" button.

[0918] Input: Information entered by the user (company name, industry, proposal details)

[0919] Output: Information is sent from the terminal to the server.

[0920] Step 2:

[0921] The server receives the information and checks its format and validity.

[0922] The server processes the information received from the terminal and checks the format and validity of the input data. Using a message queue system such as Apache Kafka or RabbitMQ, it verifies after receiving the data whether the format is correct and whether all required fields are present. If the validity is not confirmed, it generates an error message and sends it back to the terminal.

[0923] Specific actions

[0924] The system checks whether the received data is in the correct format, and if the data is inappropriate, it returns an error message such as "Company name is not entered."

[0925] Input: Information sent from the device

[0926] Output: Formatted information, or error message.

[0927] Step 3:

[0928] The server calls the generated AI model to perform research.

[0929] The server calls a generating AI model (such as OpenAI's GPT-4) based on the input information. It issues specific research instructions and collects the necessary data. It uses specific sentences as prompts, such as "Please tell me about the latest trends and examples of efficiency improvements in the manufacturing industry."

[0930] Specific actions

[0931] This process sends a prompt to a generative AI model to retrieve information about a specified topic. The retrieved data is also temporarily stored.

[0932] Input: Formatted information

[0933] Output: Research data received from the generative AI model

[0934] Step 4:

[0935] The server analyzes the data and generates parts for the proposal.

[0936] The server analyzes the data received from the generated AI model using Python libraries such as Pandas and NumPy. Based on the analysis results, it automatically generates components for the proposal document.

[0937] Specific actions

[0938] Based on the analysis results, sections of the proposal document such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories" are generated. Unnecessary data is filtered out during the analysis process.

[0939] Input: Data received from the generated AI model

[0940] Output: Proposal parts (sections)

[0941] Step 5:

[0942] The server retrieves data in conjunction with the existing system.

[0943] The server retrieves past proposals and related documents from existing databases such as MySQL and PostgreSQL. This makes it possible to reference past data in new proposals.

[0944] Specific actions

[0945] Use SQL queries to extract necessary data from the database and incorporate the processing results into a draft of the new proposal.

[0946] Input: Request for necessary past proposals and related documents

[0947] Output: Past proposals and related document data

[0948] Step 6:

[0949] The server generates the draft proposal.

[0950] The server generates a draft proposal based on the collected data and analysis results. This draft proposal includes industry analysis, problem analysis, and proposed solutions. It is then converted into a document format using document generation tools such as LaTeX or Markdown.

[0951] Specific actions

[0952] A template engine is used to embed proposal components in the appropriate locations. Finally, it is converted to formats such as PDF and Word.

[0953] Input: Analysis results and existing documents

[0954] Output: Draft proposal

[0955] Step 7:

[0956] The server provides the user with a draft proposal.

[0957] The server sends the generated draft proposal to the user. This is done via email or a dedicated web interface. The user reviews the draft proposal on their terminal and makes any necessary final adjustments.

[0958] Specific actions

[0959] The draft proposal will be generated in formats such as PDF files and provided via email attachment or web dashboard.

[0960] Input: Generated proposal draft

[0961] Output: Draft proposal provided to the user

[0962] Step 8:

[0963] The server prepares for sale to external customers.

[0964] The server prepares to provide proposal creation support functions to external customers. It also prepares digital marketing materials and demonstrations.

[0965] Specific actions

[0966] We will create marketing materials using Adobe Creative Cloud and conduct demonstrations using Zoom, Microsoft Teams, and other tools.

[0967] Input: System sales materials and demonstration content

[0968] Output: Marketing materials and demonstrations provided to external customers.

[0969] (Application Example 1)

[0970] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0971] In modern business processes, particularly in the operation of logistics centers, the creation of proposals quickly and effectively is essential. However, traditional methods require considerable time and effort, and make it difficult to efficiently utilize the latest information and past proposals. Furthermore, there is a lack of systems that allow for information input, confirmation, and modification on mobile devices, hindering operational efficiency. Against this backdrop, there is a need for a system that efficiently researches industry trends and specific case studies and automatically generates high-quality proposals.

[0972] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0973] In this invention, the server includes means for researching target fields and issues using generative artificial intelligence based on input information, means for analyzing the research results and automatically generating parts of a proposal document, and means for linking with an existing database to acquire past proposal documents and related materials. This enables users to quickly create proposals based on the latest industry trends and specific examples, and to easily input, confirm, and modify information via a mobile device. Furthermore, the system's convenience and reliability are improved by including means for preparing to sell the generated proposal document creation support function to external consumers, and means for verifying the validity of information provided by users and returning error messages if inappropriate information is entered.

[0974] "Inputted information" refers to the data and detailed information that the user provides to the system for creating the proposal.

[0975] "Generative artificial intelligence" refers to an artificial intelligence model that can automatically generate and analyze information based on provided data.

[0976] "Target field" refers to the specific industry or field that is the subject of research or proposal writing.

[0977] A "problem" refers to an issue that needs to be solved or an area for improvement within the field in question.

[0978] The "research method" refers to a function that uses generative artificial intelligence based on input information to investigate the latest industry trends and success stories.

[0979] "Means of analysis" refers to the function of analyzing data obtained from research and extracting useful information for the proposal.

[0980] "Parts of the proposal document" refers to each section or element that makes up the proposal.

[0981] "Automatic generation method" refers to a function that automatically generates a proposal document based on the analyzed results.

[0982] An "existing database" is a system that stores past proposals, related documents, industry data, and other similar information.

[0983] "Means of collaboration" refers to the function of communicating with existing databases and retrieving necessary data.

[0984] A "mobile device" is a portable information processing device such as a smartphone or tablet.

[0985] A "user" is an individual or organization that uses the system to create a proposal.

[0986] "External consumers" refers to external individuals or corporations who purchase or use the services of this system.

[0987] "Means of preparing for sale" refers to the function of preparing to offer the generated proposal creation support function to the market.

[0988] "Means of validating validity" refers to a function that verifies whether the information entered by the user is accurate.

[0989] An "error message" is a message sent to the user when there is a problem with the information they have entered.

[0990] "Reliability" refers to a system's ability to deliver accurate and consistent results.

[0991] The system for implementing this invention enables operators of logistics centers and other facilities to efficiently prepare proposals. This system consists of the following main phases.

[0992] Information input phase

[0993] Users use mobile devices (smartphones or tablets) to input the information necessary to create a proposal. For example, they enter the client name, industry name, and the purpose of the proposal. This information is collected via the input form and sent to the server.

[0994] Research phase

[0995] The server receives the input information and uses generative artificial intelligence (such as the OpenAI API) to research the latest trends and success stories related to the target field and challenges. An example of a prompt used here is, "Please research the latest trends and success stories in the logistics industry."

[0996] Data Analysis Phase

[0997] The server analyzes the data received from the generative artificial intelligence and automatically generates the proposal document. This includes details of the latest efficiency technologies and success stories. Based on the analysis results, a concrete proposal document is constructed.

[0998] Data collection phase

[0999] The server integrates with existing databases (such as proposal management systems) to retrieve past proposal documents and related materials. This information is then incorporated into the content of new proposals.

[1000] Proposal generation phase

[1001] The server generates a draft proposal document based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and details of the proposed solutions.

[1002] Proposal submission phase

[1003] The generated proposal draft is provided to the user's mobile device, allowing them to review the draft and make revisions as needed. This enables the user to finalize the proposal quickly and effectively.

[1004] External sales preparation phase

[1005] The server prepares to sell the generated proposal document creation support function to external consumers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system.

[1006] Furthermore, the system includes a function to verify the validity of information provided by users and return an error message if inappropriate information is entered. This improves the reliability and usability of the system.

[1007] Ultimately, this system enables logistics center operators to quickly propose operational efficiency improvements and enhancements, and to easily input, verify, and modify information via mobile devices. In this way, the entire proposal creation process is significantly streamlined.

[1008] The following is an example of a prompt statement:

[1009] 1. "Please research the latest trends and success stories in the logistics industry."

[1010] 2. "Please explain how the latest trends in efficiency technologies can be applied to logistics centers."

[1011] The main hardware used will be smartphones, tablets, and servers, while the software will include the OpenAI API, APIs for existing proposal management systems, Python, and the Requests library.

[1012] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1013] Step 1:

[1014] The user enters information using a mobile device. Specifically, they fill in information such as the client name, industry name, and the purpose of the proposal in an input form. This information is then sent from the device to the server.

[1015] Input: Client name, industry, purpose of the proposal, etc.

[1016] Output: Input information sent to the server.

[1017] Step 2:

[1018] Based on the information received by the server, prompts are sent to the generative AI model. For example, a prompt such as "Research the latest trends and success stories in the logistics industry" might be sent to the generative AI model (e.g., via the OpenAI API).

