system

Abstract

Provide a system. 【Solution means】 Means for obtaining public notice information of public institutions, Means for filtering the obtained public notice information based on the conditions of the business entity, Means for checking the participation eligibility requirements of the filtered public notice information, Means for generating a proposal template based on the confirmed requirements, Means for analyzing past bidding data and predicting the optimal bidding amount, Means for adjusting the generated proposal to generate the final version, Means for submitting the final version and related documents to the online portal of public institutions, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When participating in bidding and proposal activities carried out by local governments and public institutions, business entities are forced to rely on a lot of manual information collection and proposal preparation processes. This process requires a great deal of labor and time, and there is also a problem that specialized knowledge is required to ensure the confirmation of participation qualifications and the appropriateness of the content of the proposal. Furthermore, the determination of the optimal bidding amount often depends on experience, and as a result, it has become a major factor affecting the success rate. In such a situation, there is a need for a technology that can efficiently and integrally perform the process from obtaining public information to submitting a proposal.

Means for Solving the Problems

[0005] This invention provides a system that automatically acquires public notices from public institutions and filters them based on the conditions of the business entity. It then verifies the eligibility requirements from the acquired information and dynamically generates a proposal template based on the verified requirements. Furthermore, the invention utilizes a machine learning model that analyzes past bidding data to predict the optimal bid amount and provides the user with the information necessary to refine their proposal. Finally, it includes a function to submit the refined proposal and related documents online to the public institution's portal. This entire process significantly reduces the time and effort required from application to proposal submission.

[0006] "Means for obtaining public information from public institutions" refers to a function that automatically collects information on bids and proposals published online by public institutions and stores it in a database.

[0007] "Filtering means" refers to a function that narrows down the acquired public information based on conditions set by the business entity and extracts only the relevant information.

[0008] "Means of verifying eligibility requirements" refers to a function that analyzes the conditions included in filtered publicly announced information and determines whether the business entity meets those conditions.

[0009] "Means for generating proposal templates" refers to a function that automatically creates a proposal format based on eligibility requirements and pre-creates some necessary documents.

[0010] "Methods for predicting the optimal bid amount" refers to a function that uses machine learning models to analyze past data and calculate the appropriate bid amount for a specific bidding project.

[0011] "Means of submitting the final version and related documents to the public institution's online portal" refers to the function of electronically sending the completed proposal and necessary documents to the designated public institution's web portal to complete the formal application. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] 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).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system for effectively managing public tender and proposal information from public institutions, enabling organizations to efficiently conduct proposal activities based on this information. This system operates through the interconnectedness of three elements: a server, terminals, and users.

[0034] First, the server periodically accesses the websites of public institutions and automatically retrieves public notices using scraping technology. The retrieved information is stored in a database and filtered according to the conditions set by the institution. At this stage, only the matters of interest to the user are extracted.

[0035] Next, the server checks the eligibility requirements for the filtered information. By analyzing the detailed requirements and comparing them with the registered information of the business entity, it determines whether the case is feasible. This result is fed back to the user in real time, leading to the approach of finding the appropriate case.

[0036] Furthermore, for projects whose eligibility has been confirmed, the server analyzes the specifications and evaluation metrics and automatically generates a draft proposal using natural language processing technology. This allows users to efficiently create the basic documents.

[0037] Furthermore, the server runs a machine learning model based on past bidding data to predict the optimal bid amount. This predicted amount is provided to the user as information that helps in the strategic structuring of the proposal.

[0038] Ultimately, users can review a draft proposal generated by the server on their terminal and make adjustments to suit their company's needs. This finalized proposal is automatically submitted to the local government's online portal via the terminal. After submission, the system sends a confirmation notification to the user, ensuring a smooth proposal process.

[0039] As a concrete example, if a local government announces a tender for cleaning services for a new public facility, the server retrieves that information and determines whether the applicant meets the requirements. If the requirements are met, it then generates an optimal proposal and provides the user with the optimal bid amount based on similar past projects. This entire process allows the user to proceed through the bidding process efficiently.

[0040] This system not only significantly reduces the time and effort required for bidding processes, but also improves the accuracy of decision-making, making it an important tool for businesses to efficiently win more projects.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server periodically accesses public institution websites and uses scraping techniques to collect the latest public notices. This information includes project names, clients, submission deadlines, and requirements. The retrieved information is structured and stored in a database.

[0044] Step 2:

[0045] The server filters the publicly available information in the database based on conditions set in advance by the business entity (e.g., industry, region, amount). This filtering extracts only the cases that match the business entity's interests, and a candidate list is created.

[0046] Step 3:

[0047] Users view a filtered list of potential projects on their device. They can select projects of interest and view the details. Here, they evaluate whether the project's eligibility requirements are suitable for their company.

[0048] Step 4:

[0049] The server analyzes the eligibility requirements for the selected project and compares them with the organization's registration information. Through this process, it automatically determines whether the organization is eligible to participate and notifies the user of the result.

[0050] Step 5:

[0051] The server retrieves specifications and evaluation metrics related to the project and analyzes key items using natural language processing technology. Based on this, it automatically generates a draft proposal and templates. This automatically prepares the basic elements of proposal creation.

[0052] Step 6:

[0053] The server leverages historical bidding data and uses machine learning models to predict the optimal bid amount. This provides users with strategic advice on how much they should propose.

[0054] Step 7:

[0055] Users review the generated proposal and projected bid amount on their device and adjust the content to suit their company's requirements. They then add additional information and make revisions as needed to finalize the proposal.

[0056] Step 8:

[0057] The device automatically uploads the finalized proposal and related documents to the designated public institution's online submission portal. This process also includes granting the necessary authentication credentials. Once the submission is complete, the user will be notified.

[0058] (Example 1)

[0059] 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."

[0060] In traditional bidding and proposal activities, manually acquiring publicly available information and selecting appropriate projects required significant time and effort. Furthermore, creating proposals and estimating optimal bid amounts required specialized knowledge and experience, hindering efficient decision-making. Therefore, there was a need for a system that could automate information acquisition, select optimal projects, efficiently create proposals, and predict optimal bid amounts.

[0061] 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.

[0062] In this invention, the server includes means for acquiring information, means for selecting the acquired information based on conditions, and means for verifying the eligibility requirements for the selected information. This automates the entire process from information collection to selection and verification of eligibility, enabling efficient proposal activities.

[0063] "Means of acquiring information" refers to a function that automatically collects necessary data from specific information sources.

[0064] "Means of sorting based on conditions" refers to a function that filters collected data according to pre-set criteria or conditions.

[0065] "Means of verifying eligibility requirements" refers to a function that determines whether the selected information meets the required eligibility requirements.

[0066] "Means for generating document templates" refers to a function that automatically creates the basic structure of the required document based on confirmed conditions.

[0067] "A means of analyzing past data to predict the optimal amount" refers to a function that analyzes data accumulated in the past to estimate the most effective amount.

[0068] "Means for generating the final version" refers to a function that adjusts automatically generated documents and prepares them for final submission.

[0069] "Method of submitting to the portal" refers to the function of submitting completed documents and related information to an online system.

[0070] "Means of notifying information in real time" refers to functions that instantly transmit the latest information to users.

[0071] "Means for analyzing specifications and evaluation criteria" refers to functions for thoroughly analyzing and understanding the presented specifications and evaluation criteria.

[0072] This invention relates to a system for effectively managing public information of public institutions and for enabling organizations to efficiently carry out proposal activities. This system operates through the coordinated interaction of servers, terminals, and users.

[0073] The server first accesses the websites of public institutions and automatically retrieves public notices using scraping techniques such as Scrapy and BeautifulSoup. The data collected at this stage is stored in a database using MySQL® or PostgreSQL. After storage, the information is filtered based on conditions set by the organization, and only announcements of interest to the user are extracted.

[0074] Next, the server analyzes the filtered information to determine eligibility requirements. This analysis utilizes natural language processing technologies (such as NLTK and spaCy) to compare it with the registered information of the business entity. The results of this comparison are notified to the user in real time. Since WebSocket is used for this communication, users receive the information immediately, making it easier for them to make decisions regarding the project.

[0075] For projects where eligibility has been confirmed, the server uses an AI model to automatically generate a draft proposal. This generation process allows users to quickly create a proposal to use as a basis. An example of a specific prompt is, "Please generate a proposal for cleaning services for a new public facility."

[0076] Furthermore, the server analyzes past bidding data and uses machine learning models such as scikit-learn and TENSORFLOW® to predict the optimal bid amount. This predicted amount is provided to the user as useful information for creating proposals and developing bidding strategies.

[0077] Ultimately, users review the proposal on their devices and make adjustments as needed to suit their specific needs. The completed proposal is automatically submitted to the local government's online portal via the device. After submission, a confirmation notification is sent to the user from the system, allowing for efficient progress in the proposal process.

[0078] This system enables more efficient and accurate bidding and proposal activities than before.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server periodically accesses public institution websites and retrieves public notices using scraping techniques. This information is input to the server as HTML data. A scraping library (such as BeautifulSoup) is used to extract the necessary text and data and convert it into a structured data format. This converted data becomes the input for the next step.

[0082] Step 2:

[0083] The server stores the retrieved public information in a database. Before saving to the database, the data is formatted and error-checked. Here, structured data is stored in the appropriate tables in a relational database such as MySQL or PostgreSQL. The stored data becomes the input data for the next filtering step.

[0084] Step 3:

[0085] The server filters the public announcement information stored in the database. This filtering process executes SQL queries based on user-defined conditions (e.g., region or industry) and extracts only the information that matches those conditions. This extracted information then becomes the input for the next eligibility verification process.

[0086] Step 4:

[0087] The server verifies the eligibility requirements for the filtered information. This process uses natural language processing (NLTK or spaCy, etc.) to analyze the eligibility requirements from the text data. The analysis results are then compared with the user's registration information to determine if they match. The result of this determination becomes the input for the next feedback step.

[0088] Step 5:

[0089] The server notifies the user of the eligibility assessment results in real time. This notification uses WebSocket to send the assessment results to the client, allowing the user to check them immediately. The assessment results serve as input data for the user to decide whether to start generating the next proposal.

[0090] Step 6:

[0091] The server automatically generates a draft proposal for projects it can participate in. Using an AI generation model, it takes a user-specified prompt (e.g., "Generate a proposal for cleaning services at a new public facility") as input. Based on the prompt, the AI ​​outputs the basic structure of the proposal in text format and provides it to the user.

[0092] Step 7:

[0093] The server uses historical bidding data to predict the optimal bid amount. Using data analysis and machine learning algorithms (such as scikit-learn and TensorFlow), it calculates the optimal amount for filtered bids and provides the results to the user. The predicted amount serves as the foundational data for the strategic structure of the proposal.

[0094] Step 8:

[0095] Users review the generated draft proposal and estimated bid amount on their terminal and make adjustments to suit their needs. They edit the text document through a user-friendly interface and finalize the version. This final version serves as the basis for the next submission process.

[0096] Step 9:

[0097] The terminal automatically submits user-configured proposals to the local government's online portal. The submission process uses the HTTP protocol to upload documents along with necessary authentication information. After submission, the system sends a confirmation notice to the user, allowing them to follow up on the progress of the bidding process.

[0098] (Application Example 1)

[0099] 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."

[0100] In public sector bidding and proposal activities, it is difficult to centrally manage information acquisition and processing, eligibility verification, proposal preparation, appropriate pricing, and electronic payments. Therefore, efficient and accurate process management is required. Furthermore, real-time monitoring of progress is also crucial.

[0101] 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.

[0102] In this invention, the server includes means for acquiring information from public institutions, means for filtering the acquired information based on the conditions of economic entities, and means for verifying the participation criteria of the filtered information. This enables efficient and accurate management of the bidding and proposal process, as well as real-time progress monitoring and settlement processing.

[0103] "Information from public institutions" refers to information regarding tenders and requests for proposals released by public organizations such as the government and local authorities.

[0104] An "economic entity" refers to an organization such as a company or group that participates in a specific bid or proposal.

[0105] "Filtering" is the process of classifying acquired information based on pre-set conditions and extracting only the necessary information.

[0106] "Participation criteria" are the requirements that must be met in order to participate in a particular bid or proposal.

[0107] A "document template" is a model used to create the basic format for proposals and related documents.

[0108] "Past competitive bidding data" refers to the results and related information of competitive bidding that has taken place in the past.

[0109] "Optimal economic conditions" refer to the bid amount or price setting that is considered most favorable in business activities.

[0110] An "electronic system" is an information technology infrastructure for processing and managing information online.

[0111] "To pay electronically" means to make a payment using digital technology.

[0112] "Real-time progress notification" means immediately reporting the progress of a particular activity or process.

[0113] To implement this invention, a system is constructed to efficiently manage the bidding and proposal activities of public institutions. The system consists of a server that periodically acquires information from public institutions and filters it based on the conditions of economic entities, a terminal that checks the participation criteria of the filtered information and automatically generates document templates, and software that predicts optimal economic conditions using past competitive bidding data.

[0114] The server periodically accesses public institution websites using CRON jobs and retrieves information using scraping techniques such as Beautiful Soup. This information is stored in a PostgreSQL database on the server and filtered according to user-defined criteria. Subsequently, document templates are generated using natural language processing libraries such as spaCy.

[0115] The terminal provides an interface for users to review and adjust the generated proposal. After editing the proposal, related fees are paid using Stripe's electronic payment function, and progress is notified in real time via Firebase Cloud Messaging.

[0116] For example, if a user becomes interested in a new bidding project, this system automatically retrieves the information and quickly prepares them for participation. The generated proposal is reviewed on the terminal, modified as needed, and then submitted through the electronic system. By using prompts for the generating AI model, such as "Retrieve newly announced bidding information and generate a draft proposal. Also, settle the participation fees related to the project in real time and notify me of the progress," efficient process operation becomes possible.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server periodically accesses public institution websites and scrapes information using Beautiful Soup. The input in this step is the website URL, and the output is the retrieved public information. This information is collected on the server as text data and stored in a database for further processing.

[0120] Step 2:

[0121] The server filters the stored information based on user-defined criteria (e.g., project type, budget range, etc.). The input consists of the text data obtained in step 1 and the user's criteria, while the output is the filtered information. The information is processed by a filtering algorithm, and only the important information is selected.

[0122] Step 3:

[0123] The server verifies the participation criteria for the filtered information. The input for this step is the filtered information, and the output is whether or not the applicant is eligible to participate. Information analysis determines whether the necessary criteria are met and checks for any deficiencies.

[0124] Step 4:

[0125] The server uses spaCy to generate a document template based on information that meets the participation criteria. The input is the verified participation criteria information, and the output is a templated proposal. The document is constructed using natural language processing, and an automatically generated template is created.

[0126] Step 5:

[0127] The terminal presents the user with a generated document template, allowing for editing and adjustment. The input is a templated proposal, and the output is the final version of the proposal modified by the user. The user then uses the template as a base to add specific details and improve its completeness.

[0128] Step 6:

[0129] The terminal will process the electronic payment of the participation fee via Stripe. The input will be the final proposal and information on related costs, and the output will be a confirmation of payment completion. After confirming that the payment process was completed securely, proceed to the next step.

[0130] Step 7:

[0131] The terminal submits the final proposal and related documents to the public institution's electronic system. The input is the approved final proposal, and the output is a submission completion notification. The system confirms that the submission has been successfully completed.

[0132] Step 8:

[0133] The server uses Firebase Cloud Messaging to notify the user of the progress in real time. The input is information indicating that submission is complete, and the output is a notification message. The user is immediately informed of the process's progress and can clearly understand when to take the next action.

[0134] 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.

[0135] This invention combines a system that efficiently manages bidding information disseminated by public institutions and supports optimal proposal activities with an emotion engine that recognizes and adapts to user emotions. This system utilizes the collaboration of three elements—server, terminal, and user—to provide multi-functional capabilities.

[0136] First, the server automatically collects public notices from public institution websites using scraping technology. This information includes project details, conditions, and deadlines, and is stored and managed in a database. This information is then filtered to match the user's business entity, and the most relevant information is organized.

[0137] Next, using an emotion engine, the server analyzes the user's emotional state based on user input and operation data. It can determine the user's stress level, excitement, and concentration level, and dynamically adjust the style and content of the proposal template according to their emotions.

[0138] The process continues with users evaluating whether the eligibility requirements for filtered projects are applicable to their company. For approved projects, the server analyzes the specifications and evaluation criteria using natural language processing to quickly generate a draft proposal. During this process, the server uses the results of analyzing past bidding data to recommend the optimal bid amount based on a machine learning model.

[0139] The generated proposals are automatically enhanced with improvement suggestions tailored to the user's psychological state, thanks to an emotion engine that performs real-time emotion recognition. If the user is experiencing stress, a more user-friendly and easy-to-implement template is presented.

[0140] Ultimately, users use their devices to review and refine the proposal content, finalizing the version. The necessary documents are then automatically submitted to the online portal via the device. Even after submitting the proposal, users are continuously supported in making practical improvements for future proposals based on feedback received through the emotion engine.

[0141] As a concrete example, in a bidding process for a new project undertaken by a certain company, the emotional engine provides a more reassuring template based on the pressure a user feels while creating a proposal. This adjustment allows users to prepare bid documents containing sufficient proposal content while minimizing stress.

[0142] This invention aims to facilitate effective bidding processes and improve the success rate of securing eligible projects by realizing a highly adaptable system that takes into account the emotional state of the user.

[0143] The following describes the processing flow.

[0144] Step 1:

[0145] The server accesses designated websites and scrapes the necessary data to collect public sector bidding and proposal information. This information includes project names, target regions, project details, and submission deadlines. The collected data is organized and stored in a database.

[0146] Step 2:

[0147] The server applies conditional filters set by the business entity to the public notice information stored in the database and automatically selects the most relevant cases. These conditions include industry, region, budget range, etc., and the filtering results are notified to the user's terminal.

[0148] Step 3:

[0149] The user reviews a filtered list of cases on their device and selects a case. Based on the selected case, the eligibility requirements are checked, and the emotion engine initiates interaction to reduce the user's psychological burden.

[0150] Step 4:

[0151] The server analyzes the eligibility requirements associated with the selected project and matches them against the user's company information. It verifies whether the eligibility is met and communicates the results to the user in real time.

[0152] Step 5:

[0153] The server analyzes project-related specifications and evaluation metrics using natural language processing technology to automatically generate a draft proposal. It also identifies the user's emotional state using an emotion engine, adjusts the template as needed, and creates a more effective proposal.

[0154] Step 6:

[0155] The server uses a machine learning model that analyzes historical bidding data to predict the optimal bid amount for selected projects. The predicted amount is explicitly presented so that users can strategically incorporate it into their proposals.

[0156] Step 7:

[0157] Users review the proposal template and recommended bid amount provided on their device, and then incorporate any necessary modifications or additional information into their proposal based on their company's strategy and policies. Throughout this process, the sentiment engine continuously monitors the user's emotions and provides advice and fine-tunes the template as needed.

[0158] Step 8:

[0159] The terminal automatically submits the user's finalized proposal and related documents to the designated public institution's online portal. This submission process ensures all required authentication information is properly granted and the submission is officially registered as a new application. Simultaneously, the user receives a notification of submission completion and is provided with feedback for future proposals.

[0160] (Example 2)

[0161] 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".

[0162] Public institutions disseminate a wide variety of bidding information, making it difficult for companies to efficiently manage and appropriately submit proposals. Furthermore, the emotional state of users during the proposal process can influence the quality of proposals, but traditional systems do not take this into account. As a result, proposals are not optimized, leading to a lower success rate in bidding.

[0163] 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.

[0164] In this invention, the server includes means for acquiring public notices from public institutions, means for filtering the acquired public notices based on the conditions of the business entity, and sentiment analysis means for recognizing the user's emotional state and dynamically adjusting the content of the proposal document. This enables companies to efficiently acquire highly relevant bidding information, optimize proposals according to the user's emotions, and improve the success rate of bids.

[0165] "Public institutions" refer to organizations and agencies that operate for the public good, such as the government and local authorities.

[0166] "Public notice information" refers to information issued by public institutions, such as announcements, bidding information, and details including conditions and deadlines.

[0167] A "business entity" refers to a corporation or organization that conducts specific business or operations.

[0168] "Filtering" refers to the process of selecting and narrowing down data or information based on certain criteria or conditions.

[0169] "Emotional analysis methods" refer to technologies and methods for evaluating and recognizing a user's emotions and mental state.

[0170] A "proposal" is a document submitted when participating in a bidding process, and it refers to a document that describes in detail the proposal or plan for the project.

[0171] "Machine learning methods" refer to algorithms and techniques that enable computers to learn from data and make predictions and decisions on their own.

[0172] An "electronic portal" refers to an online platform that provides information and services via the internet.

[0173] This invention is a system for effectively managing bidding information disseminated by public institutions and supporting optimal proposal activities. This system primarily operates through the interaction of servers, terminals, and users.

[0174] The server utilizes web scraping techniques to collect public information from public institution websites. Specifically, it uses libraries such as Python's Beautiful Soup and Scrapy to parse the HTML of web pages and automatically extract data such as project details, conditions, and deadlines. This information is stored and managed in a database.

[0175] The server then uses SQL queries to narrow down the information in the database based on the filter conditions set by the user. This makes it possible to efficiently present bidding information that is highly relevant to the user.

[0176] The server is equipped with emotion analysis capabilities to identify emotions from user interaction data. For example, it uses machine learning models and natural language processing to determine the user's stress level and concentration level based on mouse movements, keyboard input speed, and user facial expression data. This analysis allows proposal templates and content to be dynamically adjusted to match the user's psychological state.

[0177] Users check whether their company's eligibility requirements are met for the filtered projects. For projects that meet the requirements, the server uses an AI model to analyze past bidding data and predict the optimal bid amount. During this process, a draft proposal is automatically generated.

[0178] The terminal sends the final version of the proposal, as confirmed by the user, to the online portal. Data transmission is performed securely and efficiently using an API.

[0179] For example, when a company is creating a proposal for a new project, if they feel tension or pressure, the server's emotion analysis system will detect this. The system then provides a more user-friendly and concise proposal template, helping the user reduce stress and work more efficiently.

[0180] As an example of a prompt, we will use the following sentence: "Please provide a template for creating a project proposal. We require a design that takes into account the user's current emotional state and prioritizes a sense of security and ease of use."

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The server automatically collects public notices from government websites using scraping techniques. Specifically, it uses Python's Beautiful Soup or Scrapy libraries to parse the HTML of web pages. The input is the website URL, and the output is data such as project details, conditions, and deadlines. This data is stored in a database for use in the next step.

[0184] Step 2:

[0185] The server filters the publicly available information stored in the database based on the user's business entity criteria. The input requires the user's set filter conditions, and the server uses SQL queries to search the data, narrowing down the information to only what is highly relevant to the user. The output generates a list of related case information.

[0186] Step 3:

[0187] The server uses emotion analysis tools to analyze the user's emotional state. Specifically, it receives user operation data (e.g., keyboard input speed, mouse movements, facial expression data) as input and analyzes it using machine learning models and natural language processing. The output is a determination of the user's stress level and concentration level, and based on this, it generates information to adjust the proposal template.

[0188] Step 4:

[0189] The server dynamically generates proposal templates based on the results of sentiment analysis. In this process, it selects a template appropriate to the user's psychological state and adjusts the template's content. The sentiment assessment results are used as input, and a proposal template optimized for the user is generated as output.

[0190] Step 5:

[0191] Users review filtered project information and determine if their company's eligibility requirements are met. Specifically, they compare the project information with their company's requirements, using the filtered project information as input. A list of suitable projects is generated as output.

[0192] Step 6:

[0193] The server uses a generative AI model to predict the optimal bid amount for suitable projects based on past bidding data. This process uses past bidding data as input and applies machine learning algorithms to generate a recommended bid price to be included in the proposal.

[0194] Step 7:

[0195] The user uses a terminal to review and adjust the proposal content and finalize the version. Specifically, the user enters additional information into a template and modifies the content as needed. The output is a final version of the proposal ready for submission.

[0196] Step 8:

[0197] The terminal sends the final version of the proposal and related documents to an online portal. An API is used for secure and efficient data transmission. The final version of the proposal is required as input, and upon successful submission, confirmation is provided that the proposal has been submitted to the public institution's system.

[0198] (Application Example 2)

[0199] 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".

[0200] In bidding processes, it is crucial to efficiently manage information disseminated by public institutions and quickly create optimal proposals. However, manually reviewing and analyzing a large amount of project information and participation requirements is time-consuming and labor-intensive, and the stress and pressure experienced by users can negatively impact the quality of proposals. There is a need to address these challenges and support efficient and effective bidding processes.

[0201] 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.

[0202] In this invention, the server includes a device for acquiring information from public institutions, a device for filtering the acquired information based on unit conditions, and a device for verifying the participation requirements of the filtered information. This makes it possible to efficiently generate and submit bid proposals while reducing user stress and appropriately adjusting document templates according to the user's emotional state.

[0203] "Public institutions" refer to organizations that perform public duties, such as the government and local authorities.

[0204] "Information" refers to public announcements and data related to bidding issued by public institutions.

[0205] The term "device" refers to equipment or a system with a specific function, designed to perform that function.

[0206] "Unit conditions" refer to the standards or requirements that a particular business or entity must meet.

[0207] "Filtering" refers to the process of removing unnecessary information in order to extract useful information.

[0208] "Participation requirements" refer to the standards or qualifications that must be met in order to participate in the bidding process.

[0209] "Verification" refers to the process of checking whether information or conditions are accurate and valid.

[0210] A "document template" refers to a basic format used when creating documents such as proposals and contracts.

[0211] "Emotional state" refers to the user's psychological state or emotional tendencies.

[0212] "Stress" refers to feelings of tension and anxiety that users experience, particularly in the course of performing their work.

[0213] "Adjustment" refers to the process of making appropriate changes or modifications according to the purpose.

[0214] A "proposal" refers to a document that summarizes the details of a proposal related to bidding or contracting.

[0215] A "template" refers to a pre-prepared model for creating documents or data.

[0216] "Submission" refers to the process of sending necessary documents or information to a designated location or system.

[0217] This invention is a system for supporting bidding processes in the construction industry, enabling efficient management of information disseminated by public institutions and the creation of optimal proposals. The system consists of three elements: a server, terminals, and users.

[0218] The server is responsible for automatically collecting bidding information from public institution websites using scraping technology. Technologies used include, for example, Beautiful Soup and Scrapy. The collected information is stored in a database and filtered based on specified criteria.

[0219] When users access the system via their devices, the system verifies participation requirements from filtered information and uses an emotion engine to evaluate the user's psychological state in real time. This evaluation utilizes emotion analysis libraries such as TensorFlow and PyTorch. If a user is experiencing stress, the system provides a reassuring template.

[0220] Furthermore, natural language processing tools such as spaCy and NLTK are used to generate and refine proposals. The server uses machine learning models based on historical data to predict the optimal bid amount. This model learns from past bidding results and provides practical recommendations for future proposals.

[0221] For example, when a user is bidding on a new building construction project, the emotion engine presents a relaxing proposal template to alleviate the time pressure associated with writing a proposal.

[0222] An example of a generated AI model prompt statement is as follows:

[0223] "To help users create proposals for construction bidding projects, we will provide templates and advice that reduce stress and aid in development. Utilize an emotion recognition engine to present a more reassuring style when users are feeling pressured."

[0224] In this way, users can efficiently perform their tasks while smoothly creating optimal proposals.

[0225] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0226] Step 1:

[0227] The server automatically retrieves information from public institution websites using scraping techniques. The input information consists of various tender announcement data, which is then stored in a database in a structured format. Tools such as Beautiful Soup and Scrapy are used to parse HTML and extract data.

[0228] Step 2:

[0229] The server filters information in the database based on user-defined criteria. The input is stored public notice information, and filter conditions are applied to narrow it down to projects related to a specific business. The output is a filtered list of bid projects. SQL queries are used for filtering.

[0230] Step 3:

[0231] The user reviews the filtered information via their device and assesses the participation requirements. The input is a list of filtered cases, and the output is a list of cases that the user can participate in. During the review process, the user determines whether they meet the participation requirements.

[0232] Step 4:

[0233] The server generates proposal templates based on available projects. This process uses natural language processing tools to analyze project characteristics as input and generate proposal templates as output. SpaCy and NLTK are used for the analysis.

[0234] Step 5:

[0235] The server analyzes historical bidding data and uses a machine learning model to predict the optimal bid amount. The input is historical data from a database, and the output is the recommended bid amount. A pre-trained model is used for the prediction.

[0236] Step 6:

[0237] The user reviews the proposal on their device and makes revisions and adjustments as needed. The input is the generated proposal and estimated price, and the output is the final proposal. User intervention optimizes the proposal's content.

[0238] Step 7:

[0239] The emotion engine analyzes the emotional state of users during proposal revision and adjusts templates in real time. Inputs are user operation logs and input data, and the output is the adapted template. TensorFlow and PyTorch are used for emotion analysis.