[1019] Input: Client name, industry, purpose of the proposal.

[1020] Output: Prompts for the generative AI model and research result data from the generative AI model.

[1021] Step 3:

[1022] The server analyzes the research results obtained from the generated AI model. Specifically, it performs text analysis on the acquired data and extracts and organizes important information that should be included in the proposed document.

[1023] Input: Research result data from a generated AI model.

[1024] Output: Analysis results with important information organized.

[1025] Step 4:

[1026] The server connects with the existing database (proposal management system) to retrieve past proposal documents and related materials. If necessary, the server sends an API request to download the materials.

[1027] Input: Information such as client name and industry.

[1028] Output: Past proposal documents and related materials.

[1029] Step 5:

[1030] The server automatically generates a draft of the proposal document based on the analysis results and acquired data. Specifically, it generates each section that makes up the entire proposal document, such as industry analysis and solutions.

[1031] Input: Analysis results, past proposal documents, and related materials.

[1032] Output: Draft of the proposal document.

[1033] Step 6:

[1034] The server provides a draft of the proposal document to the mobile device, allowing the user to review and modify it. The user then makes revisions on the device and finalizes the proposal document.

[1035] Input: Draft of the proposal document.

[1036] Output: Finalized proposal document.

[1037] Step 7:

[1038] Prepare marketing materials and demonstrations to provide external consumers with the proposal document creation support function generated by the server.

[1039] Input: A sample of the overall system functionality and proposed document.

[1040] Output: Marketing materials, demo content.

[1041] Through the steps outlined above, users will be able to create high-quality proposal documents efficiently and quickly.

[1042] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1043] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates a proposal based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposal and user satisfaction.

[1044] Information input phase

[1045] User enters information

[1046] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotion data from the user's facial expressions and input.

[1047] Research phase

[1048] The server receives the information.

[1049] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed.

[1050] The server calls a generative artificial intelligence.

[1051] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[1052] Data Analysis Phase

[1053] The server analyzes the data.

[1054] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates parts for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[1055] Data collection phase

[1056] The server integrates with the existing system.

[1057] The server integrates with existing systems to retrieve past proposals and related documents. For example, the server accesses an existing proposal database to retrieve "past proposals for a certain company." This retrieved material is then used as reference data for new proposals.

[1058] Proposal generation phase

[1059] The server generates a draft proposal.

[1060] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format. Furthermore, it adjusts the tone and content of the proposal, taking into account user sentiment data analyzed by the sentiment engine.

[1061] Proposal submission phase

[1062] The server provides the user with a draft proposal.

[1063] The server provides the user with a draft proposal. The user receives the draft proposal on their device and reviews its contents. The emotion engine analyzes the user's real-time reactions and provides support messages if negative emotions are detected. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[1064] External sales preparation phase

[1065] The server is preparing to sell its proposal creation support function to external customers.

[1066] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[1067] The above is a specific implementation of a proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[1068] The following describes the processing flow.

[1069] Step 1:

[1070] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotional data from the user's facial expressions, input speed, and other factors.

[1071] Step 2:

[1072] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[1073] Step 3:

[1074] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[1075] Step 4:

[1076] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates components for the proposal (industry analysis, problem analysis, proposed solutions, etc.). For example, it generates sections including "latest trends in efficiency technologies" and "details of success stories."

[1077] Step 5:

[1078] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." These retrieved documents will then be used as reference data for the new proposal.

[1079] Step 6:

[1080] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[1081] Step 7:

[1082] The emotion engine analyzes emotional data collected from the user, and if the user is experiencing anxiety or stress while creating a proposal, the server generates an appropriate support message and displays it on the terminal. For example, a message such as "Do you need any additional information on this section?" might be displayed.

[1083] Step 8:

[1084] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their device and reviews its contents. The sentiment engine analyzes the user's real-time reactions and, if positive sentiment is indicated, verifies that the proposal's content is appropriate. If negative sentiment is detected, additional revisions or advice are provided.

[1085] Step 9:

[1086] The user completes the final proposal based on the draft. The user makes additional edits and customizations on their device, and throughout the proposal completion process, the sentiment engine monitors the user's feedback and provides further support as needed.

[1087] Step 10:

[1088] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[1089] The above is the specific processing flow of the proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[1090] (Example 2)

[1091] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1092] In proposal creation, there are challenges in automatically verifying the validity of user input and ensuring that the content and tone of the proposal meet user expectations, thereby improving user satisfaction. Furthermore, there is a lack of means to improve proposal quality by considering user emotions, thus creating a need for both increased efficiency and higher quality in proposal creation.

[1093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1094] In this invention, the server includes means for receiving user-inputted information and verifying its validity; means for researching industries and issues based on the input information using generative artificial intelligence; means for analyzing the research results and automatically generating sections for the proposal; means for acquiring past data in cooperation with existing systems; means for using the acquired data for analysis and generating a draft proposal; means for acquiring user emotion data using an emotion recognition engine and adjusting the tone and content of the proposal; and means for providing the generated draft proposal to the user, analyzing the user's reaction in real time, and providing support messages. This makes it possible to automatically verify the validity of the user's input information and improve user satisfaction and the quality of the proposal by ensuring that the generated proposal has a tone and content that reflects the user's emotions.

[1095] "Means for receiving user-entered information and verifying its validity" refers to a function that allows a server to receive information entered by a user into the system and check whether that information is accurate and complete.

[1096] "A means of researching industries and issues based on input information using generative artificial intelligence" refers to a function in which a server utilizes generative artificial intelligence to collect the latest industry information and issues related to the information entered by the user from the internet or internal databases.

[1097] "A means of analyzing research results and automatically generating sections of a proposal" refers to a function in which the server analyzes research results obtained from a generative artificial intelligence and automatically creates each section of the proposal based on that information.

[1098] "Methods for retrieving past documents by linking with existing systems" refers to a function that allows the server to link with existing document management systems and databases to retrieve proposals and related documents created in the past.

[1099] "A means of using acquired data for analysis and generating a draft proposal" refers to a function that uses past data acquired by the server for analysis and creates a draft of a new proposal based on that data.

[1100] "A means of acquiring user emotional data using an emotion recognition engine and adjusting the tone and content of the proposal" refers to a function in which the server uses an emotion recognition engine to collect user emotional data and then appropriately adjusts the tone and content of the proposal based on the results.

[1101] "A means of providing users with generated draft proposals, analyzing user reactions in real time, and providing support messages" refers to a function in which the server provides users with generated draft proposals, analyzes users' real-time reactions through an emotion recognition engine, and sends support messages as needed.

[1102] "Means of preparing to sell the generated proposal creation support function to external customers" refers to the function that prepares the server to sell the proposal creation support function to external users. This preparation includes creating marketing materials and demonstrations.

[1103] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates proposals based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposals and user satisfaction.

[1104] First, the user enters the necessary information for creating the proposal into the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server, and at the same time, the emotion engine collects emotion data from the user's facial expressions and input.

[1105] Next, the server checks the received information for validation. It verifies whether the entered company name, industry, and purpose of the proposal are valid, and checks the format and required fields as needed. If inappropriate information is entered, the server returns an error message to the user.

[1106] Next, the server invokes a generative artificial intelligence (e.g., GPT-4) and instructs it to research industries and issues based on the input information. For example, it might be instructed to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI searches the internet and internal databases to collect relevant information.

[1107] The server analyzes research results sent from the generative artificial intelligence and automatically generates sections for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[1108] Subsequently, the server integrates with the existing system to retrieve past proposals and related documents. It accesses the existing document management system (DMS) and retrieves "past proposals to a certain company." These documents are used as reference materials for the new proposal.

[1109] Next, the server generates a draft proposal based on the collected research results and acquired materials. The emotion recognition engine adjusts the tone and content based on the user's emotional data. For example, if the user is feeling nervous, the proposal's writing style will be made more approachable.

[1110] The server provides the user with a generated draft proposal, which the user then reviews on their device. The emotion recognition engine analyzes the user's real-time reactions and provides a support message if negative emotions are detected.

[1111] Finally, the server prepares to sell its proposal creation support function to external customers. This includes creating marketing materials and demonstrations. For example, it prepares feature explanation videos and user manuals, and conducts sales promotion activities.

[1112] As a concrete example, if a user inputs the information "a certain company, manufacturing industry, efficiency improvement proposal," an example of a prompt message for a generative artificial intelligence would be as follows:

[1113] "Research the latest efficiency technologies and success stories in the manufacturing industry. Specifically, provide information focusing on trends in manufacturing line automation and data analytics technologies. Also, thoroughly investigate representative success stories from the past five years."

[1114] This system allows users to easily create high-quality proposals, significantly improving both the quality of the proposals and user satisfaction.