[0240] Step 8:

[0241] The server automatically submits the completed final version of the proposal and related documents to the public institution's online portal. The input is the final proposal data, and the output is the successful uploading of the proposal online. An automated process via API is used for submission.

[0242] 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.

[0243] 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.

[0244] 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.

[0245] [Second Embodiment]

[0246] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0247] 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.

[0248] 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).

[0249] 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.

[0250] 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.

[0251] 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).

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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".

[0258] This invention is a system for effectively managing public tender and proposal information from public institutions, enabling organizations to efficiently conduct proposal activities based on this information. This system operates through the interconnectedness of three elements: a server, terminals, and users.

[0259] First, the server periodically accesses the websites of public institutions and automatically retrieves public notices using scraping technology. The retrieved information is stored in a database and filtered according to the conditions set by the institution. At this stage, only the matters of interest to the user are extracted.

[0260] Next, the server checks the eligibility requirements for the filtered information. By analyzing the detailed requirements and comparing them with the registered information of the business entity, it determines whether the case is feasible. This result is fed back to the user in real time, leading to the approach of finding the appropriate case.

[0261] Furthermore, for projects whose eligibility has been confirmed, the server analyzes the specifications and evaluation metrics and automatically generates a draft proposal using natural language processing technology. This allows users to efficiently create the basic documents.

[0262] Furthermore, the server runs a machine learning model based on past bidding data to predict the optimal bid amount. This predicted amount is provided to the user as information that helps in the strategic structuring of the proposal.

[0263] Ultimately, users can review a draft proposal generated by the server on their terminal and make adjustments to suit their company's needs. This finalized proposal is automatically submitted to the local government's online portal via the terminal. After submission, the system sends a confirmation notification to the user, ensuring a smooth proposal process.

[0264] As a concrete example, if a local government announces a tender for cleaning services for a new public facility, the server retrieves that information and determines whether the applicant meets the requirements. If the requirements are met, it then generates an optimal proposal and provides the user with the optimal bid amount based on similar past projects. This entire process allows the user to proceed through the bidding process efficiently.

[0265] This system not only significantly reduces the time and effort required for bidding processes, but also improves the accuracy of decision-making, making it an important tool for businesses to efficiently win more projects.

[0266] The following describes the processing flow.

[0267] Step 1:

[0268] The server periodically accesses public institution websites and uses scraping techniques to collect the latest public notices. This information includes project names, clients, submission deadlines, and requirements. The retrieved information is structured and stored in a database.

[0269] Step 2:

[0270] The server filters the publicly available information in the database based on conditions set in advance by the business entity (e.g., industry, region, amount). This filtering extracts only the cases that match the business entity's interests, and a candidate list is created.

[0271] Step 3:

[0272] Users view a filtered list of potential projects on their device. They can select projects of interest and view the details. Here, they evaluate whether the project's eligibility requirements are suitable for their company.

[0273] Step 4:

[0274] The server analyzes the eligibility requirements for the selected project and compares them with the organization's registration information. Through this process, it automatically determines whether the organization is eligible to participate and notifies the user of the result.

[0275] Step 5:

[0276] The server retrieves specifications and evaluation metrics related to the project and analyzes key items using natural language processing technology. Based on this, it automatically generates a draft proposal and templates. This automatically prepares the basic elements of proposal creation.

[0277] Step 6:

[0278] The server utilizes past bidding data and uses a machine learning model to predict the optimal bidding amount. As a result, strategic advice on the amount to be proposed is provided to the user.

[0279] Step 7:

[0280] The user checks the generated proposal and the predicted bidding amount on the terminal and adjusts the content according to the company's requirements. If necessary, additional information or modifications are made to complete the final proposal.

[0281] Step 8:

[0282] The terminal automatically uploads the final adjusted proposal and related documents to the online submission portal of the designated public institution. This process also includes the granting of necessary authentication information. When the submission is complete, the user is notified of this.

[0283] (Example 1)

[0284] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In conventional bidding and proposal activities, the work of manually acquiring publicly available information and screening appropriate projects required a significant amount of time and effort. Also, the creation of proposals and the estimation of the optimal bidding amount required specialized knowledge and experience, which made efficient decision-making difficult. Therefore, there has been a demand for a system that enables automatic acquisition of information, screening of optimal projects, efficient creation of proposals, and prediction of the optimal bidding amount.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0287] In this invention, the server includes means for acquiring information, means for selecting the acquired information based on conditions, and means for verifying the eligibility requirements for the selected information. This automates the entire process from information collection to selection and verification of eligibility, enabling efficient proposal activities.

[0288] "Means of acquiring information" refers to a function that automatically collects necessary data from specific information sources.

[0289] "Means of sorting based on conditions" refers to a function that filters collected data according to pre-set criteria or conditions.

[0290] "Means of verifying eligibility requirements" refers to a function that determines whether the selected information meets the required eligibility requirements.

[0291] "Means for generating document templates" refers to a function that automatically creates the basic structure of the required document based on confirmed conditions.

[0292] "A means of analyzing past data to predict the optimal amount" refers to a function that analyzes data accumulated in the past to estimate the most effective amount.

[0293] "Means for generating the final version" refers to a function that adjusts automatically generated documents and prepares them for final submission.

[0294] "Method of submitting to the portal" refers to the function of submitting completed documents and related information to an online system.

[0295] "Means of notifying information in real time" refers to functions that instantly transmit the latest information to users.

[0296] "Means for analyzing specifications and evaluation criteria" refers to functions for thoroughly analyzing and understanding the presented specifications and evaluation criteria.

[0297] This invention relates to a system for effectively managing public information of public institutions and for enabling organizations to efficiently carry out proposal activities. This system operates through the coordinated interaction of servers, terminals, and users.

[0298] The server first accesses the websites of public institutions and automatically retrieves public notices using scraping techniques such as Scrapy and BeautifulSoup. The data collected at this stage is stored in a database using MySQL or PostgreSQL. After storage, the information is filtered based on conditions set by the institution, and only announcements of interest to the user are extracted.

[0299] Next, the server analyzes the filtered information to determine eligibility requirements. This analysis utilizes natural language processing technologies (such as NLTK and spaCy) to compare it with the registered information of the business entity. The results of this comparison are notified to the user in real time. Since WebSocket is used for this communication, users receive the information immediately, making it easier for them to make decisions regarding the project.

[0300] For projects where eligibility has been confirmed, the server uses an AI model to automatically generate a draft proposal. This generation process allows users to quickly create a proposal to use as a basis. An example of a specific prompt is, "Please generate a proposal for cleaning services for a new public facility."

[0301] The server also analyzes past bidding data and uses machine learning models such as scikit-learn and TensorFlow to predict the optimal bid amount. This predicted amount is provided to the user as useful information for creating proposals and developing bidding strategies.

[0302] Finally, the user checks the proposal on the terminal and makes adjustments according to the company's needs if necessary. The completed proposal is automatically submitted to the local government's online portal via the terminal. After submission, a confirmation notice from the system is sent to the user, enabling the proposal activities to proceed efficiently.

[0303] The operation of this system enables more efficient and accurate bidding and proposal activities than before.

[0304] The flow of the specific process in Example 1 will be described using FIG. 11.

[0305] Step 1:

[0306] The server regularly accesses the website of the public institution and uses scraping technology to obtain the public information. This information is input into the server as HTML-formatted data. A scraping library (such as BeautifulSoup) is used to extract the necessary text and data and convert them into a structured data format. This converted data serves as the input for the next step.

[0307] Step 2:

[0308] The server saves the obtained public information in the database. Before saving in the database, the data format and error checking are performed. Here, the structured data is stored in the appropriate tables of a relational database such as MySQL or PostgreSQL. The saved data serves as the input data for the next filtering step.

[0309] Step 3:

[0310] The server filters the public information stored in the database. In this filtering process, based on the conditions set by the user (such as region or industry), an SQL query is executed to extract only the information that meets the conditions. This extracted information serves as the input for the next participation eligibility confirmation process.

[0311] Step 4:

[0312] The server verifies the eligibility requirements for the filtered information. This process uses natural language processing (NLTK or spaCy, etc.) to analyze the eligibility requirements from the text data. The analysis results are then compared with the user's registration information to determine if they match. The result of this determination becomes the input for the next feedback step.

[0313] Step 5:

[0314] The server notifies the user of the eligibility assessment results in real time. This notification uses WebSocket to send the assessment results to the client, allowing the user to check them immediately. The assessment results serve as input data for the user to decide whether to start generating the next proposal.

[0315] Step 6:

[0316] The server automatically generates a draft proposal for projects it can participate in. Using an AI generation model, it takes a user-specified prompt (e.g., "Generate a proposal for cleaning services at a new public facility") as input. Based on the prompt, the AI ​​outputs the basic structure of the proposal in text format and provides it to the user.

[0317] Step 7:

[0318] The server uses historical bidding data to predict the optimal bid amount. Using data analysis and machine learning algorithms (such as scikit-learn and TensorFlow), it calculates the optimal amount for filtered bids and provides the results to the user. The predicted amount serves as the foundational data for the strategic structure of the proposal.

[0319] Step 8:

[0320] Users review the generated draft proposal and estimated bid amount on their terminal and make adjustments to suit their needs. They edit the text document through a user-friendly interface and finalize the version. This final version serves as the basis for the next submission process.

[0321] Step 9:

[0322] The terminal automatically submits user-configured proposals to the local government's online portal. The submission process uses the HTTP protocol to upload documents along with necessary authentication information. After submission, the system sends a confirmation notice to the user, allowing them to follow up on the progress of the bidding process.

[0323] (Application Example 1)

[0324] 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."

[0325] In public sector bidding and proposal activities, it is difficult to centrally manage information acquisition and processing, eligibility verification, proposal preparation, appropriate pricing, and electronic payments. Therefore, efficient and accurate process management is required. Furthermore, real-time monitoring of progress is also crucial.

[0326] 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.

[0327] In this invention, the server includes means for acquiring information from public institutions, means for filtering the acquired information based on the conditions of economic entities, and means for verifying the participation criteria of the filtered information. This enables efficient and accurate management of the bidding and proposal process, as well as real-time progress monitoring and settlement processing.

[0328] "Information from public institutions" refers to information regarding tenders and requests for proposals released by public organizations such as the government and local authorities.

[0329] An "economic entity" refers to an organization such as a company or group that participates in a specific bid or proposal.

[0330] "Filtering" is the process of classifying acquired information based on pre-set conditions and extracting only the necessary information.

[0331] "Participation criteria" are the requirements that must be met in order to participate in a particular bid or proposal.

[0332] A "document template" is a model used to create the basic format for proposals and related documents.

[0333] "Past competitive bidding data" refers to the results and related information of competitive bidding that has taken place in the past.

[0334] "Optimal economic conditions" refer to the bid amount or price setting that is considered most favorable in business activities.

[0335] An "electronic system" is an information technology infrastructure for processing and managing information online.

[0336] "To pay electronically" means to make a payment using digital technology.

[0337] "Real-time progress notification" means immediately reporting the progress of a particular activity or process.

[0338] To implement this invention, a system is constructed to efficiently manage the bidding and proposal activities of public institutions. The system consists of a server that periodically acquires information from public institutions and filters it based on the conditions of economic entities, a terminal that checks the participation criteria of the filtered information and automatically generates document templates, and software that predicts optimal economic conditions using past competitive bidding data.

[0339] The server periodically accesses public institution websites using CRON jobs and retrieves information using scraping techniques such as Beautiful Soup. This information is stored in a PostgreSQL database on the server and filtered according to user-defined criteria. Subsequently, document templates are generated using natural language processing libraries such as spaCy.

[0340] The terminal provides an interface for users to review and adjust the generated proposal. After editing the proposal, related fees are paid using Stripe's electronic payment function, and progress is notified in real time via Firebase Cloud Messaging.

[0341] For example, if a user becomes interested in a new bidding project, this system automatically retrieves the information and quickly prepares them for participation. The generated proposal is reviewed on the terminal, modified as needed, and then submitted through the electronic system. By using prompts for the generating AI model, such as "Retrieve newly announced bidding information and generate a draft proposal. Also, settle the participation fees related to the project in real time and notify me of the progress," efficient process operation becomes possible.

[0342] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0343] Step 1:

[0344] The server periodically accesses public institution websites and scrapes information using Beautiful Soup. The input in this step is the website URL, and the output is the retrieved public information. This information is collected on the server as text data and stored in a database for further processing.

[0345] Step 2:

[0346] The server filters the stored information based on user-defined criteria (e.g., project type, budget range, etc.). The input consists of the text data obtained in step 1 and the user's criteria, while the output is the filtered information. The information is processed by a filtering algorithm, and only the important information is selected.

[0347] Step 3:

[0348] The server verifies the participation criteria for the filtered information. The input for this step is the filtered information, and the output is whether or not the applicant is eligible to participate. Information analysis determines whether the necessary criteria are met and checks for any deficiencies.

[0349] Step 4:

[0350] The server uses spaCy to generate a document template based on information that meets the participation criteria. The input is the verified participation criteria information, and the output is a templated proposal. The document is constructed using natural language processing, and an automatically generated template is created.

[0351] Step 5:

[0352] The terminal presents the user with a generated document template, allowing for editing and adjustment. The input is a templated proposal, and the output is the final version of the proposal modified by the user. The user then uses the template as a base to add specific details and improve its completeness.

[0353] Step 6:

[0354] The terminal will process the electronic payment of the participation fee via Stripe. The input will be the final proposal and information on related costs, and the output will be a confirmation of payment completion. After confirming that the payment process was completed securely, proceed to the next step.

[0355] Step 7:

[0356] The terminal submits the final proposal and related documents to the public institution's electronic system. The input is the approved final proposal, and the output is a submission completion notification. The system confirms that the submission has been successfully completed.

[0357] Step 8:

[0358] The server uses Firebase Cloud Messaging to notify the user of the progress in real time. The input is information indicating that submission is complete, and the output is a notification message. The user is immediately informed of the process's progress and can clearly understand when to take the next action.

[0359] 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.

[0360] This invention combines a system that efficiently manages bidding information disseminated by public institutions and supports optimal proposal activities with an emotion engine that recognizes and adapts to user emotions. This system utilizes the collaboration of three elements—server, terminal, and user—to provide multi-functional capabilities.

[0361] First, the server automatically collects public notices from public institution websites using scraping technology. This information includes project details, conditions, and deadlines, and is stored and managed in a database. This information is then filtered to match the user's business entity, and the most relevant information is organized.

[0362] Next, using an emotion engine, the server analyzes the user's emotional state based on user input and operation data. It can determine the user's stress level, excitement, and concentration level, and dynamically adjust the style and content of the proposal template according to their emotions.