[1115] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1116] Step 1:

[1117] User enters information

[1118] The user enters necessary information such as company name, industry, and purpose of the proposal into the input form on the terminal. An example of the information to be entered is "Company X, manufacturing industry, proposal for efficiency improvement."

[1119] Input: Company name, industry, purpose of proposal

[1120] Output: Input data sent to the server

[1121] Step 2:

[1122] The server receives the information and verifies its validity.

[1123] The server receives information sent by the user and checks the format of the entered data and whether all required fields are present. For example, it verifies whether the company name is entered correctly and whether the industry name is valid. If inappropriate information is entered, an error message is returned to the user.

[1124] Input: Data entered by the user

[1125] Output: Valid data, error messages (if necessary)

[1126] Step 3:

[1127] The server invokes a generative artificial intelligence to instruct it on research.

[1128] Based on the input information, the server issues research instructions to a generative artificial intelligence (e.g., GPT-4). It generates a prompt and sends an instruction to the generative AI to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[1129] Input: Valid input data

[1130] Output: Prompt message, data to send to the generative AI.

[1131] Step 4:

[1132] Generative artificial intelligence begins research

[1133] Generative artificial intelligence searches the internet and internal databases, collecting relevant information according to instructions. It then sends the research results to a server. For example, it might collect data on the latest efficiency technologies and success stories.

[1134] Input: Prompt message

[1135] Output: Research results data

[1136] Step 5:

[1137] The server analyzes the data and generates sections for the proposal.

[1138] The server receives research results returned by the generative artificial intelligence and analyzes them. Based on the analysis, it automatically generates sections for the proposal. For example, it creates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[1139] Input: Research result data

[1140] Output: Section data of the proposal

[1141] Step 6:

[1142] The server retrieves data in conjunction with the existing system.

[1143] The server integrates with existing systems such as document management systems (DMS) to retrieve past proposals and related documents. For example, it can retrieve "past proposals to a certain company" and use them as reference material for new proposals.

[1144] Input: Information about existing systems, company name

[1145] Output: Historical document data

[1146] Step 7:

[1147] The server generates a draft proposal.

[1148] The server generates a draft proposal based on research results and acquired materials. It uses an emotion recognition engine to obtain user emotion data and adjusts the tone and content of the proposal accordingly. For example, if the user is nervous, the writing style is made more approachable.

[1149] Input: Research results data, historical data, sentiment data

[1150] Output: Draft proposal data

[1151] Step 8:

[1152] The server provides the user with a draft proposal.

[1153] The server sends the generated draft proposal to the user. The user reviews the draft proposal on their device and makes revisions as needed. Simultaneously, the emotion recognition engine analyzes the user's reactions and provides a support message if negative emotions are detected.

[1154] Input: Proposal draft data, real-time sentiment data

[1155] Output: Display of a draft proposal to the user, support messages (if necessary)

[1156] Step 9:

[1157] The server prepares to sell its proposal creation support function to external customers.

[1158] The server creates marketing materials and demonstrations to sell the proposal creation support function to external customers. For example, it prepares feature explanation videos and user manuals, and carries out sales promotion activities.

[1159] Input: Information on the proposal creation support function

[1160] Output: Marketing materials, demonstration content

[1161] The above outlines the specific processing steps and details of the proposal creation support system. Through these steps, users can efficiently create high-quality proposals.

[1162] (Application Example 2)

[1163] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1164] Conventional proposal creation support systems automatically generate proposals based on information provided by the user, but they have the problem of not being able to adequately respond to customer needs and reactions because they provide proposals with uniform content and tone without considering the user's feelings. Furthermore, because they lack a mechanism to collect and reflect customer feelings and feedback in real time, it is difficult to immediately provide appropriate proposal content in sales activities at physical stores.

[1165] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1166] This invention includes a server that, based on input information, uses generative artificial intelligence to research customer industries and corporate challenges; analyzes the research results and automatically generates proposal components; collaborates with existing systems to acquire past proposals and related materials; uses the acquired materials for analysis and generates a draft proposal; provides the generated draft proposal to the user, allowing the user to finalize the proposal; and collects emotional data in real time and adjusts the content and tone of the draft proposal. This improves the quality of proposals and enables optimal proposals based on the customer's real-time emotions and needs.

[1167] "Inputted information" refers to the collection of data that users provide through input forms or devices on the system.

[1168] "Generative artificial intelligence" is an artificial intelligence technology that automatically analyzes data based on the information provided and generates relevant information.

[1169] "Research" is the process of collecting and analyzing information about the challenges facing a particular industry or company.

[1170] "Analysis" is the process of examining collected data and information in detail, extracting meaning, and understanding it.

[1171] "Proposal components" refer to some elements or sections that make up the final proposal, and include specific content and data.

[1172] "Existing systems" refer to information processing systems and databases that have been implemented in the past.

[1173] "Reference materials" refer to existing documents that are useful for creating a proposal, such as past proposals and related reference data.

[1174] A "draft proposal" is an initial document used to create the final proposal, and it contains the proposal content and data.

[1175] A "user" is an individual or company representative who uses the proposal creation support system.

[1176] "Emotional data" refers to emotional information obtained by analyzing the facial expressions and statements of users and customers.

[1177] "Real-time" refers to a time frame in which data is processed as soon as it is generated, and results are provided immediately.

[1178] "Tone" refers to the style of language and expression used in the content of a proposal or document.

[1179] This invention includes the following configuration and processes for realizing a proposal creation support system.

[1180] System Configuration

[1181] 1. Hardware Configuration

[1182] Smart glasses: Equipped with a camera to detect customer facial expressions and a display to show draft proposals.

[1183] Server: Receives and analyzes data, generates proposals, and processes sentiment data.

[1184] Edge devices: Assist in real-time processing of camera images.

[1185] 2. Software Configuration

[1186] Emotion Engine: Analyzes customer emotion data in real time from camera footage.

[1187] Proposal Generator: Generates proposal components based on user input data and sentiment data.

[1188] Generative artificial intelligence: Automatically generates proposal content based on research results.

[1189] Operation details

[1190] Information input phase

[1191] The user interacts with customers while wearing smart glasses. The smart glasses' camera captures the customer's facial expressions, and the microphone records the conversation. This data is sent to a server in real time, and simultaneously, an emotion engine is activated to analyze the customer's emotional data.

[1192] Research phase

[1193] The server uses generative artificial intelligence to research customer industries and company challenges based on the input information. Relevant information is collected and analyzed from the internet and internal databases.

[1194] Data Analysis Phase

[1195] Data, including research results, is sent to the server, and proposal components are automatically generated. This includes the latest technological trends and success stories.

[1196] Data collection phase

[1197] The server integrates with existing systems to retrieve past proposals and related documents. These documents are used for analysis to improve the quality of proposals.

[1198] Proposal generation phase

[1199] The server combines all collected data and analysis results to generate a draft proposal. Based on the emotional data obtained from the emotion engine, the content and tone of the proposal are adjusted.

[1200] Proposal submission phase

[1201] The generated proposal draft is displayed in real time on the smart glasses' screen. The salesperson uses this proposal to provide appropriate explanations to the customer and further optimizes the proposal by collecting real-time feedback from the customer.

[1202] Detailed processing instructions

[1203] The server uses Python and OpenCV to process video data and utilizes an emotion recognition engine (EmotionEngine) to perform facial expression analysis. Based on the actual emotion data, a proposal generation engine (ProposalGenerator) operates to generate proposal content. Through the coordination of each hardware and software component, optimized proposals are provided in real time, aiming to improve customer satisfaction.

[1204] Example of a prompt

[1205] "Please generate a portion of the proposal for product XYZ based on the following data. The sentiment data is [Joy: 0.8, Surprise: 0.2], and the customer appears to be interested in the product's cost-effectiveness."

[1206] Based on this prompt, the generative AI model generates appropriate proposal components, which the server then combines to complete the draft proposal. In this way, a high-quality proposal based on the user's emotional data and needs can be provided.

[1207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1208] Step 1:

[1209] Information input phase

[1210] The user interacts with a customer while wearing smart glasses. During this interaction, a camera built into the glasses captures the customer's facial expressions, and a microphone records the conversation. The collected data is transmitted to a server in real time. The server uses the received video and audio data as input, and an emotion engine analyzes it to extract the customer's emotional data (e.g., joy, surprise, sadness). This emotional data is then output. The specific actions involved in each step include capturing camera footage, recording audio, and transmitting the data.

[1211] Step 2:

[1212] Research phase

[1213] The server uses generative artificial intelligence to conduct research based on information entered by the user (customer industry, company challenges, etc.). This research extracts relevant information from the internet and internal databases and collects optimal suggestions for the user. The input is information about the customer industry and company challenges, and the output is relevant research data (e.g., latest trends, success stories, etc.). Specifically, it performs information retrieval and data extraction.