[0363] The process continues with users evaluating whether the eligibility requirements for filtered projects are applicable to their company. For approved projects, the server analyzes the specifications and evaluation criteria using natural language processing to quickly generate a draft proposal. During this process, the server uses the results of analyzing past bidding data to recommend the optimal bid amount based on a machine learning model.

[0364] The generated proposals are automatically enhanced with improvement suggestions tailored to the user's psychological state, thanks to an emotion engine that performs real-time emotion recognition. If the user is experiencing stress, a more user-friendly and easy-to-implement template is presented.

[0365] Ultimately, users use their devices to review and refine the proposal content, finalizing the version. The necessary documents are then automatically submitted to the online portal via the device. Even after submitting the proposal, users are continuously supported in making practical improvements for future proposals based on feedback received through the emotion engine.

[0366] As a concrete example, in a bidding process for a new project undertaken by a certain company, the emotional engine provides a more reassuring template based on the pressure a user feels while creating a proposal. This adjustment allows users to prepare bid documents containing sufficient proposal content while minimizing stress.

[0367] This invention aims to facilitate effective bidding processes and improve the success rate of securing eligible projects by realizing a highly adaptable system that takes into account the emotional state of the user.

[0368] The following describes the processing flow.

[0369] Step 1:

[0370] The server accesses designated websites and scrapes the necessary data to collect public sector bidding and proposal information. This information includes project names, target regions, project details, and submission deadlines. The collected data is organized and stored in a database.

[0371] Step 2:

[0372] The server applies conditional filters set by the business entity to the public notice information stored in the database and automatically selects the most relevant cases. These conditions include industry, region, budget range, etc., and the filtering results are notified to the user's terminal.

[0373] Step 3:

[0374] The user reviews a filtered list of cases on their device and selects a case. Based on the selected case, the eligibility requirements are checked, and the emotion engine initiates interaction to reduce the user's psychological burden.

[0375] Step 4:

[0376] The server analyzes the eligibility requirements associated with the selected project and matches them against the user's company information. It verifies whether the eligibility is met and communicates the results to the user in real time.

[0377] Step 5:

[0378] The server analyzes project-related specifications and evaluation metrics using natural language processing technology to automatically generate a draft proposal. It also identifies the user's emotional state using an emotion engine, adjusts the template as needed, and creates a more effective proposal.

[0379] Step 6:

[0380] The server uses a machine learning model that analyzes historical bidding data to predict the optimal bid amount for selected projects. The predicted amount is explicitly presented so that users can strategically incorporate it into their proposals.

[0381] Step 7:

[0382] Users review the proposal template and recommended bid amount provided on their device, and then incorporate any necessary modifications or additional information into their proposal based on their company's strategy and policies. Throughout this process, the sentiment engine continuously monitors the user's emotions and provides advice and fine-tunes the template as needed.

[0383] Step 8:

[0384] The terminal automatically submits the user's finalized proposal and related documents to the designated public institution's online portal. This submission process ensures all required authentication information is properly granted and the submission is officially registered as a new application. Simultaneously, the user receives a notification of submission completion and is provided with feedback for future proposals.

[0385] (Example 2)

[0386] 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".

[0387] Public institutions disseminate a wide variety of bidding information, making it difficult for companies to efficiently manage and appropriately submit proposals. Furthermore, the emotional state of users during the proposal process can influence the quality of proposals, but traditional systems do not take this into account. As a result, proposals are not optimized, leading to a lower success rate in bidding.

[0388] 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.

[0389] In this invention, the server includes means for acquiring public notices from public institutions, means for filtering the acquired public notices based on the conditions of the business entity, and sentiment analysis means for recognizing the user's emotional state and dynamically adjusting the content of the proposal document. This enables companies to efficiently acquire highly relevant bidding information, optimize proposals according to the user's emotions, and improve the success rate of bids.

[0390] "Public institutions" refer to organizations and agencies that operate for the public good, such as the government and local authorities.

[0391] "Public notice information" refers to information issued by public institutions, such as announcements, bidding information, and details including conditions and deadlines.

[0392] A "business entity" refers to a corporation or organization that conducts specific business or operations.

[0393] "Filtering" refers to the process of selecting and narrowing down data or information based on certain criteria or conditions.

[0394] "Emotional analysis methods" refer to technologies and methods for evaluating and recognizing a user's emotions and mental state.

[0395] A "proposal" is a document submitted when participating in a bidding process, and it refers to a document that describes in detail the proposal or plan for the project.

[0396] "Machine learning methods" refer to algorithms and techniques that enable computers to learn from data and make predictions and decisions on their own.

[0397] An "electronic portal" refers to an online platform that provides information and services via the internet.

[0398] This invention is a system for effectively managing bidding information disseminated by public institutions and supporting optimal proposal activities. This system primarily operates through the interaction of servers, terminals, and users.

[0399] The server utilizes web scraping techniques to collect public information from public institution websites. Specifically, it uses libraries such as Python's Beautiful Soup and Scrapy to parse the HTML of web pages and automatically extract data such as project details, conditions, and deadlines. This information is stored and managed in a database.

[0400] The server then uses SQL queries to narrow down the information in the database based on the filter conditions set by the user. This makes it possible to efficiently present bidding information that is highly relevant to the user.

[0401] The server is equipped with emotion analysis capabilities to identify emotions from user interaction data. For example, it uses machine learning models and natural language processing to determine the user's stress level and concentration level based on mouse movements, keyboard input speed, and user facial expression data. This analysis allows proposal templates and content to be dynamically adjusted to match the user's psychological state.

[0402] Users check whether their company's eligibility requirements are met for the filtered projects. For projects that meet the requirements, the server uses an AI model to analyze past bidding data and predict the optimal bid amount. During this process, a draft proposal is automatically generated.

[0403] The terminal sends the final version of the proposal, as confirmed by the user, to the online portal. Data transmission is performed securely and efficiently using an API.

[0404] For example, when a company is creating a proposal for a new project, if they feel tension or pressure, the server's emotion analysis system will detect this. The system then provides a more user-friendly and concise proposal template, helping the user reduce stress and work more efficiently.

[0405] As an example of a prompt, we will use the following sentence: "Please provide a template for creating a project proposal. We require a design that takes into account the user's current emotional state and prioritizes a sense of security and ease of use."

[0406] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0407] Step 1:

[0408] The server automatically collects public notices from government websites using scraping techniques. Specifically, it uses Python's Beautiful Soup or Scrapy libraries to parse the HTML of web pages. The input is the website URL, and the output is data such as project details, conditions, and deadlines. This data is stored in a database for use in the next step.

[0409] Step 2:

[0410] The server filters the publicly available information stored in the database based on the user's business entity criteria. The input requires the user's set filter conditions, and the server uses SQL queries to search the data, narrowing down the information to only what is highly relevant to the user. The output generates a list of related case information.

[0411] Step 3:

[0412] The server uses emotion analysis tools to analyze the user's emotional state. Specifically, it receives user operation data (e.g., keyboard input speed, mouse movements, facial expression data) as input and analyzes it using machine learning models and natural language processing. The output is a determination of the user's stress level and concentration level, and based on this, it generates information to adjust the proposal template.

[0413] Step 4:

[0414] The server dynamically generates proposal templates based on the results of sentiment analysis. In this process, it selects a template appropriate to the user's psychological state and adjusts the template's content. The sentiment assessment results are used as input, and a proposal template optimized for the user is generated as output.

[0415] Step 5:

[0416] Users review filtered project information and determine if their company's eligibility requirements are met. Specifically, they compare the project information with their company's requirements, using the filtered project information as input. A list of suitable projects is generated as output.

[0417] Step 6:

[0418] The server uses a generative AI model to predict the optimal bid amount for suitable projects based on past bidding data. This process uses past bidding data as input and applies machine learning algorithms to generate a recommended bid price to be included in the proposal.

[0419] Step 7:

[0420] The user uses a terminal to review and adjust the proposal content and finalize the version. Specifically, the user enters additional information into a template and modifies the content as needed. The output is a final version of the proposal ready for submission.

[0421] Step 8:

[0422] The terminal sends the final version of the proposal and related documents to an online portal. An API is used for secure and efficient data transmission. The final version of the proposal is required as input, and upon successful submission, confirmation is provided that the proposal has been submitted to the public institution's system.

[0423] (Application Example 2)

[0424] 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."

[0425] In bidding processes, it is crucial to efficiently manage information disseminated by public institutions and quickly create optimal proposals. However, manually reviewing and analyzing a large amount of project information and participation requirements is time-consuming and labor-intensive, and the stress and pressure experienced by users can negatively impact the quality of proposals. There is a need to address these challenges and support efficient and effective bidding processes.

[0426] 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.

[0427] In this invention, the server includes a device for acquiring information from public institutions, a device for filtering the acquired information based on unit conditions, and a device for verifying the participation requirements of the filtered information. This makes it possible to efficiently generate and submit bid proposals while reducing user stress and appropriately adjusting document templates according to the user's emotional state.

[0428] "Public institutions" refer to organizations that perform public duties, such as the government and local authorities.

[0429] "Information" refers to public announcements and data related to bidding issued by public institutions.

[0430] The term "device" refers to equipment or a system with a specific function, designed to perform that function.

[0431] "Unit conditions" refer to the standards or requirements that a particular business or entity must meet.

[0432] "Filtering" refers to the process of removing unnecessary information in order to extract useful information.

[0433] "Participation requirements" refer to the standards or qualifications that must be met in order to participate in the bidding process.

[0434] "Verification" refers to the process of checking whether information or conditions are accurate and valid.

[0435] A "document template" refers to a basic format used when creating documents such as proposals and contracts.

[0436] "Emotional state" refers to the user's psychological state or emotional tendencies.

[0437] "Stress" refers to feelings of tension and anxiety that users experience, particularly in the course of performing their work.

[0438] "Adjustment" refers to the process of making appropriate changes or modifications according to the purpose.

[0439] A "proposal" refers to a document that summarizes the details of a proposal related to bidding or contracting.

[0440] A "template" refers to a pre-prepared model for creating documents or data.

[0441] "Submission" refers to the process of sending necessary documents or information to a designated location or system.

[0442] This invention is a system for supporting bidding processes in the construction industry, enabling efficient management of information disseminated by public institutions and the creation of optimal proposals. The system consists of three elements: a server, terminals, and users.

[0443] The server is responsible for automatically collecting bidding information from public institution websites using scraping technology. Technologies used include, for example, Beautiful Soup and Scrapy. The collected information is stored in a database and filtered based on specified criteria.

[0444] When users access the system via their devices, the system verifies participation requirements from filtered information and uses an emotion engine to evaluate the user's psychological state in real time. This evaluation utilizes emotion analysis libraries such as TensorFlow and PyTorch. If a user is experiencing stress, the system provides a reassuring template.

[0445] Furthermore, natural language processing tools such as spaCy and NLTK are used to generate and refine proposals. The server uses machine learning models based on historical data to predict the optimal bid amount. This model learns from past bidding results and provides practical recommendations for future proposals.

[0446] For example, when a user is bidding on a new building construction project, the emotion engine presents a relaxing proposal template to alleviate the time pressure associated with writing a proposal.

[0447] An example of a generated AI model prompt statement is as follows:

[0448] "To help users create proposals for construction bidding projects, we will provide templates and advice that reduce stress and aid in development. Utilize an emotion recognition engine to present a more reassuring style when users are feeling pressured."

[0449] In this way, users can efficiently perform their tasks while smoothly creating optimal proposals.

[0450] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0451] Step 1:

[0452] The server automatically retrieves information from public institution websites using scraping techniques. The input information consists of various tender announcement data, which is then stored in a database in a structured format. Tools such as Beautiful Soup and Scrapy are used to parse HTML and extract data.

[0453] Step 2:

[0454] The server filters information in the database based on user-defined criteria. The input is stored public notice information, and filter conditions are applied to narrow it down to projects related to a specific business. The output is a filtered list of bid projects. SQL queries are used for filtering.

[0455] Step 3:

[0456] The user reviews the filtered information via their device and assesses the participation requirements. The input is a list of filtered cases, and the output is a list of cases that the user can participate in. During the review process, the user determines whether they meet the participation requirements.

[0457] Step 4:

[0458] The server generates proposal templates based on available projects. This process uses natural language processing tools to analyze project characteristics as input and generate proposal templates as output. SpaCy and NLTK are used for the analysis.

[0459] Step 5:

[0460] The server analyzes historical bidding data and uses a machine learning model to predict the optimal bid amount. The input is historical data from a database, and the output is the recommended bid amount. A pre-trained model is used for the prediction.

[0461] Step 6:

[0462] The user reviews the proposal on their device and makes revisions and adjustments as needed. The input is the generated proposal and estimated price, and the output is the final proposal. User intervention optimizes the proposal's content.

[0463] Step 7:

[0464] The emotion engine analyzes the emotional state of users during proposal revision and adjusts templates in real time. Inputs are user operation logs and input data, and the output is the adapted template. TensorFlow and PyTorch are used for emotion analysis.

[0465] Step 8:

[0466] The server automatically submits the completed final version of the proposal and related documents to the public institution's online portal. The input is the final proposal data, and the output is the successful uploading of the proposal online. An automated process via API is used for submission.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] [Third Embodiment]

[0471] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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).

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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".

[0483] This invention is a system for effectively managing public tender and proposal information from public institutions, enabling organizations to efficiently conduct proposal activities based on this information. This system operates through the interconnectedness of three elements: a server, terminals, and users.

[0484] First, the server periodically accesses the websites of public institutions and automatically retrieves public notices using scraping technology. The retrieved information is stored in a database and filtered according to the conditions set by the institution. At this stage, only the matters of interest to the user are extracted.

[0485] Next, the server checks the eligibility requirements for the filtered information. By analyzing the detailed requirements and comparing them with the registered information of the business entity, it determines whether the case is feasible. This result is fed back to the user in real time, leading to the approach of finding the appropriate case.

[0486] Furthermore, for projects whose eligibility has been confirmed, the server analyzes the specifications and evaluation metrics and automatically generates a draft proposal using natural language processing technology. This allows users to efficiently create the basic documents.

[0487] Furthermore, the server runs a machine learning model based on past bidding data to predict the optimal bid amount. This predicted amount is provided to the user as information that helps in the strategic structuring of the proposal.

[0488] Ultimately, users can review a draft proposal generated by the server on their terminal and make adjustments to suit their company's needs. This finalized proposal is automatically submitted to the local government's online portal via the terminal. After submission, the system sends a confirmation notification to the user, ensuring a smooth proposal process.