[1214] Step 3:

[1215] Data Analysis Phase

[1216] The server receives research results and sentiment data as input and analyzes them. The research results are analyzed by generative artificial intelligence, and proposal components are automatically generated. Furthermore, the tone and content of the proposal are adjusted based on the sentiment data. The output consists of each component of the proposal. Specifically, the process includes data analysis and the generation of proposal components.

[1217] Step 4:

[1218] Data collection phase

[1219] The server integrates with existing systems to retrieve past proposals and related documents. This process involves accessing a database of past proposals and collecting information and reference materials previously provided by users. The input is existing database information, and the output is the retrieved past proposals and reference materials. Specific operations include accessing the database and retrieving the documents.

[1220] Step 5:

[1221] Proposal generation phase

[1222] The server combines all collected data and analysis results to generate a draft proposal. This draft includes content that reflects research results, historical documents, and sentiment data. Inputs include research results, historical documents, and sentiment data, and output is the generated draft proposal. Specific operations include data integration and proposal draft generation.

[1223] Step 6:

[1224] Proposal submission phase

[1225] The generated proposal draft is displayed in real time on the smart glasses' screen. This allows salespeople to immediately present the proposal to customers. The input is the proposal draft, and the output is the proposal displayed on the smart glasses' screen. Specific operations include displaying data.

[1226] In this way, data is entered at each processing step, and after going through each process, the proposal is finally displayed on smart glasses.

[1227] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1228] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1230] [Fourth Embodiment]

[1231] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1232] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1234] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1238] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1239] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1240] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1241] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1242] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1243] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1244] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on input information. The processing of this system's program is described below in natural language.

[1245] Information input phase

[1246] User enters information

[1247] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, manufacturing industry, proposal for efficiency improvements."

[1248] Research phase

[1249] The server receives the information.

[1250] The server receives information entered by the user and verifies its format. Validation checks are performed as needed.

[1251] The server calls a generative artificial intelligence.

[1252] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct it to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[1253] Data Analysis Phase

[1254] The server analyzes the data.

[1255] The server analyzes the data received from the generative artificial intelligence. Based on the analysis results, it automatically generates parts of the proposal. For example, it generates sections including "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[1256] Data collection phase

[1257] The server integrates with the existing system.

[1258] The server integrates with existing systems to retrieve past proposals and related documents. For example, it can retrieve past proposals to a specific company and incorporate that information into new proposals.

[1259] Proposal generation phase

[1260] The server generates a draft proposal.

[1261] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions.

[1262] Proposal submission phase

[1263] The server provides the user with a draft proposal.

[1264] The server sends the generated draft proposal to the user, who then reviews it on their terminal. The user makes final adjustments based on the draft and completes the proposal.

[1265] External sales preparation phase

[1266] Servers are ready for sale to external customers.

[1267] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations, and explains how to use the system.

[1268] The above describes a specific embodiment of the proposal creation support system of the present invention.

[1269] The following describes the processing flow.

[1270] Step 1:

[1271] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is then sent to the server.

[1272] Step 2:

[1273] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[1274] Step 3:

[1275] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[1276] Step 4:

[1277] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data. Specifically, it extracts highly relevant information from the collected data and classifies and organizes it as components of a proposal (industry analysis, problem analysis, solutions, etc.).

[1278] Step 5:

[1279] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." This retrieved material will then be used as reference data for the new proposal.

[1280] Step 6:

[1281] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[1282] Step 7:

[1283] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their terminal and reviews its contents. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[1284] Step 8:

[1285] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[1286] The above is the specific processing flow of the proposal creation support system.

[1287] (Example 1)

[1288] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1289] Traditional proposal writing processes are inefficient, requiring a great deal of manual work such as information gathering, analysis, and referencing past proposals. Furthermore, creating proposals based on accurate information demands specialized knowledge, requiring significant time and effort. Additionally, the preparation process for providing proposal writing support systems to external clients is cumbersome. This creates a significant obstacle, especially for companies aiming to improve operational efficiency.

[1290] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1291] In this invention, the server includes means for the user to input information into an input form on the terminal, means for the server to receive the input information and check its format and validity, means for the server to call a generation AI model based on the input information and perform research, means for the server to analyze the data received from the generation AI model and generate proposal components based on the analysis results, means for the server to acquire past proposals and related materials in cooperation with existing systems, means for the server to generate a draft proposal using the acquired materials and analysis results, and means for the server to provide the generated draft proposal to the user so that the user can finalize the proposal. This enables the efficient and highly accurate automatic generation of proposals and smooth preparation for sales to external customers.

[1292] "User" refers to the end user who inputs information to create a proposal using the system.

[1293] A "terminal" refers to a hardware device used by a user to input information, and specifically includes personal computers, smartphones, and tablets.

[1294] A "server" refers to a computer system that receives input from users and performs processing using AI models for information analysis and generation.

[1295] An "input form" refers to a web-based interface that allows users to input the information necessary for creating a proposal from their device.

[1296] A "generative AI model" refers to an artificial intelligence model that automatically performs research and generates data based on the information provided.

[1297] "Research" refers to the process of collecting information on a specified topic using a generative AI model.

[1298] "Data analysis" refers to the analytical process of processing data received from a generative AI model to generate components for a proposal.

[1299] "Parts of a proposal" refer to the individual sections or elements that make up a proposal, such as industry analysis and problem analysis.

[1300] "Existing systems" refers to databases and storage systems that store past proposals and related documents that the servers are connected to.

[1301] A "draft proposal" refers to the initial version of a proposal generated by the server, an incomplete document before the user finalizes it.

[1302] "External customers" refer to third-party companies or individuals who purchase the system's proposal creation support functionality.

[1303] "Sales preparation" refers to the process of preliminary preparations such as marketing, demonstrations, and document creation for providing a system to external customers.

[1304] "Validation check" refers to the process of verifying whether the information entered by the user is accurate and complete, and returns an error message if inaccurate or incomplete information is entered.

[1305] This invention relates to a proposal creation support system, the program of which automatically generates a proposal based on the input information. The processing of this system's program will be described in detail below.

[1306] Users input information for creating proposals using their devices. These devices can include PCs and smartphones. Specifically, the information provided by users might include "Company A, Manufacturing Industry, Proposal for Efficiency Improvement." The input form is a web form using HTML or JavaScript. For example, the user might input specific details such as "Company A, New Product Development, Proposal for Innovative Technology."

[1307] When information is entered, the server receives it. The server uses a message queue system such as Apache Kafka or RabbitMQ to receive the information and check its format and validity. It checks the format of the received information to ensure that all required fields are filled in and that no inappropriate information is included. To verify validity, it checks whether the entered content is in the correct format and returns an error message if inappropriate information is entered.

[1308] The server uses properly formatted information to generate AI models (for example, OpenAI's GPT-4 model) and conduct research. For example, it might be instructed to research "the latest trends and case studies of efficiency improvements in the manufacturing industry." The prompt in this case would be, "Please tell me about the latest trends and success stories of efficiency improvements in the manufacturing industry."

[1309] When the AI ​​model provides data, the server analyzes it. Data analysis uses Python's Pandas and NumPy libraries. Based on the analysis results, the server automatically generates proposal components. Specifically, it embeds the generated data into a template and creates sections such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories."

[1310] Furthermore, the server integrates with existing systems to retrieve past proposals and related documents. The server uses databases such as MySQL or PostgreSQL to extract the necessary data and incorporate it into the new proposal. This makes it possible to retrieve past "proposals to a certain company" and reflect them in the new proposal.

[1311] The server generates a draft proposal based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and proposed solutions. Document generation tools such as LaTeX and Markdown are used to generate the proposal. Specifically, a template engine is used to embed the data in the appropriate places and convert it into the final document format.

[1312] The generated draft proposal is sent from the server to the user. This is done via email or a dedicated web interface, and the user reviews the draft proposal on their device. The user then makes any necessary final adjustments based on the submitted draft proposal to complete the proposal.

[1313] Finally, the server prepares to provide proposal creation support functions to external customers. Specifically, this includes preparing digital marketing materials and demonstrations. Marketing materials are created using Adobe Creative Cloud, and demonstrations are conducted using Zoom or Microsoft Teams.

[1314] The above describes a specific embodiment of the proposal creation support system of this invention.

[1315] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1316] Step 1:

[1317] User enters information

[1318] The user enters information into an input form on their device. This information includes company name, industry, and proposal details, all necessary for creating a proposal. The input form is implemented as a web form using HTML and JavaScript. Once the input data is submitted, the device sends that data to the server.

[1319] Specific actions

[1320] Fill in the input form with specific details such as "Company Name, Manufacturing Industry, Proposal for Efficiency Improvement," and click the "Submit" button.

[1321] Input: Information entered by the user (company name, industry, proposal details)

[1322] Output: Information is sent from the terminal to the server.

[1323] Step 2:

[1324] The server receives the information and checks its format and validity.

[1325] The server processes the information received from the terminal and checks the format and validity of the input data. Using a message queue system such as Apache Kafka or RabbitMQ, it verifies after receiving the data whether the format is correct and whether all required fields are present. If the validity is not confirmed, it generates an error message and sends it back to the terminal.

[1326] Specific actions

[1327] The system checks whether the received data is in the correct format, and if the data is inappropriate, it returns an error message such as "Company name is not entered."

[1328] Input: Information sent from the device

[1329] Output: Formatted information, or error message.

[1330] Step 3:

[1331] The server calls the generated AI model to perform research.

[1332] The server calls a generating AI model (such as OpenAI's GPT-4) based on the input information. It issues specific research instructions and collects the necessary data. It uses specific sentences as prompts, such as "Please tell me about the latest trends and examples of efficiency improvements in the manufacturing industry."

[1333] Specific actions

[1334] This process sends a prompt to a generative AI model to retrieve information about a specified topic. The retrieved data is also temporarily stored.

[1335] Input: Formatted information

[1336] Output: Research data received from the generative AI model

[1337] Step 4:

[1338] The server analyzes the data and generates parts for the proposal.

[1339] The server analyzes the data received from the generated AI model using Python libraries such as Pandas and NumPy. Based on the analysis results, it automatically generates components for the proposal document.

[1340] Specific actions

[1341] Based on the analysis results, sections of the proposal document such as "Latest Trends in Efficiency Improvement Technologies" and "Details of Success Stories" are generated. Unnecessary data is filtered out during the analysis process.

[1342] Input: Data received from the generated AI model

[1343] Output: Proposal parts (sections)

[1344] Step 5:

[1345] The server retrieves data in conjunction with the existing system.

[1346] The server retrieves past proposals and related documents from existing databases such as MySQL and PostgreSQL. This makes it possible to reference past data in new proposals.

[1347] Specific actions

[1348] Use SQL queries to extract necessary data from the database and incorporate the processing results into a draft of the new proposal.

[1349] Input: Request for necessary past proposals and related documents

[1350] Output: Past proposals and related document data

[1351] Step 6:

[1352] The server generates the draft proposal.

[1353] The server generates a draft proposal based on the collected data and analysis results. This draft proposal includes industry analysis, problem analysis, and proposed solutions. It is then converted into a document format using document generation tools such as LaTeX or Markdown.

[1354] Specific actions

[1355] A template engine is used to embed proposal components in the appropriate locations. Finally, it is converted to formats such as PDF and Word.

[1356] Input: Analysis results and existing documents

[1357] Output: Draft proposal

[1358] Step 7:

[1359] The server provides the user with a draft proposal.

[1360] The server sends the generated draft proposal to the user. This is done via email or a dedicated web interface. The user reviews the draft proposal on their terminal and makes any necessary final adjustments.

[1361] Specific actions

[1362] The draft proposal will be generated in formats such as PDF files and provided via email attachment or web dashboard.

[1363] Input: Generated proposal draft

[1364] Output: Draft proposal provided to the user

[1365] Step 8:

[1366] The server prepares for sale to external customers.

[1367] The server prepares to provide proposal creation support functions to external customers. It also prepares digital marketing materials and demonstrations.

[1368] Specific actions

[1369] We will create marketing materials using Adobe Creative Cloud and conduct demonstrations using Zoom, Microsoft Teams, and other tools.

[1370] Input: System sales materials and demonstration content

[1371] Output: Marketing materials and demonstrations provided to external customers.

[1372] (Application Example 1)

[1373] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1374] In modern business processes, particularly in the operation of logistics centers, the creation of proposals quickly and effectively is essential. However, traditional methods require considerable time and effort, and make it difficult to efficiently utilize the latest information and past proposals. Furthermore, there is a lack of systems that allow for information input, confirmation, and modification on mobile devices, hindering operational efficiency. Against this backdrop, there is a need for a system that efficiently researches industry trends and specific case studies and automatically generates high-quality proposals.

[1375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1376] In this invention, the server includes means for researching target fields and issues using generative artificial intelligence based on input information, means for analyzing the research results and automatically generating parts of a proposal document, and means for linking with an existing database to acquire past proposal documents and related materials. This enables users to quickly create proposals based on the latest industry trends and specific examples, and to easily input, confirm, and modify information via a mobile device. Furthermore, the system's convenience and reliability are improved by including means for preparing to sell the generated proposal document creation support function to external consumers, and means for verifying the validity of information provided by users and returning error messages if inappropriate information is entered.

[1377] "Inputted information" refers to the data and detailed information that the user provides to the system for creating the proposal.

[1378] "Generative artificial intelligence" refers to an artificial intelligence model that can automatically generate and analyze information based on provided data.

[1379] "Target field" refers to the specific industry or field that is the subject of research or proposal writing.

[1380] A "problem" refers to an issue that needs to be solved or an area for improvement within the field in question.

[1381] The "research method" refers to a function that uses generative artificial intelligence based on input information to investigate the latest industry trends and success stories.

[1382] "Means of analysis" refers to the function of analyzing data obtained from research and extracting useful information for the proposal.

[1383] "Parts of the proposal document" refers to each section or element that makes up the proposal.

[1384] "Automatic generation method" refers to a function that automatically generates a proposal document based on the analyzed results.

[1385] An "existing database" is a system that stores past proposals, related documents, industry data, and other similar information.

[1386] "Means of collaboration" refers to the function of communicating with existing databases and retrieving necessary data.

[1387] A "mobile device" is a portable information processing device such as a smartphone or tablet.

[1388] A "user" is an individual or organization that uses the system to create a proposal.

[1389] "External consumers" refers to external individuals or corporations who purchase or use the services of this system.

[1390] "Means of preparing for sale" refers to the function of preparing to offer the generated proposal creation support function to the market.

[1391] "Means of validating validity" refers to a function that verifies whether the information entered by the user is accurate.

[1392] An "error message" is a message sent to the user when there is a problem with the information they have entered.

[1393] "Reliability" refers to a system's ability to deliver accurate and consistent results.

[1394] The system for implementing this invention enables operators of logistics centers and other facilities to efficiently prepare proposals. This system consists of the following main phases.

[1395] Information input phase

[1396] Users use mobile devices (smartphones or tablets) to input the information necessary to create a proposal. For example, they enter the client name, industry name, and the purpose of the proposal. This information is collected via the input form and sent to the server.

[1397] Research phase

[1398] The server receives the input information and uses generative artificial intelligence (such as the OpenAI API) to research the latest trends and success stories related to the target field and challenges. An example of a prompt used here is, "Please research the latest trends and success stories in the logistics industry."

[1399] Data Analysis Phase

[1400] The server analyzes the data received from the generative artificial intelligence and automatically generates the proposal document. This includes details of the latest efficiency technologies and success stories. Based on the analysis results, a concrete proposal document is constructed.

[1401] Data collection phase

[1402] The server integrates with existing databases (such as proposal management systems) to retrieve past proposal documents and related materials. This information is then incorporated into the content of new proposals.

[1403] Proposal generation phase

[1404] The server generates a draft proposal document based on the collected data and analysis results. This draft includes industry analysis, problem analysis, and details of the proposed solutions.

[1405] Proposal submission phase

[1406] The generated proposal draft is provided to the user's mobile device, allowing them to review the draft and make revisions as needed. This enables the user to finalize the proposal quickly and effectively.

[1407] External sales preparation phase

[1408] The server prepares to sell the generated proposal document creation support function to external consumers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system.

[1409] Furthermore, the system includes a function to verify the validity of information provided by users and return an error message if inappropriate information is entered. This improves the reliability and usability of the system.

[1410] Ultimately, this system enables logistics center operators to quickly propose operational efficiency improvements and enhancements, and to easily input, verify, and modify information via mobile devices. In this way, the entire proposal creation process is significantly streamlined.

[1411] The following is an example of a prompt statement:

[1412] 1. "Please research the latest trends and success stories in the logistics industry."

[1413] 2. "Please explain how the latest trends in efficiency technologies can be applied to logistics centers."

[1414] The main hardware used will be smartphones, tablets, and servers, while the software will include the OpenAI API, APIs for existing proposal management systems, Python, and the Requests library.

[1415] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1416] Step 1:

[1417] The user enters information using a mobile device. Specifically, they fill in information such as the client name, industry name, and the purpose of the proposal in an input form. This information is then sent from the device to the server.

[1418] Input: Client name, industry, purpose of the proposal, etc.

[1419] Output: Input information sent to the server.