[0489] As a concrete example, if a local government announces a tender for cleaning services for a new public facility, the server retrieves that information and determines whether the applicant meets the requirements. If the requirements are met, it then generates an optimal proposal and provides the user with the optimal bid amount based on similar past projects. This entire process allows the user to proceed through the bidding process efficiently.

[0490] This system not only significantly reduces the time and effort required for bidding processes, but also improves the accuracy of decision-making, making it an important tool for businesses to efficiently win more projects.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The server periodically accesses public institution websites and uses scraping techniques to collect the latest public notices. This information includes project names, clients, submission deadlines, and requirements. The retrieved information is structured and stored in a database.

[0494] Step 2:

[0495] The server filters the publicly available information in the database based on conditions set in advance by the business entity (e.g., industry, region, amount). This filtering extracts only the cases that match the business entity's interests, and a candidate list is created.

[0496] Step 3:

[0497] Users view a filtered list of potential projects on their device. They can select projects of interest and view the details. Here, they evaluate whether the project's eligibility requirements are suitable for their company.

[0498] Step 4:

[0499] The server analyzes the eligibility requirements for the selected project and compares them with the organization's registration information. Through this process, it automatically determines whether the organization is eligible to participate and notifies the user of the result.

[0500] Step 5:

[0501] The server retrieves specifications and evaluation metrics related to the project and analyzes key items using natural language processing technology. Based on this, it automatically generates a draft proposal and templates. This automatically prepares the basic elements of proposal creation.

[0502] Step 6:

[0503] The server leverages historical bidding data and uses machine learning models to predict the optimal bid amount. This provides users with strategic advice on how much they should propose.

[0504] Step 7:

[0505] Users review the generated proposal and projected bid amount on their device and adjust the content to suit their company's requirements. They then add additional information and make revisions as needed to finalize the proposal.

[0506] Step 8:

[0507] The device automatically uploads the finalized proposal and related documents to the designated public institution's online submission portal. This process also includes granting the necessary authentication credentials. Once the submission is complete, the user will be notified.

[0508] (Example 1)

[0509] 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."

[0510] In traditional bidding and proposal activities, manually acquiring publicly available information and selecting appropriate projects required significant time and effort. Furthermore, creating proposals and estimating optimal bid amounts required specialized knowledge and experience, hindering efficient decision-making. Therefore, there was a need for a system that could automate information acquisition, select optimal projects, efficiently create proposals, and predict optimal bid amounts.

[0511] 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.

[0512] In this invention, the server includes means for acquiring information, means for selecting the acquired information based on conditions, and means for verifying the eligibility requirements for the selected information. This automates the entire process from information collection to selection and verification of eligibility, enabling efficient proposal activities.

[0513] "Means of acquiring information" refers to a function that automatically collects necessary data from specific information sources.

[0514] "Means of sorting based on conditions" refers to a function that filters collected data according to pre-set criteria or conditions.

[0515] "Means of verifying eligibility requirements" refers to a function that determines whether the selected information meets the required eligibility requirements.

[0516] "Means for generating document templates" refers to a function that automatically creates the basic structure of the required document based on confirmed conditions.

[0517] "A means of analyzing past data to predict the optimal amount" refers to a function that analyzes data accumulated in the past to estimate the most effective amount.

[0518] "Means for generating the final version" refers to a function that adjusts automatically generated documents and prepares them for final submission.

[0519] "Method of submitting to the portal" refers to the function of submitting completed documents and related information to an online system.

[0520] "Means of notifying information in real time" refers to functions that instantly transmit the latest information to users.

[0521] "Means for analyzing specifications and evaluation criteria" refers to functions for thoroughly analyzing and understanding the presented specifications and evaluation criteria.

[0522] This invention relates to a system for effectively managing public information of public institutions and for enabling organizations to efficiently carry out proposal activities. This system operates through the coordinated interaction of servers, terminals, and users.

[0523] The server first accesses the websites of public institutions and automatically retrieves public notices using scraping techniques such as Scrapy and BeautifulSoup. The data collected at this stage is stored in a database using MySQL or PostgreSQL. After storage, the information is filtered based on conditions set by the institution, and only announcements of interest to the user are extracted.

[0524] Next, the server analyzes the filtered information to determine eligibility requirements. This analysis utilizes natural language processing technologies (such as NLTK and spaCy) to compare it with the registered information of the business entity. The results of this comparison are notified to the user in real time. Since WebSocket is used for this communication, users receive the information immediately, making it easier for them to make decisions regarding the project.

[0525] For projects where eligibility has been confirmed, the server uses an AI model to automatically generate a draft proposal. This generation process allows users to quickly create a proposal to use as a basis. An example of a specific prompt is, "Please generate a proposal for cleaning services for a new public facility."

[0526] The server also analyzes past bidding data and uses machine learning models such as scikit-learn and TensorFlow to predict the optimal bid amount. This predicted amount is provided to the user as useful information for creating proposals and developing bidding strategies.

[0527] Ultimately, users review the proposal on their devices and make adjustments as needed to suit their specific needs. The completed proposal is automatically submitted to the local government's online portal via the device. After submission, a confirmation notification is sent to the user from the system, allowing for efficient progress in the proposal process.

[0528] This system enables more efficient and accurate bidding and proposal activities than before.

[0529] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0530] Step 1:

[0531] The server periodically accesses public institution websites and retrieves public notices using scraping techniques. This information is input to the server as HTML data. A scraping library (such as BeautifulSoup) is used to extract the necessary text and data and convert it into a structured data format. This converted data becomes the input for the next step.

[0532] Step 2:

[0533] The server stores the retrieved public information in a database. Before saving to the database, the data is formatted and error-checked. Here, structured data is stored in the appropriate tables in a relational database such as MySQL or PostgreSQL. The stored data becomes the input data for the next filtering step.

[0534] Step 3:

[0535] The server filters the public announcement information stored in the database. This filtering process executes SQL queries based on user-defined conditions (e.g., region or industry) and extracts only the information that matches those conditions. This extracted information then becomes the input for the next eligibility verification process.

[0536] Step 4:

[0537] The server verifies the eligibility requirements for the filtered information. This process uses natural language processing (NLTK or spaCy, etc.) to analyze the eligibility requirements from the text data. The analysis results are then compared with the user's registration information to determine if they match. The result of this determination becomes the input for the next feedback step.

[0538] Step 5:

[0539] The server notifies the user of the eligibility assessment results in real time. This notification uses WebSocket to send the assessment results to the client, allowing the user to check them immediately. The assessment results serve as input data for the user to decide whether to start generating the next proposal.

[0540] Step 6:

[0541] The server automatically generates a draft proposal for projects it can participate in. Using an AI generation model, it takes a user-specified prompt (e.g., "Generate a proposal for cleaning services at a new public facility") as input. Based on the prompt, the AI ​​outputs the basic structure of the proposal in text format and provides it to the user.

[0542] Step 7:

[0543] The server uses historical bidding data to predict the optimal bid amount. Using data analysis and machine learning algorithms (such as scikit-learn and TensorFlow), it calculates the optimal amount for filtered bids and provides the results to the user. The predicted amount serves as the foundational data for the strategic structure of the proposal.

[0544] Step 8:

[0545] Users review the generated draft proposal and estimated bid amount on their terminal and make adjustments to suit their needs. They edit the text document through a user-friendly interface and finalize the version. This final version serves as the basis for the next submission process.

[0546] Step 9:

[0547] The terminal automatically submits user-configured proposals to the local government's online portal. The submission process uses the HTTP protocol to upload documents along with necessary authentication information. After submission, the system sends a confirmation notice to the user, allowing them to follow up on the progress of the bidding process.

[0548] (Application Example 1)

[0549] 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."

[0550] In public sector bidding and proposal activities, it is difficult to centrally manage information acquisition and processing, eligibility verification, proposal preparation, appropriate pricing, and electronic payments. Therefore, efficient and accurate process management is required. Furthermore, real-time monitoring of progress is also crucial.

[0551] 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.

[0552] In this invention, the server includes means for acquiring information from public institutions, means for filtering the acquired information based on the conditions of economic entities, and means for verifying the participation criteria of the filtered information. This enables efficient and accurate management of the bidding and proposal process, as well as real-time progress monitoring and settlement processing.

[0553] "Information from public institutions" refers to information regarding tenders and requests for proposals released by public organizations such as the government and local authorities.

[0554] An "economic entity" refers to an organization such as a company or group that participates in a specific bid or proposal.

[0555] "Filtering" is the process of classifying acquired information based on pre-set conditions and extracting only the necessary information.

[0556] "Participation criteria" are the requirements that must be met in order to participate in a particular bid or proposal.

[0557] A "document template" is a model used to create the basic format for proposals and related documents.

[0558] "Past competitive bidding data" refers to the results and related information of competitive bidding that has taken place in the past.

[0559] "Optimal economic conditions" refer to the bid amount or price setting that is considered most favorable in business activities.

[0560] An "electronic system" is an information technology infrastructure for processing and managing information online.

[0561] "To pay electronically" means to make a payment using digital technology.

[0562] "Real-time progress notification" means immediately reporting the progress of a particular activity or process.

[0563] To implement this invention, a system is constructed to efficiently manage the bidding and proposal activities of public institutions. The system consists of a server that periodically acquires information from public institutions and filters it based on the conditions of economic entities, a terminal that checks the participation criteria of the filtered information and automatically generates document templates, and software that predicts optimal economic conditions using past competitive bidding data.

[0564] The server periodically accesses public institution websites using CRON jobs and retrieves information using scraping techniques such as Beautiful Soup. This information is stored in a PostgreSQL database on the server and filtered according to user-defined criteria. Subsequently, document templates are generated using natural language processing libraries such as spaCy.

[0565] The terminal provides an interface for users to review and adjust the generated proposal. After editing the proposal, related fees are paid using Stripe's electronic payment function, and progress is notified in real time via Firebase Cloud Messaging.

[0566] For example, if a user becomes interested in a new bidding project, this system automatically retrieves the information and quickly prepares them for participation. The generated proposal is reviewed on the terminal, modified as needed, and then submitted through the electronic system. By using prompts for the generating AI model, such as "Retrieve newly announced bidding information and generate a draft proposal. Also, settle the participation fees related to the project in real time and notify me of the progress," efficient process operation becomes possible.

[0567] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0568] Step 1:

[0569] The server periodically accesses public institution websites and scrapes information using Beautiful Soup. The input in this step is the website URL, and the output is the retrieved public information. This information is collected on the server as text data and stored in a database for further processing.

[0570] Step 2:

[0571] The server filters the stored information based on user-defined criteria (e.g., project type, budget range, etc.). The input consists of the text data obtained in step 1 and the user's criteria, while the output is the filtered information. The information is processed by a filtering algorithm, and only the important information is selected.

[0572] Step 3:

[0573] The server verifies the participation criteria for the filtered information. The input for this step is the filtered information, and the output is whether or not the applicant is eligible to participate. Information analysis determines whether the necessary criteria are met and checks for any deficiencies.

[0574] Step 4:

[0575] The server uses spaCy to generate a document template based on information that meets the participation criteria. The input is the verified participation criteria information, and the output is a templated proposal. The document is constructed using natural language processing, and an automatically generated template is created.

[0576] Step 5:

[0577] The terminal presents the user with a generated document template, allowing for editing and adjustment. The input is a templated proposal, and the output is the final version of the proposal modified by the user. The user then uses the template as a base to add specific details and improve its completeness.

[0578] Step 6:

[0579] The terminal will process the electronic payment of the participation fee via Stripe. The input will be the final proposal and information on related costs, and the output will be a confirmation of payment completion. After confirming that the payment process was completed securely, proceed to the next step.

[0580] Step 7:

[0581] The terminal submits the final proposal and related documents to the public institution's electronic system. The input is the approved final proposal, and the output is a submission completion notification. The system confirms that the submission has been successfully completed.

[0582] Step 8:

[0583] The server uses Firebase Cloud Messaging to notify the user of the progress in real time. The input is information indicating that submission is complete, and the output is a notification message. The user is immediately informed of the process's progress and can clearly understand when to take the next action.

[0584] 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.

[0585] This invention combines a system that efficiently manages bidding information disseminated by public institutions and supports optimal proposal activities with an emotion engine that recognizes and adapts to user emotions. This system utilizes the collaboration of three elements—server, terminal, and user—to provide multi-functional capabilities.

[0586] First, the server automatically collects public notices from public institution websites using scraping technology. This information includes project details, conditions, and deadlines, and is stored and managed in a database. This information is then filtered to match the user's business entity, and the most relevant information is organized.

[0587] Next, using an emotion engine, the server analyzes the user's emotional state based on user input and operation data. It can determine the user's stress level, excitement, and concentration level, and dynamically adjust the style and content of the proposal template according to their emotions.

[0588] The process continues with users evaluating whether the eligibility requirements for filtered projects are applicable to their company. For approved projects, the server analyzes the specifications and evaluation criteria using natural language processing to quickly generate a draft proposal. During this process, the server uses the results of analyzing past bidding data to recommend the optimal bid amount based on a machine learning model.

[0589] The generated proposals are automatically enhanced with improvement suggestions tailored to the user's psychological state, thanks to an emotion engine that performs real-time emotion recognition. If the user is experiencing stress, a more user-friendly and easy-to-implement template is presented.

[0590] Ultimately, users use their devices to review and refine the proposal content, finalizing the version. The necessary documents are then automatically submitted to the online portal via the device. Even after submitting the proposal, users are continuously supported in making practical improvements for future proposals based on feedback received through the emotion engine.

[0591] As a concrete example, in a bidding process for a new project undertaken by a certain company, the emotional engine provides a more reassuring template based on the pressure a user feels while creating a proposal. This adjustment allows users to prepare bid documents containing sufficient proposal content while minimizing stress.

[0592] This invention aims to facilitate effective bidding processes and improve the success rate of securing eligible projects by realizing a highly adaptable system that takes into account the emotional state of the user.

[0593] The following describes the processing flow.

[0594] Step 1:

[0595] The server accesses designated websites and scrapes the necessary data to collect public sector bidding and proposal information. This information includes project names, target regions, project details, and submission deadlines. The collected data is organized and stored in a database.

[0596] Step 2:

[0597] The server applies conditional filters set by the business entity to the public notice information stored in the database and automatically selects the most relevant cases. These conditions include industry, region, budget range, etc., and the filtering results are notified to the user's terminal.

[0598] Step 3:

[0599] The user reviews a filtered list of cases on their device and selects a case. Based on the selected case, the eligibility requirements are checked, and the emotion engine initiates interaction to reduce the user's psychological burden.

[0600] Step 4:

[0601] The server analyzes the eligibility requirements associated with the selected project and matches them against the user's company information. It verifies whether the eligibility is met and communicates the results to the user in real time.