[1420] Step 2:

[1421] Based on the information received by the server, prompts are sent to the generative AI model. For example, a prompt such as "Research the latest trends and success stories in the logistics industry" might be sent to the generative AI model (e.g., via the OpenAI API).

[1422] Input: Client name, industry, purpose of the proposal.

[1423] Output: Prompts for the generative AI model and research result data from the generative AI model.

[1424] Step 3:

[1425] The server analyzes the research results obtained from the generated AI model. Specifically, it performs text analysis on the acquired data and extracts and organizes important information that should be included in the proposed document.

[1426] Input: Research result data from a generated AI model.

[1427] Output: Analysis results with important information organized.

[1428] Step 4:

[1429] The server connects with the existing database (proposal management system) to retrieve past proposal documents and related materials. If necessary, the server sends an API request to download the materials.

[1430] Input: Information such as client name and industry.

[1431] Output: Past proposal documents and related materials.

[1432] Step 5:

[1433] The server automatically generates a draft of the proposal document based on the analysis results and acquired data. Specifically, it generates each section that makes up the entire proposal document, such as industry analysis and solutions.

[1434] Input: Analysis results, past proposal documents, and related materials.

[1435] Output: Draft of the proposal document.

[1436] Step 6:

[1437] The server provides a draft of the proposal document to the mobile device, allowing the user to review and modify it. The user then makes revisions on the device and finalizes the proposal document.

[1438] Input: Draft of the proposal document.

[1439] Output: Finalized proposal document.

[1440] Step 7:

[1441] Prepare marketing materials and demonstrations to provide external consumers with the proposal document creation support function generated by the server.

[1442] Input: A sample of the overall system functionality and proposed document.

[1443] Output: Marketing materials, demo content.

[1444] Through the steps outlined above, users will be able to create high-quality proposal documents efficiently and quickly.

[1445] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1446] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates a proposal based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposal and user satisfaction.

[1447] Information input phase

[1448] User enters information

[1449] The user fills in the necessary information for creating the proposal in the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotion data from the user's facial expressions and input.

[1450] Research phase

[1451] The server receives the information.

[1452] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed.

[1453] The server calls a generative artificial intelligence.

[1454] The server issues research instructions to the generative artificial intelligence based on the input information. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[1455] Data Analysis Phase

[1456] The server analyzes the data.

[1457] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates parts for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[1458] Data collection phase

[1459] The server integrates with the existing system.

[1460] The server integrates with existing systems to retrieve past proposals and related documents. For example, the server accesses an existing proposal database to retrieve "past proposals for a certain company." This retrieved material is then used as reference data for new proposals.

[1461] Proposal generation phase

[1462] The server generates a draft proposal.

[1463] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format. Furthermore, it adjusts the tone and content of the proposal, taking into account user sentiment data analyzed by the sentiment engine.

[1464] Proposal submission phase

[1465] The server provides the user with a draft proposal.

[1466] The server provides the user with a draft proposal. The user receives the draft proposal on their device and reviews its contents. The emotion engine analyzes the user's real-time reactions and provides support messages if negative emotions are detected. The user makes any necessary adjustments and additional customizations to complete the final proposal.

[1467] External sales preparation phase

[1468] The server is preparing to sell its proposal creation support function to external customers.

[1469] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[1470] The above is a specific implementation of a proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[1471] The following describes the processing flow.

[1472] Step 1:

[1473] The user enters the information necessary to create the proposal into the input form on their device. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server. Simultaneously, the emotion engine collects emotional data from the user's facial expressions, input speed, and other factors.

[1474] Step 2:

[1475] The server receives information entered by the user. This information includes company name, industry, and purpose of the proposal. The server checks the format of the input information and performs validation checks as needed. For example, if there are any problems with the input information, it generates an error message and returns it to the user.

[1476] Step 3:

[1477] The server invokes a generative artificial intelligence (AI) and issues research instructions based on user input. For example, it might instruct the AI ​​to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI then searches the internet and internal databases to collect relevant information.

[1478] Step 4:

[1479] The generative artificial intelligence returns the research results to the server. The server analyzes the collected data and automatically generates components for the proposal (industry analysis, problem analysis, proposed solutions, etc.). For example, it generates sections including "latest trends in efficiency technologies" and "details of success stories."

[1480] Step 5:

[1481] The server will, as needed, integrate with existing systems to retrieve past proposals and related documents. For example, the server will access an existing proposal database and retrieve "past proposals for a certain company." These retrieved documents will then be used as reference data for the new proposal.

[1482] Step 6:

[1483] The server combines all collected data and analysis results to generate a draft proposal. The draft proposal includes industry analysis, problem analysis, and proposed solutions based on research results and existing materials. The server uses an automated generation algorithm to create a draft that conforms to the proposal format.

[1484] Step 7:

[1485] The emotion engine analyzes emotional data collected from the user, and if the user is experiencing anxiety or stress while creating a proposal, the server generates an appropriate support message and displays it on the terminal. For example, a message such as "Do you need any additional information on this section?" might be displayed.

[1486] Step 8:

[1487] The server generates a draft proposal and provides it to the user. The user receives the draft proposal on their device and reviews its contents. The sentiment engine analyzes the user's real-time reactions and, if positive sentiment is indicated, verifies that the proposal's content is appropriate. If negative sentiment is detected, additional revisions or advice are provided.

[1488] Step 9:

[1489] The user completes the final proposal based on the draft. The user makes additional edits and customizations on their device, and throughout the proposal completion process, the sentiment engine monitors the user's feedback and provides further support as needed.

[1490] Step 10:

[1491] The server prepares to sell its proposal creation support function to external customers. Specifically, it prepares marketing materials and demonstrations to explain how to use the system. This will enable external customers to use the system to create proposals efficiently.

[1492] The above is the specific processing flow of the proposal creation support system that incorporates an emotion engine. This system aims to improve the efficiency and quality of proposal creation, and to increase user satisfaction.

[1493] (Example 2)

[1494] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1495] In proposal creation, there are challenges in automatically verifying the validity of user input and ensuring that the content and tone of the proposal meet user expectations, thereby improving user satisfaction. Furthermore, there is a lack of means to improve proposal quality by considering user emotions, thus creating a need for both increased efficiency and higher quality in proposal creation.

[1496] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1497] In this invention, the server includes means for receiving user-inputted information and verifying its validity; means for researching industries and issues based on the input information using generative artificial intelligence; means for analyzing the research results and automatically generating sections for the proposal; means for acquiring past data in cooperation with existing systems; means for using the acquired data for analysis and generating a draft proposal; means for acquiring user emotion data using an emotion recognition engine and adjusting the tone and content of the proposal; and means for providing the generated draft proposal to the user, analyzing the user's reaction in real time, and providing support messages. This makes it possible to automatically verify the validity of the user's input information and improve user satisfaction and the quality of the proposal by ensuring that the generated proposal has a tone and content that reflects the user's emotions.

[1498] "Means for receiving user-entered information and verifying its validity" refers to a function that allows a server to receive information entered by a user into the system and check whether that information is accurate and complete.

[1499] "A means of researching industries and issues based on input information using generative artificial intelligence" refers to a function in which a server utilizes generative artificial intelligence to collect the latest industry information and issues related to the information entered by the user from the internet or internal databases.

[1500] "A means of analyzing research results and automatically generating sections of a proposal" refers to a function in which the server analyzes research results obtained from a generative artificial intelligence and automatically creates each section of the proposal based on that information.

[1501] "Methods for retrieving past documents by linking with existing systems" refers to a function that allows the server to link with existing document management systems and databases to retrieve proposals and related documents created in the past.

[1502] "A means of using acquired data for analysis and generating a draft proposal" refers to a function that uses past data acquired by the server for analysis and creates a draft of a new proposal based on that data.

[1503] "A means of acquiring user emotional data using an emotion recognition engine and adjusting the tone and content of the proposal" refers to a function in which the server uses an emotion recognition engine to collect user emotional data and then appropriately adjusts the tone and content of the proposal based on the results.

[1504] "A means of providing users with generated draft proposals, analyzing user reactions in real time, and providing support messages" refers to a function in which the server provides users with generated draft proposals, analyzes users' real-time reactions through an emotion recognition engine, and sends support messages as needed.

[1505] "Means of preparing to sell the generated proposal creation support function to external customers" refers to the function that prepares the server to sell the proposal creation support function to external users. This preparation includes creating marketing materials and demonstrations.

[1506] This invention combines user emotion recognition with a proposal creation support system. This system automatically generates proposals based on information entered by the user, recognizes the user's emotions, and improves the quality of the proposals and user satisfaction.

[1507] First, the user enters the necessary information for creating the proposal into the input form on the terminal. For example, they might enter information such as "Company X, Manufacturing Industry, Proposal for Efficiency Improvement." This information is sent to the server, and at the same time, the emotion engine collects emotion data from the user's facial expressions and input.

[1508] Next, the server checks the received information for validation. It verifies whether the entered company name, industry, and purpose of the proposal are valid, and checks the format and required fields as needed. If inappropriate information is entered, the server returns an error message to the user.

[1509] Next, the server invokes a generative artificial intelligence (e.g., GPT-4) and instructs it to research industries and issues based on the input information. For example, it might be instructed to research "the latest trends and case studies in efficiency improvements in the manufacturing industry." The generative AI searches the internet and internal databases to collect relevant information.

[1510] The server analyzes research results sent from the generative artificial intelligence and automatically generates sections for the proposal. For example, it generates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[1511] Subsequently, the server integrates with the existing system to retrieve past proposals and related documents. It accesses the existing document management system (DMS) and retrieves "past proposals to a certain company." These documents are used as reference materials for the new proposal.

[1512] Next, the server generates a draft proposal based on the collected research results and acquired materials. The emotion recognition engine adjusts the tone and content based on the user's emotional data. For example, if the user is feeling nervous, the proposal's writing style will be made more approachable.

[1513] The server provides the user with a generated draft proposal, which the user then reviews on their device. The emotion recognition engine analyzes the user's real-time reactions and provides a support message if negative emotions are detected.

[1514] Finally, the server prepares to sell its proposal creation support function to external customers. This includes creating marketing materials and demonstrations. For example, it prepares feature explanation videos and user manuals, and conducts sales promotion activities.

[1515] As a concrete example, if a user inputs the information "a certain company, manufacturing industry, efficiency improvement proposal," an example of a prompt message for a generative artificial intelligence would be as follows:

[1516] "Research the latest efficiency technologies and success stories in the manufacturing industry. Specifically, provide information focusing on trends in manufacturing line automation and data analytics technologies. Also, thoroughly investigate representative success stories from the past five years."

[1517] This system allows users to easily create high-quality proposals, significantly improving both the quality of the proposals and user satisfaction.

[1518] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1519] Step 1:

[1520] User enters information

[1521] The user enters necessary information such as company name, industry, and purpose of the proposal into the input form on the terminal. An example of the information to be entered is "Company X, manufacturing industry, proposal for efficiency improvement."

[1522] Input: Company name, industry, purpose of proposal

[1523] Output: Input data sent to the server

[1524] Step 2:

[1525] The server receives the information and verifies its validity.

[1526] The server receives information sent by the user and checks the format of the entered data and whether all required fields are present. For example, it verifies whether the company name is entered correctly and whether the industry name is valid. If inappropriate information is entered, an error message is returned to the user.

[1527] Input: Data entered by the user

[1528] Output: Valid data, error messages (if necessary)

[1529] Step 3:

[1530] The server invokes a generative artificial intelligence to instruct it on research.

[1531] Based on the input information, the server issues research instructions to a generative artificial intelligence (e.g., GPT-4). It generates a prompt and sends an instruction to the generative AI to research "the latest trends and case studies in efficiency improvements in the manufacturing industry."

[1532] Input: Valid input data

[1533] Output: Prompt message, data to send to the generative AI.

[1534] Step 4:

[1535] Generative artificial intelligence begins research

[1536] Generative artificial intelligence searches the internet and internal databases, collecting relevant information according to instructions. It then sends the research results to a server. For example, it might collect data on the latest efficiency technologies and success stories.

[1537] Input: Prompt message

[1538] Output: Research results data

[1539] Step 5:

[1540] The server analyzes the data and generates sections for the proposal.

[1541] The server receives research results returned by the generative artificial intelligence and analyzes them. Based on the analysis, it automatically generates sections for the proposal. For example, it creates sections including "Latest Trends in Efficiency Technologies" and "Details of Success Stories."

[1542] Input: Research result data

[1543] Output: Section data of the proposal

[1544] Step 6:

[1545] The server retrieves data in conjunction with the existing system.

[1546] The server integrates with existing systems such as document management systems (DMS) to retrieve past proposals and related documents. For example, it can retrieve "past proposals to a certain company" and use them as reference material for new proposals.

[1547] Input: Information about existing systems, company name

[1548] Output: Historical document data

[1549] Step 7:

[1550] The server generates a draft proposal.

[1551] The server generates a draft proposal based on research results and acquired materials. It uses an emotion recognition engine to obtain user emotion data and adjusts the tone and content of the proposal accordingly. For example, if the user is nervous, the writing style is made more approachable.

[1552] Input: Research results data, historical data, sentiment data

[1553] Output: Draft proposal data

[1554] Step 8:

[1555] The server provides the user with a draft proposal.

[1556] The server sends the generated draft proposal to the user. The user reviews the draft proposal on their device and makes revisions as needed. Simultaneously, the emotion recognition engine analyzes the user's reactions and provides a support message if negative emotions are detected.

[1557] Input: Proposal draft data, real-time sentiment data

[1558] Output: Display of a draft proposal to the user, support messages (if necessary)

[1559] Step 9:

[1560] The server prepares to sell its proposal creation support function to external customers.

[1561] The server creates marketing materials and demonstrations to sell the proposal creation support function to external customers. For example, it prepares feature explanation videos and user manuals, and carries out sales promotion activities.

[1562] Input: Information on the proposal creation support function

[1563] Output: Marketing materials, demonstration content

[1564] The above outlines the specific processing steps and details of the proposal creation support system. Through these steps, users can efficiently create high-quality proposals.

[1565] (Application Example 2)

[1566] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1567] Conventional proposal creation support systems automatically generate proposals based on information provided by the user, but they have the problem of not being able to adequately respond to customer needs and reactions because they provide proposals with uniform content and tone without considering the user's feelings. Furthermore, because they lack a mechanism to collect and reflect customer feelings and feedback in real time, it is difficult to immediately provide appropriate proposal content in sales activities at physical stores.

[1568] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1569] This invention includes a server that, based on input information, uses generative artificial intelligence to research customer industries and corporate challenges; analyzes the research results and automatically generates proposal components; collaborates with existing systems to acquire past proposals and related materials; uses the acquired materials for analysis and generates a draft proposal; provides the generated draft proposal to the user, allowing the user to finalize the proposal; and collects emotional data in real time and adjusts the content and tone of the draft proposal. This improves the quality of proposals and enables optimal proposals based on the customer's real-time emotions and needs.

[1570] "Inputted information" refers to the collection of data that users provide through input forms or devices on the system.

[1571] "Generative artificial intelligence" is an artificial intelligence technology that automatically analyzes data based on the information provided and generates relevant information.

[1572] "Research" is the process of collecting and analyzing information about the challenges facing a particular industry or company.

[1573] "Analysis" is the process of examining collected data and information in detail, extracting meaning, and understanding it.

[1574] "Proposal components" refer to some elements or sections that make up the final proposal, and include specific content and data.

[1575] "Existing systems" refer to information processing systems and databases that have been implemented in the past.

[1576] "Reference materials" refer to existing documents that are useful for creating a proposal, such as past proposals and related reference data.

[1577] A "draft proposal" is an initial document used to create the final proposal, and it contains the proposal content and data.

[1578] A "user" is an individual or company representative who uses the proposal creation support system.

[1579] "Emotional data" refers to emotional information obtained by analyzing the facial expressions and statements of users and customers.

[1580] "Real-time" refers to a time frame in which data is processed as soon as it is generated, and results are provided immediately.

[1581] "Tone" refers to the style of language and expression used in the content of a proposal or document.

[1582] This invention includes the following configuration and processes for realizing a proposal creation support system.

[1583] System Configuration

[1584] 1. Hardware Configuration

[1585] Smart glasses: Equipped with a camera to detect customer facial expressions and a display to show draft proposals.

[1586] Server: Receives and analyzes data, generates proposals, and processes sentiment data.

[1587] Edge devices: Assist in real-time processing of camera images.

[1588] 2. Software Configuration

[1589] Emotion Engine: Analyzes customer emotion data in real time from camera footage.

[1590] Proposal Generator: Generates proposal components based on user input data and sentiment data.

[1591] Generative artificial intelligence: Automatically generates proposal content based on research results.

[1592] Operation details

[1593] Information input phase

[1594] The user interacts with customers while wearing smart glasses. The smart glasses' camera captures the customer's facial expressions, and the microphone records the conversation. This data is sent to a server in real time, and simultaneously, an emotion engine is activated to analyze the customer's emotional data.

[1595] Research phase

[1596] The server uses generative artificial intelligence to research customer industries and company challenges based on the input information. Relevant information is collected and analyzed from the internet and internal databases.

[1597] Data Analysis Phase

[1598] Data, including research results, is sent to the server, and proposal components are automatically generated. This includes the latest technological trends and success stories.