[0602] Step 5:

[0603] The server analyzes project-related specifications and evaluation metrics using natural language processing technology to automatically generate a draft proposal. It also identifies the user's emotional state using an emotion engine, adjusts the template as needed, and creates a more effective proposal.

[0604] Step 6:

[0605] The server uses a machine learning model that analyzes historical bidding data to predict the optimal bid amount for selected projects. The predicted amount is explicitly presented so that users can strategically incorporate it into their proposals.

[0606] Step 7:

[0607] Users review the proposal template and recommended bid amount provided on their device, and then incorporate any necessary modifications or additional information into their proposal based on their company's strategy and policies. Throughout this process, the sentiment engine continuously monitors the user's emotions and provides advice and fine-tunes the template as needed.

[0608] Step 8:

[0609] The terminal automatically submits the user's finalized proposal and related documents to the designated public institution's online portal. This submission process ensures all required authentication information is properly granted and the submission is officially registered as a new application. Simultaneously, the user receives a notification of submission completion and is provided with feedback for future proposals.

[0610] (Example 2)

[0611] 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."

[0612] Public institutions disseminate a wide variety of bidding information, making it difficult for companies to efficiently manage and appropriately submit proposals. Furthermore, the emotional state of users during the proposal process can influence the quality of proposals, but traditional systems do not take this into account. As a result, proposals are not optimized, leading to a lower success rate in bidding.

[0613] 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.

[0614] In this invention, the server includes means for acquiring public notices from public institutions, means for filtering the acquired public notices based on the conditions of the business entity, and sentiment analysis means for recognizing the user's emotional state and dynamically adjusting the content of the proposal document. This enables companies to efficiently acquire highly relevant bidding information, optimize proposals according to the user's emotions, and improve the success rate of bids.

[0615] "Public institutions" refer to organizations and agencies that operate for the public good, such as the government and local authorities.

[0616] "Public notice information" refers to information issued by public institutions, such as announcements, bidding information, and details including conditions and deadlines.

[0617] A "business entity" refers to a corporation or organization that conducts specific business or operations.

[0618] "Filtering" refers to the process of selecting and narrowing down data or information based on certain criteria or conditions.

[0619] "Emotional analysis methods" refer to technologies and methods for evaluating and recognizing a user's emotions and mental state.

[0620] A "proposal" is a document submitted when participating in a bidding process, and it refers to a document that describes in detail the proposal or plan for the project.

[0621] "Machine learning methods" refer to algorithms and techniques that enable computers to learn from data and make predictions and decisions on their own.

[0622] An "electronic portal" refers to an online platform that provides information and services via the internet.

[0623] This invention is a system for effectively managing bidding information disseminated by public institutions and supporting optimal proposal activities. This system primarily operates through the interaction of servers, terminals, and users.

[0624] The server utilizes web scraping techniques to collect public information from public institution websites. Specifically, it uses libraries such as Python's Beautiful Soup and Scrapy to parse the HTML of web pages and automatically extract data such as project details, conditions, and deadlines. This information is stored and managed in a database.

[0625] The server then uses SQL queries to narrow down the information in the database based on the filter conditions set by the user. This makes it possible to efficiently present bidding information that is highly relevant to the user.

[0626] The server is equipped with emotion analysis capabilities to identify emotions from user interaction data. For example, it uses machine learning models and natural language processing to determine the user's stress level and concentration level based on mouse movements, keyboard input speed, and user facial expression data. This analysis allows proposal templates and content to be dynamically adjusted to match the user's psychological state.

[0627] Users check whether their company's eligibility requirements are met for the filtered projects. For projects that meet the requirements, the server uses an AI model to analyze past bidding data and predict the optimal bid amount. During this process, a draft proposal is automatically generated.

[0628] The terminal sends the final version of the proposal, as confirmed by the user, to the online portal. Data transmission is performed securely and efficiently using an API.

[0629] For example, when a company is creating a proposal for a new project, if they feel tension or pressure, the server's emotion analysis system will detect this. The system then provides a more user-friendly and concise proposal template, helping the user reduce stress and work more efficiently.

[0630] As an example of a prompt, we will use the following sentence: "Please provide a template for creating a project proposal. We require a design that takes into account the user's current emotional state and prioritizes a sense of security and ease of use."

[0631] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0632] Step 1:

[0633] The server automatically collects public notices from government websites using scraping techniques. Specifically, it uses Python's Beautiful Soup or Scrapy libraries to parse the HTML of web pages. The input is the website URL, and the output is data such as project details, conditions, and deadlines. This data is stored in a database for use in the next step.

[0634] Step 2:

[0635] The server filters the publicly available information stored in the database based on the user's business entity criteria. The input requires the user's set filter conditions, and the server uses SQL queries to search the data, narrowing down the information to only what is highly relevant to the user. The output generates a list of related case information.

[0636] Step 3:

[0637] The server uses emotion analysis tools to analyze the user's emotional state. Specifically, it receives user operation data (e.g., keyboard input speed, mouse movements, facial expression data) as input and analyzes it using machine learning models and natural language processing. The output is a determination of the user's stress level and concentration level, and based on this, it generates information to adjust the proposal template.

[0638] Step 4:

[0639] The server dynamically generates proposal templates based on the results of sentiment analysis. In this process, it selects a template appropriate to the user's psychological state and adjusts the template's content. The sentiment assessment results are used as input, and a proposal template optimized for the user is generated as output.

[0640] Step 5:

[0641] Users review filtered project information and determine if their company's eligibility requirements are met. Specifically, they compare the project information with their company's requirements, using the filtered project information as input. A list of suitable projects is generated as output.

[0642] Step 6:

[0643] The server uses a generative AI model to predict the optimal bid amount for suitable projects based on past bidding data. This process uses past bidding data as input and applies machine learning algorithms to generate a recommended bid price to be included in the proposal.

[0644] Step 7:

[0645] The user uses a terminal to review and adjust the proposal content and finalize the version. Specifically, the user enters additional information into a template and modifies the content as needed. The output is a final version of the proposal ready for submission.

[0646] Step 8:

[0647] The terminal sends the final version of the proposal and related documents to an online portal. An API is used for secure and efficient data transmission. The final version of the proposal is required as input, and upon successful submission, confirmation is provided that the proposal has been submitted to the public institution's system.

[0648] (Application Example 2)

[0649] 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."

[0650] In bidding processes, it is crucial to efficiently manage information disseminated by public institutions and quickly create optimal proposals. However, manually reviewing and analyzing a large amount of project information and participation requirements is time-consuming and labor-intensive, and the stress and pressure experienced by users can negatively impact the quality of proposals. There is a need to address these challenges and support efficient and effective bidding processes.

[0651] 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.

[0652] In this invention, the server includes a device for acquiring information from public institutions, a device for filtering the acquired information based on unit conditions, and a device for verifying the participation requirements of the filtered information. This makes it possible to efficiently generate and submit bid proposals while reducing user stress and appropriately adjusting document templates according to the user's emotional state.

[0653] "Public institutions" refer to organizations that perform public duties, such as the government and local authorities.

[0654] "Information" refers to public announcements and data related to bidding issued by public institutions.

[0655] The term "device" refers to equipment or a system with a specific function, designed to perform that function.

[0656] "Unit conditions" refer to the standards or requirements that a particular business or entity must meet.

[0657] "Filtering" refers to the process of removing unnecessary information in order to extract useful information.

[0658] "Participation requirements" refer to the standards or qualifications that must be met in order to participate in the bidding process.

[0659] "Verification" refers to the process of checking whether information or conditions are accurate and valid.

[0660] A "document template" refers to a basic format used when creating documents such as proposals and contracts.

[0661] "Emotional state" refers to the user's psychological state or emotional tendencies.

[0662] "Stress" refers to feelings of tension and anxiety that users experience, particularly in the course of performing their work.

[0663] "Adjustment" refers to the process of making appropriate changes or modifications according to the purpose.

[0664] A "proposal" refers to a document that summarizes the details of a proposal related to bidding or contracting.

[0665] A "template" refers to a pre-prepared model for creating documents or data.

[0666] "Submission" refers to the process of sending necessary documents or information to a designated location or system.

[0667] This invention is a system for supporting bidding processes in the construction industry, enabling efficient management of information disseminated by public institutions and the creation of optimal proposals. The system consists of three elements: a server, terminals, and users.

[0668] The server is responsible for automatically collecting bidding information from public institution websites using scraping technology. Technologies used include, for example, Beautiful Soup and Scrapy. The collected information is stored in a database and filtered based on specified criteria.

[0669] When users access the system via their devices, the system verifies participation requirements from filtered information and uses an emotion engine to evaluate the user's psychological state in real time. This evaluation utilizes emotion analysis libraries such as TensorFlow and PyTorch. If a user is experiencing stress, the system provides a reassuring template.

[0670] Furthermore, natural language processing tools such as spaCy and NLTK are used to generate and refine proposals. The server uses machine learning models based on historical data to predict the optimal bid amount. This model learns from past bidding results and provides practical recommendations for future proposals.

[0671] For example, when a user is bidding on a new building construction project, the emotion engine presents a relaxing proposal template to alleviate the time pressure associated with writing a proposal.

[0672] An example of a generated AI model prompt statement is as follows:

[0673] "To help users create proposals for construction bidding projects, we will provide templates and advice that reduce stress and aid in development. Utilize an emotion recognition engine to present a more reassuring style when users are feeling pressured."

[0674] In this way, users can efficiently perform their tasks while smoothly creating optimal proposals.

[0675] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0676] Step 1:

[0677] The server automatically retrieves information from public institution websites using scraping techniques. The input information consists of various tender announcement data, which is then stored in a database in a structured format. Tools such as Beautiful Soup and Scrapy are used to parse HTML and extract data.

[0678] Step 2:

[0679] The server filters information in the database based on user-defined criteria. The input is stored public notice information, and filter conditions are applied to narrow it down to projects related to a specific business. The output is a filtered list of bid projects. SQL queries are used for filtering.

[0680] Step 3:

[0681] The user reviews the filtered information via their device and assesses the participation requirements. The input is a list of filtered cases, and the output is a list of cases that the user can participate in. During the review process, the user determines whether they meet the participation requirements.

[0682] Step 4:

[0683] The server generates proposal templates based on available projects. This process uses natural language processing tools to analyze project characteristics as input and generate proposal templates as output. SpaCy and NLTK are used for the analysis.

[0684] Step 5:

[0685] The server analyzes historical bidding data and uses a machine learning model to predict the optimal bid amount. The input is historical data from a database, and the output is the recommended bid amount. A pre-trained model is used for the prediction.

[0686] Step 6:

[0687] The user reviews the proposal on their device and makes revisions and adjustments as needed. The input is the generated proposal and estimated price, and the output is the final proposal. User intervention optimizes the proposal's content.

[0688] Step 7:

[0689] The emotion engine analyzes the emotional state of users during proposal revision and adjusts templates in real time. Inputs are user operation logs and input data, and the output is the adapted template. TensorFlow and PyTorch are used for emotion analysis.

[0690] Step 8:

[0691] The server automatically submits the completed final version of the proposal and related documents to the public institution's online portal. The input is the final proposal data, and the output is the successful uploading of the proposal online. An automated process via API is used for submission.

[0692] 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.

[0693] 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.

[0694] 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.

[0695] [Fourth Embodiment]

[0696] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0697] 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.

[0698] 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).

[0699] 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.

[0700] 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.

[0701] 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).

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] 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".

[0709] This invention is a system for effectively managing public tender and proposal information from public institutions, enabling organizations to efficiently conduct proposal activities based on this information. This system operates through the interconnectedness of three elements: a server, terminals, and users.

[0710] First, the server periodically accesses the websites of public institutions and automatically retrieves public notices using scraping technology. The retrieved information is stored in a database and filtered according to the conditions set by the institution. At this stage, only the matters of interest to the user are extracted.

[0711] Next, the server checks the eligibility requirements for the filtered information. By analyzing the detailed requirements and comparing them with the registered information of the business entity, it determines whether the case is feasible. This result is fed back to the user in real time, leading to the approach of finding the appropriate case.

[0712] Furthermore, for projects whose eligibility has been confirmed, the server analyzes the specifications and evaluation metrics and automatically generates a draft proposal using natural language processing technology. This allows users to efficiently create the basic documents.

[0713] Furthermore, the server runs a machine learning model based on past bidding data to predict the optimal bid amount. This predicted amount is provided to the user as information that helps in the strategic structuring of the proposal.

[0714] Ultimately, users can review a draft proposal generated by the server on their terminal and make adjustments to suit their company's needs. This finalized proposal is automatically submitted to the local government's online portal via the terminal. After submission, the system sends a confirmation notification to the user, ensuring a smooth proposal process.

[0715] As a concrete example, if a local government announces a tender for cleaning services for a new public facility, the server retrieves that information and determines whether the applicant meets the requirements. If the requirements are met, it then generates an optimal proposal and provides the user with the optimal bid amount based on similar past projects. This entire process allows the user to proceed through the bidding process efficiently.

[0716] This system not only significantly reduces the time and effort required for bidding processes, but also improves the accuracy of decision-making, making it an important tool for businesses to efficiently win more projects.

[0717] The following describes the processing flow.

[0718] Step 1:

[0719] The server periodically accesses public institution websites and uses scraping techniques to collect the latest public notices. This information includes project names, clients, submission deadlines, and requirements. The retrieved information is structured and stored in a database.

[0720] Step 2:

[0721] The server filters the publicly available information in the database based on conditions set in advance by the business entity (e.g., industry, region, amount). This filtering extracts only the cases that match the business entity's interests, and a candidate list is created.

[0722] Step 3:

[0723] Users view a filtered list of potential projects on their device. They can select projects of interest and view the details. Here, they evaluate whether the project's eligibility requirements are suitable for their company.

[0724] Step 4:

[0725] The server analyzes the eligibility requirements for the selected project and compares them with the organization's registration information. Through this process, it automatically determines whether the organization is eligible to participate and notifies the user of the result.

[0726] Step 5:

[0727] The server retrieves specifications and evaluation metrics related to the project and analyzes key items using natural language processing technology. Based on this, it automatically generates a draft proposal and templates. This automatically prepares the basic elements of proposal creation.

[0728] Step 6:

[0729] The server leverages historical bidding data and uses machine learning models to predict the optimal bid amount. This provides users with strategic advice on how much they should propose.

[0730] Step 7:

[0731] Users review the generated proposal and projected bid amount on their device and adjust the content to suit their company's requirements. They then add additional information and make revisions as needed to finalize the proposal.