[1599] Data collection phase

[1600] The server integrates with existing systems to retrieve past proposals and related documents. These documents are used for analysis to improve the quality of proposals.

[1601] Proposal generation phase

[1602] The server combines all collected data and analysis results to generate a draft proposal. Based on the emotional data obtained from the emotion engine, the content and tone of the proposal are adjusted.

[1603] Proposal submission phase

[1604] The generated proposal draft is displayed in real time on the smart glasses' screen. The salesperson uses this proposal to provide appropriate explanations to the customer and further optimizes the proposal by collecting real-time feedback from the customer.

[1605] Detailed processing instructions

[1606] The server uses Python and OpenCV to process video data and utilizes an emotion recognition engine (EmotionEngine) to perform facial expression analysis. Based on the actual emotion data, a proposal generation engine (ProposalGenerator) operates to generate proposal content. Through the coordination of each hardware and software component, optimized proposals are provided in real time, aiming to improve customer satisfaction.

[1607] Example of a prompt

[1608] "Please generate a portion of the proposal for product XYZ based on the following data. The sentiment data is [Joy: 0.8, Surprise: 0.2], and the customer appears to be interested in the product's cost-effectiveness."

[1609] Based on this prompt, the generative AI model generates appropriate proposal components, which the server then combines to complete the draft proposal. In this way, a high-quality proposal based on the user's emotional data and needs can be provided.

[1610] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1611] Step 1:

[1612] Information input phase

[1613] The user interacts with a customer while wearing smart glasses. During this interaction, a camera built into the glasses captures the customer's facial expressions, and a microphone records the conversation. The collected data is transmitted to a server in real time. The server uses the received video and audio data as input, and an emotion engine analyzes it to extract the customer's emotional data (e.g., joy, surprise, sadness). This emotional data is then output. The specific actions involved in each step include capturing camera footage, recording audio, and transmitting the data.

[1614] Step 2:

[1615] Research phase

[1616] The server uses generative artificial intelligence to conduct research based on information entered by the user (customer industry, company challenges, etc.). This research extracts relevant information from the internet and internal databases and collects optimal suggestions for the user. The input is information about the customer industry and company challenges, and the output is relevant research data (e.g., latest trends, success stories, etc.). Specifically, it performs information retrieval and data extraction.

[1617] Step 3:

[1618] Data Analysis Phase

[1619] The server receives research results and sentiment data as input and analyzes them. The research results are analyzed by generative artificial intelligence, and proposal components are automatically generated. Furthermore, the tone and content of the proposal are adjusted based on the sentiment data. The output consists of each component of the proposal. Specifically, the process includes data analysis and the generation of proposal components.

[1620] Step 4:

[1621] Data collection phase

[1622] The server integrates with existing systems to retrieve past proposals and related documents. This process involves accessing a database of past proposals and collecting information and reference materials previously provided by users. The input is existing database information, and the output is the retrieved past proposals and reference materials. Specific operations include accessing the database and retrieving the documents.

[1623] Step 5:

[1624] Proposal generation phase

[1625] The server combines all collected data and analysis results to generate a draft proposal. This draft includes content that reflects research results, historical documents, and sentiment data. Inputs include research results, historical documents, and sentiment data, and output is the generated draft proposal. Specific operations include data integration and proposal draft generation.

[1626] Step 6:

[1627] Proposal submission phase

[1628] The generated proposal draft is displayed in real time on the smart glasses' screen. This allows salespeople to immediately present the proposal to customers. The input is the proposal draft, and the output is the proposal displayed on the smart glasses' screen. Specific operations include displaying data.

[1629] In this way, data is entered at each processing step, and after going through each process, the proposal is finally displayed on smart glasses.

[1630] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1631] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1632] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1633] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1634] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1635] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1636] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1637] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1638] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1639] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1640] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1641] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1642] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1643] 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.

[1644] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1645] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1646] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1647] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1648] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1649] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1650] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1651] The following is further disclosed regarding the embodiments described above.

[1652] (Claim 1)

[1653] Based on the input information, a method for researching customer industries and corporate challenges using generative artificial intelligence,

[1654] A method for analyzing research results and automatically generating proposal components,

[1655] A means to acquire past proposals and related documents by integrating with existing systems,

[1656] A means of using the acquired data for analysis and generating a draft of the proposal,

[1657] A method for providing the user with a generated draft proposal and for the user to finalize the proposal,

[1658] A system that includes this.

[1659] (Claim 2)

[1660] The system according to claim 1, further comprising means for preparing to sell the generated proposal creation support function to an external customer.

[1661] (Claim 3)

[1662] The system according to claim 1, further comprising means for verifying the validity of information provided by a user and returning an error message if inappropriate information is entered.

[1663] "Example 1"

[1664] (Claim 1)

[1665] A means by which the user enters information into an input form on the device,

[1666] A means for the server to receive the input information and check its format and validity,

[1667] A method for the server to call a generated AI model based on input information to perform research,

[1668] A means by which a server analyzes data received from a generating AI model and generates proposal components based on the analysis results,

[1669] A means for the server to integrate with existing systems to retrieve past proposals and related documents,

[1670] A means by which the server generates a draft proposal using the acquired data and analysis results,

[1671] A method by which the server provides the generated draft proposal to the user, allowing the user to finalize the proposal,

[1672] A system that includes this.

[1673] (Claim 2)

[1674] The system according to claim 1, further comprising means for preparing to sell the generated proposal creation support function to an external customer.

[1675] (Claim 3)

[1676] The system according to claim 1, further comprising means for verifying the validity of information provided by a user and returning an error message if inappropriate information is entered.

[1677] "Application Example 1"

[1678] (Claim 1)

[1679] Based on the input information, a means of researching target fields and issues using generative artificial intelligence,

[1680] A means of analyzing research results and automatically generating the proposal document section,

[1681] A means of retrieving past proposal documents and related materials by linking with existing databases,

[1682] A means of using the acquired data for analysis and generating a draft of the proposal document,

[1683] A means to provide users with a generated draft proposal document and for users to finalize the proposal document,

[1684] A means to enable information input, confirmation, and correction on a mobile device,

[1685] A system that includes this.

[1686] (Claim 2)

[1687] The system according to claim 1, further comprising means for preparing to sell the generated proposal document creation support function to external consumers.

[1688] (Claim 3)

[1689] The system according to claim 1, further comprising means for verifying the validity of information provided by a user and returning an error message if inappropriate information is entered.

[1690] "Example 2 of combining an emotion engine"

[1691] (Claim 1)

[1692] A means of receiving information entered by a user and verifying its validity,

[1693] A method for researching industries and issues based on input information using generative artificial intelligence,

[1694] A means of analyzing research results and automatically generating sections for a proposal,

[1695] A means of retrieving historical data by linking with existing systems,

[1696] A means of using the acquired data for analysis and generating a draft of the proposal,

[1697] A means of acquiring user emotion data using an emotion recognition engine and adjusting the tone and content of the proposal,

[1698] A means of providing users with a generated draft proposal, analyzing user reactions in real time, and providing support messages,

[1699] A system that includes this.

[1700] (Claim 2)

[1701] The system according to claim 1, further comprising means for preparing to sell the generated proposal creation support function to an external customer.

[1702] (Claim 3)

[1703] The system according to claim 1, further comprising means for returning an error message if the information entered by the user is inappropriate.

[1704] "Application example 2 when combining with an emotional engine"

[1705] (Claim 1)

[1706] Based on the input information, a method for researching customer industries and corporate challenges using generative artificial intelligence,

[1707] A method for analyzing research results and automatically generating proposal components,

[1708] A means to acquire past proposals and related documents by integrating with existing systems,

[1709] A means of using the acquired data for analysis and generating a draft of the proposal,

[1710] A method for providing the user with a generated draft proposal and for the user to finalize the proposal,

[1711] A means of collecting emotional data in real time and adjusting the content and tone of the proposal draft,

[1712] A system that includes this.

[1713] (Claim 2)

[1714] The system according to claim 1, which prepares to sell the generated proposal creation support function to an external customer.

[1715] (Claim 3)

[1716] The system according to claim 1, further comprising means for verifying the validity of information provided by a user and returning an error message if inappropriate information is entered. [Explanation of symbols]

[1717] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Based on the input information, a method for researching customer industries and corporate challenges using generative artificial intelligence, A method for analyzing research results and automatically generating proposal components, A means to acquire past proposals and related documents by integrating with existing systems, A means of using the acquired data for analysis and generating a draft of the proposal, A method for providing the user with a generated draft proposal and for the user to finalize the proposal, A system that includes this.

2. The system according to claim 1, further comprising means for preparing to sell the generated proposal creation support function to an external customer.

3. The system according to claim 1, further comprising means for verifying the validity of information provided by a user and returning an error message if inappropriate information is entered.

Images