[0732] Step 8:

[0733] The device automatically uploads the finalized proposal and related documents to the designated public institution's online submission portal. This process also includes granting the necessary authentication credentials. Once the submission is complete, the user will be notified.

[0734] (Example 1)

[0735] 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".

[0736] In traditional bidding and proposal activities, manually acquiring publicly available information and selecting appropriate projects required significant time and effort. Furthermore, creating proposals and estimating optimal bid amounts required specialized knowledge and experience, hindering efficient decision-making. Therefore, there was a need for a system that could automate information acquisition, select optimal projects, efficiently create proposals, and predict optimal bid amounts.

[0737] 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.

[0738] In this invention, the server includes means for acquiring information, means for selecting the acquired information based on conditions, and means for verifying the eligibility requirements for the selected information. This automates the entire process from information collection to selection and verification of eligibility, enabling efficient proposal activities.

[0739] "Means of acquiring information" refers to a function that automatically collects necessary data from specific information sources.

[0740] "Means of sorting based on conditions" refers to a function that filters collected data according to pre-set criteria or conditions.

[0741] "Means of verifying eligibility requirements" refers to a function that determines whether the selected information meets the required eligibility requirements.

[0742] "Means for generating document templates" refers to a function that automatically creates the basic structure of the required document based on confirmed conditions.

[0743] "A means of analyzing past data to predict the optimal amount" refers to a function that analyzes data accumulated in the past to estimate the most effective amount.

[0744] "Means for generating the final version" refers to a function that adjusts automatically generated documents and prepares them for final submission.

[0745] "Method of submitting to the portal" refers to the function of submitting completed documents and related information to an online system.

[0746] "Means of notifying information in real time" refers to functions that instantly transmit the latest information to users.

[0747] "Means for analyzing specifications and evaluation criteria" refers to functions for thoroughly analyzing and understanding the presented specifications and evaluation criteria.

[0748] This invention relates to a system for effectively managing public information of public institutions and for enabling organizations to efficiently carry out proposal activities. This system operates through the coordinated interaction of servers, terminals, and users.

[0749] The server first accesses the websites of public institutions and automatically retrieves public notices using scraping techniques such as Scrapy and BeautifulSoup. The data collected at this stage is stored in a database using MySQL or PostgreSQL. After storage, the information is filtered based on conditions set by the institution, and only announcements of interest to the user are extracted.

[0750] Next, the server analyzes the filtered information to determine eligibility requirements. This analysis utilizes natural language processing technologies (such as NLTK and spaCy) to compare it with the registered information of the business entity. The results of this comparison are notified to the user in real time. Since WebSocket is used for this communication, users receive the information immediately, making it easier for them to make decisions regarding the project.

[0751] For projects where eligibility has been confirmed, the server uses an AI model to automatically generate a draft proposal. This generation process allows users to quickly create a proposal to use as a basis. An example of a specific prompt is, "Please generate a proposal for cleaning services for a new public facility."

[0752] The server also analyzes past bidding data and uses machine learning models such as scikit-learn and TensorFlow to predict the optimal bid amount. This predicted amount is provided to the user as useful information for creating proposals and developing bidding strategies.

[0753] Ultimately, users review the proposal on their devices and make adjustments as needed to suit their specific needs. The completed proposal is automatically submitted to the local government's online portal via the device. After submission, a confirmation notification is sent to the user from the system, allowing for efficient progress in the proposal process.

[0754] This system enables more efficient and accurate bidding and proposal activities than before.

[0755] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0756] Step 1:

[0757] The server periodically accesses public institution websites and retrieves public notices using scraping techniques. This information is input to the server as HTML data. A scraping library (such as BeautifulSoup) is used to extract the necessary text and data and convert it into a structured data format. This converted data becomes the input for the next step.

[0758] Step 2:

[0759] The server stores the retrieved public information in a database. Before saving to the database, the data is formatted and error-checked. Here, structured data is stored in the appropriate tables in a relational database such as MySQL or PostgreSQL. The stored data becomes the input data for the next filtering step.

[0760] Step 3:

[0761] The server filters the public announcement information stored in the database. This filtering process executes SQL queries based on user-defined conditions (e.g., region or industry) and extracts only the information that matches those conditions. This extracted information then becomes the input for the next eligibility verification process.

[0762] Step 4:

[0763] The server verifies the eligibility requirements for the filtered information. This process uses natural language processing (NLTK or spaCy, etc.) to analyze the eligibility requirements from the text data. The analysis results are then compared with the user's registration information to determine if they match. The result of this determination becomes the input for the next feedback step.

[0764] Step 5:

[0765] The server notifies the user of the eligibility assessment results in real time. This notification uses WebSocket to send the assessment results to the client, allowing the user to check them immediately. The assessment results serve as input data for the user to decide whether to start generating the next proposal.

[0766] Step 6:

[0767] The server automatically generates a draft proposal for projects it can participate in. Using an AI generation model, it takes a user-specified prompt (e.g., "Generate a proposal for cleaning services at a new public facility") as input. Based on the prompt, the AI ​​outputs the basic structure of the proposal in text format and provides it to the user.

[0768] Step 7:

[0769] The server uses historical bidding data to predict the optimal bid amount. Using data analysis and machine learning algorithms (such as scikit-learn and TensorFlow), it calculates the optimal amount for filtered bids and provides the results to the user. The predicted amount serves as the foundational data for the strategic structure of the proposal.

[0770] Step 8:

[0771] Users review the generated draft proposal and estimated bid amount on their terminal and make adjustments to suit their needs. They edit the text document through a user-friendly interface and finalize the version. This final version serves as the basis for the next submission process.

[0772] Step 9:

[0773] The terminal automatically submits user-configured proposals to the local government's online portal. The submission process uses the HTTP protocol to upload documents along with necessary authentication information. After submission, the system sends a confirmation notice to the user, allowing them to follow up on the progress of the bidding process.

[0774] (Application Example 1)

[0775] 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".

[0776] In public sector bidding and proposal activities, it is difficult to centrally manage information acquisition and processing, eligibility verification, proposal preparation, appropriate pricing, and electronic payments. Therefore, efficient and accurate process management is required. Furthermore, real-time monitoring of progress is also crucial.

[0777] 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.

[0778] In this invention, the server includes means for acquiring information from public institutions, means for filtering the acquired information based on the conditions of economic entities, and means for verifying the participation criteria of the filtered information. This enables efficient and accurate management of the bidding and proposal process, as well as real-time progress monitoring and settlement processing.

[0779] "Information from public institutions" refers to information regarding tenders and requests for proposals released by public organizations such as the government and local authorities.

[0780] An "economic entity" refers to an organization such as a company or group that participates in a specific bid or proposal.

[0781] "Filtering" is the process of classifying acquired information based on pre-set conditions and extracting only the necessary information.

[0782] "Participation criteria" are the requirements that must be met in order to participate in a particular bid or proposal.

[0783] A "document template" is a model used to create the basic format for proposals and related documents.

[0784] "Past competitive bidding data" refers to the results and related information of competitive bidding that has taken place in the past.

[0785] "Optimal economic conditions" refer to the bid amount or price setting that is considered most favorable in business activities.

[0786] An "electronic system" is an information technology infrastructure for processing and managing information online.

[0787] "To pay electronically" means to make a payment using digital technology.

[0788] "Real-time progress notification" means immediately reporting the progress of a particular activity or process.

[0789] To implement this invention, a system is constructed to efficiently manage the bidding and proposal activities of public institutions. The system consists of a server that periodically acquires information from public institutions and filters it based on the conditions of economic entities, a terminal that checks the participation criteria of the filtered information and automatically generates document templates, and software that predicts optimal economic conditions using past competitive bidding data.

[0790] The server periodically accesses public institution websites using CRON jobs and retrieves information using scraping techniques such as Beautiful Soup. This information is stored in a PostgreSQL database on the server and filtered according to user-defined criteria. Subsequently, document templates are generated using natural language processing libraries such as spaCy.

[0791] The terminal provides an interface for users to review and adjust the generated proposal. After editing the proposal, related fees are paid using Stripe's electronic payment function, and progress is notified in real time via Firebase Cloud Messaging.

[0792] For example, if a user becomes interested in a new bidding project, this system automatically retrieves the information and quickly prepares them for participation. The generated proposal is reviewed on the terminal, modified as needed, and then submitted through the electronic system. By using prompts for the generating AI model, such as "Retrieve newly announced bidding information and generate a draft proposal. Also, settle the participation fees related to the project in real time and notify me of the progress," efficient process operation becomes possible.

[0793] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0794] Step 1:

[0795] The server periodically accesses public institution websites and scrapes information using Beautiful Soup. The input in this step is the website URL, and the output is the retrieved public information. This information is collected on the server as text data and stored in a database for further processing.

[0796] Step 2:

[0797] The server filters the stored information based on user-defined criteria (e.g., project type, budget range, etc.). The input consists of the text data obtained in step 1 and the user's criteria, while the output is the filtered information. The information is processed by a filtering algorithm, and only the important information is selected.

[0798] Step 3:

[0799] The server verifies the participation criteria for the filtered information. The input for this step is the filtered information, and the output is whether or not the applicant is eligible to participate. Information analysis determines whether the necessary criteria are met and checks for any deficiencies.

[0800] Step 4:

[0801] The server uses spaCy to generate a document template based on information that meets the participation criteria. The input is the verified participation criteria information, and the output is a templated proposal. The document is constructed using natural language processing, and an automatically generated template is created.

[0802] Step 5:

[0803] The terminal presents the user with a generated document template, allowing for editing and adjustment. The input is a templated proposal, and the output is the final version of the proposal modified by the user. The user then uses the template as a base to add specific details and improve its completeness.

[0804] Step 6:

[0805] The terminal will process the electronic payment of the participation fee via Stripe. The input will be the final proposal and information on related costs, and the output will be a confirmation of payment completion. After confirming that the payment process was completed securely, proceed to the next step.

[0806] Step 7:

[0807] The terminal submits the final proposal and related documents to the public institution's electronic system. The input is the approved final proposal, and the output is a submission completion notification. The system confirms that the submission has been successfully completed.

[0808] Step 8:

[0809] The server uses Firebase Cloud Messaging to notify the user of the progress in real time. The input is information indicating that submission is complete, and the output is a notification message. The user is immediately informed of the process's progress and can clearly understand when to take the next action.

[0810] 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.

[0811] This invention combines a system that efficiently manages bidding information disseminated by public institutions and supports optimal proposal activities with an emotion engine that recognizes and adapts to user emotions. This system utilizes the collaboration of three elements—server, terminal, and user—to provide multi-functional capabilities.

[0812] First, the server automatically collects public notices from public institution websites using scraping technology. This information includes project details, conditions, and deadlines, and is stored and managed in a database. This information is then filtered to match the user's business entity, and the most relevant information is organized.

[0813] Next, using an emotion engine, the server analyzes the user's emotional state based on user input and operation data. It can determine the user's stress level, excitement, and concentration level, and dynamically adjust the style and content of the proposal template according to their emotions.

[0814] The process continues with users evaluating whether the eligibility requirements for filtered projects are applicable to their company. For approved projects, the server analyzes the specifications and evaluation criteria using natural language processing to quickly generate a draft proposal. During this process, the server uses the results of analyzing past bidding data to recommend the optimal bid amount based on a machine learning model.

[0815] The generated proposals are automatically enhanced with improvement suggestions tailored to the user's psychological state, thanks to an emotion engine that performs real-time emotion recognition. If the user is experiencing stress, a more user-friendly and easy-to-implement template is presented.

[0816] Ultimately, users use their devices to review and refine the proposal content, finalizing the version. The necessary documents are then automatically submitted to the online portal via the device. Even after submitting the proposal, users are continuously supported in making practical improvements for future proposals based on feedback received through the emotion engine.

[0817] As a concrete example, in a bidding process for a new project undertaken by a certain company, the emotional engine provides a more reassuring template based on the pressure a user feels while creating a proposal. This adjustment allows users to prepare bid documents containing sufficient proposal content while minimizing stress.

[0818] This invention aims to facilitate effective bidding processes and improve the success rate of securing eligible projects by realizing a highly adaptable system that takes into account the emotional state of the user.

[0819] The following describes the processing flow.

[0820] Step 1:

[0821] The server accesses designated websites and scrapes the necessary data to collect public sector bidding and proposal information. This information includes project names, target regions, project details, and submission deadlines. The collected data is organized and stored in a database.

[0822] Step 2:

[0823] The server applies conditional filters set by the business entity to the public notice information stored in the database and automatically selects the most relevant cases. These conditions include industry, region, budget range, etc., and the filtering results are notified to the user's terminal.

[0824] Step 3:

[0825] The user reviews a filtered list of cases on their device and selects a case. Based on the selected case, the eligibility requirements are checked, and the emotion engine initiates interaction to reduce the user's psychological burden.

[0826] Step 4:

[0827] The server analyzes the eligibility requirements associated with the selected project and matches them against the user's company information. It verifies whether the eligibility is met and communicates the results to the user in real time.

[0828] Step 5:

[0829] The server analyzes project-related specifications and evaluation metrics using natural language processing technology to automatically generate a draft proposal. It also identifies the user's emotional state using an emotion engine, adjusts the template as needed, and creates a more effective proposal.

[0830] Step 6:

[0831] The server uses a machine learning model that analyzes historical bidding data to predict the optimal bid amount for selected projects. The predicted amount is explicitly presented so that users can strategically incorporate it into their proposals.

[0832] Step 7:

[0833] Users review the proposal template and recommended bid amount provided on their device, and then incorporate any necessary modifications or additional information into their proposal based on their company's strategy and policies. Throughout this process, the sentiment engine continuously monitors the user's emotions and provides advice and fine-tunes the template as needed.

[0834] Step 8:

[0835] The terminal automatically submits the user's finalized proposal and related documents to the designated public institution's online portal. This submission process ensures all required authentication information is properly granted and the submission is officially registered as a new application. Simultaneously, the user receives a notification of submission completion and is provided with feedback for future proposals.

[0836] (Example 2)

[0837] 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".

[0838] Public institutions disseminate a wide variety of bidding information, making it difficult for companies to efficiently manage and appropriately submit proposals. Furthermore, the emotional state of users during the proposal process can influence the quality of proposals, but traditional systems do not take this into account. As a result, proposals are not optimized, leading to a lower success rate in bidding.

[0839] 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.

[0840] In this invention, the server includes means for acquiring public notices from public institutions, means for filtering the acquired public notices based on the conditions of the business entity, and sentiment analysis means for recognizing the user's emotional state and dynamically adjusting the content of the proposal document. This enables companies to efficiently acquire highly relevant bidding information, optimize proposals according to the user's emotions, and improve the success rate of bids.

[0841] "Public institutions" refer to organizations and agencies that operate for the public good, such as the government and local authorities.

[0842] "Public notice information" refers to information issued by public institutions, such as announcements, bidding information, and details including conditions and deadlines.

[0843] A "business entity" refers to a corporation or organization that conducts specific business or operations.

[0844] "Filtering" refers to the process of selecting and narrowing down data or information based on certain criteria or conditions.

[0845] "Emotional analysis methods" refer to technologies and methods for evaluating and recognizing a user's emotions and mental state.

[0846] A "proposal" is a document submitted when participating in a bidding process, and it refers to a document that describes in detail the proposal or plan for the project.

[0847] "Machine learning methods" refer to algorithms and techniques that enable computers to learn from data and make predictions and decisions on their own.

[0848] An "electronic portal" refers to an online platform that provides information and services via the internet.

[0849] This invention is a system for effectively managing bidding information disseminated by public institutions and supporting optimal proposal activities. This system primarily operates through the interaction of servers, terminals, and users.

[0850] The server utilizes web scraping techniques to collect public information from public institution websites. Specifically, it uses libraries such as Python's Beautiful Soup and Scrapy to parse the HTML of web pages and automatically extract data such as project details, conditions, and deadlines. This information is stored and managed in a database.

[0851] The server then uses SQL queries to narrow down the information in the database based on the filter conditions set by the user. This makes it possible to efficiently present bidding information that is highly relevant to the user.

[0852] The server is equipped with emotion analysis capabilities to identify emotions from user interaction data. For example, it uses machine learning models and natural language processing to determine the user's stress level and concentration level based on mouse movements, keyboard input speed, and user facial expression data. This analysis allows proposal templates and content to be dynamically adjusted to match the user's psychological state.

[0853] Users check whether their company's eligibility requirements are met for the filtered projects. For projects that meet the requirements, the server uses an AI model to analyze past bidding data and predict the optimal bid amount. During this process, a draft proposal is automatically generated.

[0854] The terminal sends the final version of the proposal, as confirmed by the user, to the online portal. Data transmission is performed securely and efficiently using an API.

[0855] For example, when a company is creating a proposal for a new project, if they feel tension or pressure, the server's emotion analysis system will detect this. The system then provides a more user-friendly and concise proposal template, helping the user reduce stress and work more efficiently.

[0856] As an example of a prompt, we will use the following sentence: "Please provide a template for creating a project proposal. We require a design that takes into account the user's current emotional state and prioritizes a sense of security and ease of use."

[0857] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0858] Step 1:

[0859] The server automatically collects public notices from government websites using scraping techniques. Specifically, it uses Python's Beautiful Soup or Scrapy libraries to parse the HTML of web pages. The input is the website URL, and the output is data such as project details, conditions, and deadlines. This data is stored in a database for use in the next step.

[0860] Step 2:

[0861] The server filters the publicly available information stored in the database based on the user's business entity criteria. The input requires the user's set filter conditions, and the server uses SQL queries to search the data, narrowing down the information to only what is highly relevant to the user. The output generates a list of related case information.

[0862] Step 3:

[0863] The server uses emotion analysis tools to analyze the user's emotional state. Specifically, it receives user operation data (e.g., keyboard input speed, mouse movements, facial expression data) as input and analyzes it using machine learning models and natural language processing. The output is a determination of the user's stress level and concentration level, and based on this, it generates information to adjust the proposal template.

[0864] Step 4:

[0865] The server dynamically generates proposal templates based on the results of sentiment analysis. In this process, it selects a template appropriate to the user's psychological state and adjusts the template's content. The sentiment assessment results are used as input, and a proposal template optimized for the user is generated as output.

[0866] Step 5:

[0867] Users review filtered project information and determine if their company's eligibility requirements are met. Specifically, they compare the project information with their company's requirements, using the filtered project information as input. A list of suitable projects is generated as output.

[0868] Step 6:

[0869] The server uses a generative AI model to predict the optimal bid amount for suitable projects based on past bidding data. This process uses past bidding data as input and applies machine learning algorithms to generate a recommended bid price to be included in the proposal.

[0870] Step 7:

[0871] The user uses a terminal to review and adjust the proposal content and finalize the version. Specifically, the user enters additional information into a template and modifies the content as needed. The output is a final version of the proposal ready for submission.

[0872] Step 8:

[0873] The terminal sends the final version of the proposal and related documents to an online portal. An API is used for secure and efficient data transmission. The final version of the proposal is required as input, and upon successful submission, confirmation is provided that the proposal has been submitted to the public institution's system.

[0874] (Application Example 2)

[0875] 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".

[0876] In bidding processes, it is crucial to efficiently manage information disseminated by public institutions and quickly create optimal proposals. However, manually reviewing and analyzing a large amount of project information and participation requirements is time-consuming and labor-intensive, and the stress and pressure experienced by users can negatively impact the quality of proposals. There is a need to address these challenges and support efficient and effective bidding processes.

[0877] 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.

[0878] In this invention, the server includes a device for acquiring information from public institutions, a device for filtering the acquired information based on unit conditions, and a device for verifying the participation requirements of the filtered information. This makes it possible to efficiently generate and submit bid proposals while reducing user stress and appropriately adjusting document templates according to the user's emotional state.

[0879] "Public institutions" refer to organizations that perform public duties, such as the government and local authorities.

[0880] "Information" refers to public announcements and data related to bidding issued by public institutions.

[0881] The term "device" refers to equipment or a system with a specific function, designed to perform that function.

[0882] "Unit conditions" refer to the standards or requirements that a particular business or entity must meet.

[0883] "Filtering" refers to the process of removing unnecessary information in order to extract useful information.

[0884] "Participation requirements" refer to the standards or qualifications that must be met in order to participate in the bidding process.

[0885] "Verification" refers to the process of checking whether information or conditions are accurate and valid.

[0886] A "document template" refers to a basic format used when creating documents such as proposals and contracts.

[0887] "Emotional state" refers to the user's psychological state or emotional tendencies.

[0888] "Stress" refers to feelings of tension and anxiety that users experience, particularly in the course of performing their work.

[0889] "Adjustment" refers to the process of making appropriate changes or modifications according to the purpose.

[0890] A "proposal" refers to a document that summarizes the details of a proposal related to bidding or contracting.

[0891] A "template" refers to a pre-prepared model for creating documents or data.

[0892] "Submission" refers to the process of sending necessary documents or information to a designated location or system.

[0893] This invention is a system for supporting bidding processes in the construction industry, enabling efficient management of information disseminated by public institutions and the creation of optimal proposals. The system consists of three elements: a server, terminals, and users.

[0894] The server is responsible for automatically collecting bidding information from public institution websites using scraping technology. Technologies used include, for example, Beautiful Soup and Scrapy. The collected information is stored in a database and filtered based on specified criteria.

[0895] When users access the system via their devices, the system verifies participation requirements from filtered information and uses an emotion engine to evaluate the user's psychological state in real time. This evaluation utilizes emotion analysis libraries such as TensorFlow and PyTorch. If a user is experiencing stress, the system provides a reassuring template.

[0896] Furthermore, natural language processing tools such as spaCy and NLTK are used to generate and refine proposals. The server uses machine learning models based on historical data to predict the optimal bid amount. This model learns from past bidding results and provides practical recommendations for future proposals.

[0897] For example, when a user is bidding on a new building construction project, the emotion engine presents a relaxing proposal template to alleviate the time pressure associated with writing a proposal.

[0898] An example of a generated AI model prompt statement is as follows:

[0899] "To help users create proposals for construction bidding projects, we will provide templates and advice that reduce stress and aid in development. Utilize an emotion recognition engine to present a more reassuring style when users are feeling pressured."

[0900] In this way, users can efficiently perform their tasks while smoothly creating optimal proposals.

[0901] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0902] Step 1:

[0903] The server automatically retrieves information from public institution websites using scraping techniques. The input information consists of various tender announcement data, which is then stored in a database in a structured format. Tools such as Beautiful Soup and Scrapy are used to parse HTML and extract data.

[0904] Step 2:

[0905] The server filters information in the database based on user-defined criteria. The input is stored public notice information, and filter conditions are applied to narrow it down to projects related to a specific business. The output is a filtered list of bid projects. SQL queries are used for filtering.

[0906] Step 3:

[0907] The user reviews the filtered information via their device and assesses the participation requirements. The input is a list of filtered cases, and the output is a list of cases that the user can participate in. During the review process, the user determines whether they meet the participation requirements.

[0908] Step 4:

[0909] The server generates proposal templates based on available projects. This process uses natural language processing tools to analyze project characteristics as input and generate proposal templates as output. SpaCy and NLTK are used for the analysis.

[0910] Step 5:

[0911] The server analyzes historical bidding data and uses a machine learning model to predict the optimal bid amount. The input is historical data from a database, and the output is the recommended bid amount. A pre-trained model is used for the prediction.

[0912] Step 6:

[0913] The user reviews the proposal on their device and makes revisions and adjustments as needed. The input is the generated proposal and estimated price, and the output is the final proposal. User intervention optimizes the proposal's content.

[0914] Step 7:

[0915] The emotion engine analyzes the emotional state of users during proposal revision and adjusts templates in real time. Inputs are user operation logs and input data, and the output is the adapted template. TensorFlow and PyTorch are used for emotion analysis.

[0916] Step 8:

[0917] The server automatically submits the completed final version of the proposal and related documents to the public institution's online portal. The input is the final proposal data, and the output is the successful uploading of the proposal online. An automated process via API is used for submission.

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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.

[0924] 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.

[0925] 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.

[0926] 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."

[0927] 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.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] 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.

[0932] 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.

[0933] 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.

[0934] 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.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] The following is further disclosed regarding the embodiments described above.

[0940] (Claim 1)

[0941] Means of obtaining public information from public institutions,

[0942] A means of filtering the acquired publicly announced information based on the conditions of the business entity,

[0943] A means of verifying the eligibility requirements for participation in filtered public notices,

[0944] A means of generating a proposal template based on confirmed requirements,

[0945] A method for analyzing past bidding data to predict the optimal bid amount,

[0946] A means of adjusting the generated proposal and producing the final version,

[0947] A means of submitting the final version and related documents to the public institution's online portal,

[0948] A system that includes this.

[0949] (Claim 2)

[0950] The system according to claim 1, further comprising means for analyzing public information using natural language processing for proposal generation.

[0951] (Claim 3)

[0952] The system according to claim 1, comprising means of using a machine learning model that uses historical bidding data to predict the optimal bid amount.

[0953] "Example 1"

[0954] (Claim 1)

[0955] Means of obtaining information,

[0956] A means of sorting acquired information based on conditions,

[0957] A means of verifying the eligibility requirements for the selected information,

[0958] A means for generating a document template based on confirmed conditions,

[0959] A method for analyzing past data to predict the optimal amount,

[0960] A means of adjusting the generated document and producing the final version,

[0961] A means of submitting the final version and related documents to the portal,

[0962] A means of notifying information in real time,

[0963] A means of analyzing specifications and evaluation criteria,

[0964] A system that includes this.

[0965] (Claim 2)

[0966] The system according to claim 1, further comprising means for analyzing information using natural language processing for document generation.

[0967] (Claim 3)

[0968] The system according to claim 1, comprising means of using a machine learning model that uses historical data to predict the optimal amount.

[0969] "Application Example 1"

[0970] (Claim 1)

[0971] Means of obtaining information from public institutions,

[0972] A means of filtering acquired information based on the conditions of economic entities,

[0973] A means of verifying the participation criteria for filtered information,

[0974] A means of generating a document template based on confirmed standards,

[0975] A method for analyzing past competitive bidding data to predict optimal economic conditions,

[0976] A means of adjusting the generated document and producing the final version,

[0977] Means for submitting the final version and related documents to the electronic system of a public institution,

[0978] A means of settling related expenses electronically,

[0979] A means of notifying progress in real time,

[0980] A system that includes this.

[0981] (Claim 2)

[0982] The system according to claim 1, further comprising means for analyzing information using natural language processing for document generation.

[0983] (Claim 3)

[0984] The system according to claim 1, comprising means of using a machine learning model that uses historical competitive bidding data to predict optimal economic conditions.

[0985] "Example 2 of combining an emotion engine"

[0986] (Claim 1)

[0987] Means of obtaining public information from public institutions,

[0988] A means of filtering the acquired publicly announced information based on the conditions of the business entity,

[0989] A means of verifying the eligibility requirements for participation in filtered public notices,

[0990] A means of generating the proposal format based on the confirmed requirements,

[0991] A method for analyzing past bidding information to predict the optimal bid amount,

[0992] A means of adjusting the generated proposal and producing the final version,

[0993] A means of transmitting the final version and related documents to the electronic portal of a public institution,

[0994] A sentiment analysis means that recognizes the user's emotional state and dynamically adjusts the content of the proposed document,

[0995] A system that includes this.

[0996] (Claim 2)

[0997] The system according to claim 1, further comprising means for analyzing public information using natural language processing for proposal generation.

[0998] (Claim 3)

[0999] The system according to claim 1, comprising means of using a machine learning method that uses past bidding information to predict the optimal bid amount.

[1000] "Application example 2 when combining with an emotional engine"

[1001] (Claim 1)

[1002] A device for acquiring information from public institutions,

[1003] A device that filters acquired information based on unit conditions,

[1004] A device to verify the participation requirements for filtered information,

[1005] A device that generates document templates based on confirmed requirements,

[1006] A device that analyzes past data to predict the optimal amount,

[1007] A device that adjusts the generated document and produces the final version,

[1008] A device for submitting the final version and related documents to a public institution's online platform,

[1009] A device that analyzes the user's emotional state and dynamically adjusts document templates according to that emotion,

[1010] A system that includes this.

[1011] (Claim 2)

[1012] The system according to claim 1, further comprising a device for analyzing information using natural language processing for document generation.

[1013] (Claim 3)

[1014] The system according to claim 1, comprising an apparatus that uses a learning model that uses historical data to predict the optimal amount. [Explanation of symbols]

[1015] 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. Means of obtaining public information from public institutions, A means of filtering the acquired publicly announced information based on the conditions of the business entity, A means of verifying the eligibility requirements for participation in filtered public notices, A means of generating a proposal template based on confirmed requirements, A method for analyzing past bidding data to predict the optimal bid amount, A means of adjusting the generated proposal and producing the final version, A means of submitting the final version and related documents to the public institution's online portal, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing public information using natural language processing for the purpose of generating a proposal.

3. The system according to claim 1, comprising means of using a machine learning model that uses historical bidding data to predict the optimal bid amount.

Images